From c897c13dde3bb413e723317c0579781fb6045a8b Mon Sep 17 00:00:00 2001 From: Janek van Oirschot Date: Mon, 30 Sep 2024 11:43:34 +0100 Subject: [PATCH] [AMDGPU] Convert AMDGPUResourceUsageAnalysis pass from Module to MF pass (#102913) Converts AMDGPUResourceUsageAnalysis pass from Module to MachineFunction pass. Moves function resource info propagation to to MC layer (through helpers in AMDGPUMCResourceInfo) by generating MCExprs for every function resource which the emitters have been prepped for. Fixes https://github.com/llvm/llvm-project/issues/64863 --- .../amdgcn-machine-analysis-remarks.cl | 2 +- llvm/docs/AMDGPUUsage.rst | 49 ++ llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp | 266 +++++++-- llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h | 14 +- .../Target/AMDGPU/AMDGPUMCResourceInfo.cpp | 224 ++++++++ llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.h | 102 ++++ .../AMDGPU/AMDGPUResourceUsageAnalysis.cpp | 147 +---- .../AMDGPU/AMDGPUResourceUsageAnalysis.h | 40 +- llvm/lib/Target/AMDGPU/CMakeLists.txt | 1 + .../MCTargetDesc/AMDGPUTargetStreamer.cpp | 41 ++ .../MCTargetDesc/AMDGPUTargetStreamer.h | 23 + .../Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp | 10 +- .../CodeGen/AMDGPU/agpr-register-count.ll | 33 +- .../amdhsa-kernarg-preload-num-sgprs.ll | 8 +- .../amdpal-metadata-agpr-register-count.ll | 4 +- ...-amdgpu-flat-work-group-size-vgpr-limit.ll | 51 +- .../AMDGPU/call-alias-register-usage-agpr.ll | 16 +- .../AMDGPU/call-alias-register-usage0.ll | 8 +- .../AMDGPU/call-alias-register-usage1.ll | 11 +- .../AMDGPU/call-alias-register-usage2.ll | 11 +- .../AMDGPU/call-alias-register-usage3.ll | 11 +- .../AMDGPU/call-graph-register-usage.ll | 86 ++- .../test/CodeGen/AMDGPU/cndmask-no-def-vcc.ll | 1 + .../AMDGPU/codegen-internal-only-func.ll | 6 +- llvm/test/CodeGen/AMDGPU/flat-scratch-reg.ll | 70 +-- .../CodeGen/AMDGPU/function-resource-usage.ll | 531 ++++++++++++++++++ .../AMDGPU/inline-asm-reserved-regs.ll | 2 +- .../CodeGen/AMDGPU/insert-delay-alu-bug.ll | 24 +- llvm/test/CodeGen/AMDGPU/ipra.ll | 22 +- llvm/test/CodeGen/AMDGPU/llc-pipeline.ll | 45 +- .../AMDGPU/lower-module-lds-offsets.ll | 26 +- .../AMDGPU/module-lds-false-sharing.ll | 99 ++-- llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll | 2 +- llvm/test/CodeGen/AMDGPU/recursion.ll | 28 +- .../CodeGen/AMDGPU/register-count-comments.ll | 2 +- .../AMDGPU/resource-optimization-remarks.ll | 22 +- .../AMDGPU/resource-usage-dead-function.ll | 13 +- 37 files changed, 1566 insertions(+), 485 deletions(-) create mode 100644 llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp create mode 100644 llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.h create mode 100644 llvm/test/CodeGen/AMDGPU/function-resource-usage.ll diff --git a/clang/test/Frontend/amdgcn-machine-analysis-remarks.cl b/clang/test/Frontend/amdgcn-machine-analysis-remarks.cl index a05e21b37b9127..f15130d5f8b611 100644 --- a/clang/test/Frontend/amdgcn-machine-analysis-remarks.cl +++ b/clang/test/Frontend/amdgcn-machine-analysis-remarks.cl @@ -2,7 +2,7 @@ // RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu gfx908 -Rpass-analysis=kernel-resource-usage -S -O0 -verify %s -o /dev/null // expected-remark@+10 {{Function Name: foo}} -// expected-remark@+9 {{ SGPRs: 13}} +// expected-remark@+9 {{ TotalSGPRs: 13}} // expected-remark@+8 {{ VGPRs: 10}} // expected-remark@+7 {{ AGPRs: 12}} // expected-remark@+6 {{ ScratchSize [bytes/lane]: 0}} diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst index 9e11b13c101d47..38300863f7889a 100644 --- a/llvm/docs/AMDGPUUsage.rst +++ b/llvm/docs/AMDGPUUsage.rst @@ -1757,6 +1757,55 @@ As part of the AMDGPU MC layer, AMDGPU provides the following target specific =================== ================= ======================================================== +Function Resource Usage +----------------------- + +A function's resource usage depends on each of its callees' resource usage. The +expressions used to denote resource usage reflect this by propagating each +callees' equivalent expressions. Said expressions are emitted as symbols by the +compiler when compiling to either assembly or object format and should not be +overwritten or redefined. + +The following describes all emitted function resource usage symbols: + + .. table:: Function Resource Usage: + :name: function-usage-table + + ===================================== ========= ========================================= =============================================================================== + Symbol Type Description Example + ===================================== ========= ========================================= =============================================================================== + .num_vgpr Integer Number of VGPRs used by , .set foo.num_vgpr, max(32, bar.num_vgpr, baz.num_vgpr) + worst case of itself and its callees' + VGPR use + .num_agpr Integer Number of AGPRs used by , .set foo.num_agpr, max(35, bar.num_agpr) + worst case of itself and its callees' + AGPR use + .numbered_sgpr Integer Number of SGPRs used by , .set foo.num_sgpr, 21 + worst case of itself and its callees' + SGPR use (without any of the implicitly + used SGPRs) + .private_seg_size Integer Total stack size required for .set foo.private_seg_size, 16+max(bar.private_seg_size, baz.private_seg_size) + , expression is the + locally used stack size + the worst case + callee + .uses_vcc Bool Whether , or any of its .set foo.uses_vcc, or(0, bar.uses_vcc) + callees, uses vcc + .uses_flat_scratch Bool Whether , or any of its .set foo.uses_flat_scratch, 1 + callees, uses flat scratch or not + .has_dyn_sized_stack Bool Whether , or any of its .set foo.has_dyn_sized_stack, 1 + callees, is dynamically sized + .has_recursion Bool Whether , or any of its .set foo.has_recursion, 0 + callees, contains recursion + .has_indirect_call Bool Whether , or any of its .set foo.has_indirect_call, max(0, bar.has_indirect_call) + callees, contains an indirect call + ===================================== ========= ========================================= =============================================================================== + +Futhermore, three symbols are additionally emitted describing the compilation +unit's worst case (i.e, maxima) ``num_vgpr``, ``num_agpr``, and +``numbered_sgpr`` which may be referenced and used by the aforementioned +symbolic expressions. These three symbols are ``amdgcn.max_num_vgpr``, +``amdgcn.max_num_agpr``, and ``amdgcn.max_num_sgpr``. + .. _amdgpu-elf-code-object: ELF Code Object diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp index 682c29457c35ee..4f6633d8027c70 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp @@ -18,6 +18,7 @@ #include "AMDGPUAsmPrinter.h" #include "AMDGPU.h" #include "AMDGPUHSAMetadataStreamer.h" +#include "AMDGPUMCResourceInfo.h" #include "AMDGPUResourceUsageAnalysis.h" #include "GCNSubtarget.h" #include "MCTargetDesc/AMDGPUInstPrinter.h" @@ -33,6 +34,7 @@ #include "llvm/Analysis/OptimizationRemarkEmitter.h" #include "llvm/BinaryFormat/ELF.h" #include "llvm/CodeGen/MachineFrameInfo.h" +#include "llvm/CodeGen/MachineModuleInfo.h" #include "llvm/CodeGen/MachineOptimizationRemarkEmitter.h" #include "llvm/IR/DiagnosticInfo.h" #include "llvm/MC/MCAssembler.h" @@ -359,6 +361,127 @@ bool AMDGPUAsmPrinter::doInitialization(Module &M) { return AsmPrinter::doInitialization(M); } +void AMDGPUAsmPrinter::validateMCResourceInfo(Function &F) { + if (F.isDeclaration() || !AMDGPU::isModuleEntryFunctionCC(F.getCallingConv())) + return; + + using RIK = MCResourceInfo::ResourceInfoKind; + const GCNSubtarget &STM = TM.getSubtarget(F); + + auto TryGetMCExprValue = [](const MCExpr *Value, uint64_t &Res) -> bool { + int64_t Val; + if (Value->evaluateAsAbsolute(Val)) { + Res = Val; + return true; + } + return false; + }; + + const uint64_t MaxScratchPerWorkitem = + STM.getMaxWaveScratchSize() / STM.getWavefrontSize(); + MCSymbol *ScratchSizeSymbol = + RI.getSymbol(F.getName(), RIK::RIK_PrivateSegSize, OutContext); + uint64_t ScratchSize; + if (ScratchSizeSymbol->isVariable() && + TryGetMCExprValue(ScratchSizeSymbol->getVariableValue(), ScratchSize) && + ScratchSize > MaxScratchPerWorkitem) { + DiagnosticInfoStackSize DiagStackSize(F, ScratchSize, MaxScratchPerWorkitem, + DS_Error); + F.getContext().diagnose(DiagStackSize); + } + + // Validate addressable scalar registers (i.e., prior to added implicit + // SGPRs). + MCSymbol *NumSGPRSymbol = + RI.getSymbol(F.getName(), RIK::RIK_NumSGPR, OutContext); + if (STM.getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS && + !STM.hasSGPRInitBug()) { + unsigned MaxAddressableNumSGPRs = STM.getAddressableNumSGPRs(); + uint64_t NumSgpr; + if (NumSGPRSymbol->isVariable() && + TryGetMCExprValue(NumSGPRSymbol->getVariableValue(), NumSgpr) && + NumSgpr > MaxAddressableNumSGPRs) { + DiagnosticInfoResourceLimit Diag(F, "addressable scalar registers", + NumSgpr, MaxAddressableNumSGPRs, + DS_Error, DK_ResourceLimit); + F.getContext().diagnose(Diag); + return; + } + } + + MCSymbol *VCCUsedSymbol = + RI.getSymbol(F.getName(), RIK::RIK_UsesVCC, OutContext); + MCSymbol *FlatUsedSymbol = + RI.getSymbol(F.getName(), RIK::RIK_UsesFlatScratch, OutContext); + uint64_t VCCUsed, FlatUsed, NumSgpr; + + if (NumSGPRSymbol->isVariable() && VCCUsedSymbol->isVariable() && + FlatUsedSymbol->isVariable() && + TryGetMCExprValue(NumSGPRSymbol->getVariableValue(), NumSgpr) && + TryGetMCExprValue(VCCUsedSymbol->getVariableValue(), VCCUsed) && + TryGetMCExprValue(FlatUsedSymbol->getVariableValue(), FlatUsed)) { + + // Recomputes NumSgprs + implicit SGPRs but all symbols should now be + // resolvable. + NumSgpr += IsaInfo::getNumExtraSGPRs( + &STM, VCCUsed, FlatUsed, + getTargetStreamer()->getTargetID()->isXnackOnOrAny()); + if (STM.getGeneration() <= AMDGPUSubtarget::SEA_ISLANDS || + STM.hasSGPRInitBug()) { + unsigned MaxAddressableNumSGPRs = STM.getAddressableNumSGPRs(); + if (NumSgpr > MaxAddressableNumSGPRs) { + DiagnosticInfoResourceLimit Diag(F, "scalar registers", NumSgpr, + MaxAddressableNumSGPRs, DS_Error, + DK_ResourceLimit); + F.getContext().diagnose(Diag); + return; + } + } + + MCSymbol *NumVgprSymbol = + RI.getSymbol(F.getName(), RIK::RIK_NumVGPR, OutContext); + MCSymbol *NumAgprSymbol = + RI.getSymbol(F.getName(), RIK::RIK_NumAGPR, OutContext); + uint64_t NumVgpr, NumAgpr; + + MachineModuleInfo &MMI = + getAnalysis().getMMI(); + MachineFunction *MF = MMI.getMachineFunction(F); + if (MF && NumVgprSymbol->isVariable() && NumAgprSymbol->isVariable() && + TryGetMCExprValue(NumVgprSymbol->getVariableValue(), NumVgpr) && + TryGetMCExprValue(NumAgprSymbol->getVariableValue(), NumAgpr)) { + const SIMachineFunctionInfo &MFI = *MF->getInfo(); + unsigned MaxWaves = MFI.getMaxWavesPerEU(); + uint64_t TotalNumVgpr = + getTotalNumVGPRs(STM.hasGFX90AInsts(), NumAgpr, NumVgpr); + uint64_t NumVGPRsForWavesPerEU = std::max( + {TotalNumVgpr, (uint64_t)1, (uint64_t)STM.getMinNumVGPRs(MaxWaves)}); + uint64_t NumSGPRsForWavesPerEU = std::max( + {NumSgpr, (uint64_t)1, (uint64_t)STM.getMinNumSGPRs(MaxWaves)}); + const MCExpr *OccupancyExpr = AMDGPUMCExpr::createOccupancy( + STM.computeOccupancy(F, MFI.getLDSSize()), + MCConstantExpr::create(NumSGPRsForWavesPerEU, OutContext), + MCConstantExpr::create(NumVGPRsForWavesPerEU, OutContext), STM, + OutContext); + uint64_t Occupancy; + + const auto [MinWEU, MaxWEU] = AMDGPU::getIntegerPairAttribute( + F, "amdgpu-waves-per-eu", {0, 0}, true); + + if (TryGetMCExprValue(OccupancyExpr, Occupancy) && Occupancy < MinWEU) { + DiagnosticInfoOptimizationFailure Diag( + F, F.getSubprogram(), + "failed to meet occupancy target given by 'amdgpu-waves-per-eu' in " + "'" + + F.getName() + "': desired occupancy was " + Twine(MinWEU) + + ", final occupancy is " + Twine(Occupancy)); + F.getContext().diagnose(Diag); + return; + } + } + } +} + bool AMDGPUAsmPrinter::doFinalization(Module &M) { // Pad with s_code_end to help tools and guard against instruction prefetch // causing stale data in caches. Arguably this should be done by the linker, @@ -371,25 +494,24 @@ bool AMDGPUAsmPrinter::doFinalization(Module &M) { getTargetStreamer()->EmitCodeEnd(STI); } - return AsmPrinter::doFinalization(M); -} + // Assign expressions which can only be resolved when all other functions are + // known. + RI.finalize(OutContext); -// Print comments that apply to both callable functions and entry points. -void AMDGPUAsmPrinter::emitCommonFunctionComments( - uint32_t NumVGPR, std::optional NumAGPR, uint32_t TotalNumVGPR, - uint32_t NumSGPR, uint64_t ScratchSize, uint64_t CodeSize, - const AMDGPUMachineFunction *MFI) { - OutStreamer->emitRawComment(" codeLenInByte = " + Twine(CodeSize), false); - OutStreamer->emitRawComment(" NumSgprs: " + Twine(NumSGPR), false); - OutStreamer->emitRawComment(" NumVgprs: " + Twine(NumVGPR), false); - if (NumAGPR) { - OutStreamer->emitRawComment(" NumAgprs: " + Twine(*NumAGPR), false); - OutStreamer->emitRawComment(" TotalNumVgprs: " + Twine(TotalNumVGPR), - false); - } - OutStreamer->emitRawComment(" ScratchSize: " + Twine(ScratchSize), false); - OutStreamer->emitRawComment(" MemoryBound: " + Twine(MFI->isMemoryBound()), - false); + // Switch section and emit all GPR maximums within the processed module. + OutStreamer->pushSection(); + MCSectionELF *MaxGPRSection = + OutContext.getELFSection(".AMDGPU.gpr_maximums", ELF::SHT_PROGBITS, 0); + OutStreamer->switchSection(MaxGPRSection); + getTargetStreamer()->EmitMCResourceMaximums(RI.getMaxVGPRSymbol(OutContext), + RI.getMaxAGPRSymbol(OutContext), + RI.getMaxSGPRSymbol(OutContext)); + OutStreamer->popSection(); + + for (Function &F : M.functions()) + validateMCResourceInfo(F); + + return AsmPrinter::doFinalization(M); } SmallString<128> AMDGPUAsmPrinter::getMCExprStr(const MCExpr *Value) { @@ -402,12 +524,14 @@ SmallString<128> AMDGPUAsmPrinter::getMCExprStr(const MCExpr *Value) { return Str; } +// Print comments that apply to both callable functions and entry points. void AMDGPUAsmPrinter::emitCommonFunctionComments( const MCExpr *NumVGPR, const MCExpr *NumAGPR, const MCExpr *TotalNumVGPR, const MCExpr *NumSGPR, const MCExpr *ScratchSize, uint64_t CodeSize, const AMDGPUMachineFunction *MFI) { OutStreamer->emitRawComment(" codeLenInByte = " + Twine(CodeSize), false); - OutStreamer->emitRawComment(" NumSgprs: " + getMCExprStr(NumSGPR), false); + OutStreamer->emitRawComment(" TotalNumSgprs: " + getMCExprStr(NumSGPR), + false); OutStreamer->emitRawComment(" NumVgprs: " + getMCExprStr(NumVGPR), false); if (NumAGPR && TotalNumVGPR) { OutStreamer->emitRawComment(" NumAgprs: " + getMCExprStr(NumAGPR), false); @@ -540,6 +664,10 @@ bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) { OutStreamer->switchSection(ConfigSection); } + const AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo &Info = + ResourceUsage->getResourceInfo(); + RI.gatherResourceInfo(MF, Info, OutContext); + if (MFI->isModuleEntryFunction()) { getSIProgramInfo(CurrentProgramInfo, MF); } @@ -571,21 +699,44 @@ bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) { emitResourceUsageRemarks(MF, CurrentProgramInfo, MFI->isModuleEntryFunction(), STM.hasMAIInsts()); + { + using RIK = MCResourceInfo::ResourceInfoKind; + getTargetStreamer()->EmitMCResourceInfo( + RI.getSymbol(MF.getName(), RIK::RIK_NumVGPR, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_NumAGPR, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_NumSGPR, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_PrivateSegSize, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_UsesVCC, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_UsesFlatScratch, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_HasDynSizedStack, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_HasRecursion, OutContext), + RI.getSymbol(MF.getName(), RIK::RIK_HasIndirectCall, OutContext)); + } + if (isVerbose()) { MCSectionELF *CommentSection = Context.getELFSection(".AMDGPU.csdata", ELF::SHT_PROGBITS, 0); OutStreamer->switchSection(CommentSection); if (!MFI->isEntryFunction()) { + using RIK = MCResourceInfo::ResourceInfoKind; OutStreamer->emitRawComment(" Function info:", false); - const AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo &Info = - ResourceUsage->getResourceInfo(&MF.getFunction()); + emitCommonFunctionComments( - Info.NumVGPR, - STM.hasMAIInsts() ? Info.NumAGPR : std::optional(), - Info.getTotalNumVGPRs(STM), - Info.getTotalNumSGPRs(MF.getSubtarget()), - Info.PrivateSegmentSize, getFunctionCodeSize(MF), MFI); + RI.getSymbol(MF.getName(), RIK::RIK_NumVGPR, OutContext) + ->getVariableValue(), + STM.hasMAIInsts() + ? RI.getSymbol(MF.getName(), RIK::RIK_NumAGPR, OutContext) + ->getVariableValue() + : nullptr, + RI.createTotalNumVGPRs(MF, Ctx), + RI.createTotalNumSGPRs( + MF, + MF.getSubtarget().getTargetID().isXnackOnOrAny(), + Ctx), + RI.getSymbol(MF.getName(), RIK::RIK_PrivateSegSize, OutContext) + ->getVariableValue(), + getFunctionCodeSize(MF), MFI); return false; } @@ -751,10 +902,26 @@ uint64_t AMDGPUAsmPrinter::getFunctionCodeSize(const MachineFunction &MF) const return CodeSize; } +// AccumOffset computed for the MCExpr equivalent of: +// alignTo(std::max(1, NumVGPR), 4) / 4 - 1; +static const MCExpr *computeAccumOffset(const MCExpr *NumVGPR, MCContext &Ctx) { + const MCExpr *ConstFour = MCConstantExpr::create(4, Ctx); + const MCExpr *ConstOne = MCConstantExpr::create(1, Ctx); + + // Can't be lower than 1 for subsequent alignTo. + const MCExpr *MaximumTaken = + AMDGPUMCExpr::createMax({ConstOne, NumVGPR}, Ctx); + + // Practically, it's computing divideCeil(MaximumTaken, 4). + const MCExpr *DivCeil = MCBinaryExpr::createDiv( + AMDGPUMCExpr::createAlignTo(MaximumTaken, ConstFour, Ctx), ConstFour, + Ctx); + + return MCBinaryExpr::createSub(DivCeil, ConstOne, Ctx); +} + void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo, const MachineFunction &MF) { - const AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo &Info = - ResourceUsage->getResourceInfo(&MF.getFunction()); const GCNSubtarget &STM = MF.getSubtarget(); MCContext &Ctx = MF.getContext(); @@ -771,28 +938,27 @@ void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo, return false; }; - ProgInfo.NumArchVGPR = CreateExpr(Info.NumVGPR); - ProgInfo.NumAccVGPR = CreateExpr(Info.NumAGPR); - ProgInfo.NumVGPR = CreateExpr(Info.getTotalNumVGPRs(STM)); - ProgInfo.AccumOffset = - CreateExpr(alignTo(std::max(1, Info.NumVGPR), 4) / 4 - 1); + auto GetSymRefExpr = + [&](MCResourceInfo::ResourceInfoKind RIK) -> const MCExpr * { + MCSymbol *Sym = RI.getSymbol(MF.getName(), RIK, OutContext); + return MCSymbolRefExpr::create(Sym, Ctx); + }; + + using RIK = MCResourceInfo::ResourceInfoKind; + ProgInfo.NumArchVGPR = GetSymRefExpr(RIK::RIK_NumVGPR); + ProgInfo.NumAccVGPR = GetSymRefExpr(RIK::RIK_NumAGPR); + ProgInfo.NumVGPR = AMDGPUMCExpr::createTotalNumVGPR( + ProgInfo.NumAccVGPR, ProgInfo.NumArchVGPR, Ctx); + + ProgInfo.AccumOffset = computeAccumOffset(ProgInfo.NumArchVGPR, Ctx); ProgInfo.TgSplit = STM.isTgSplitEnabled(); - ProgInfo.NumSGPR = CreateExpr(Info.NumExplicitSGPR); - ProgInfo.ScratchSize = CreateExpr(Info.PrivateSegmentSize); - ProgInfo.VCCUsed = CreateExpr(Info.UsesVCC); - ProgInfo.FlatUsed = CreateExpr(Info.UsesFlatScratch); + ProgInfo.NumSGPR = GetSymRefExpr(RIK::RIK_NumSGPR); + ProgInfo.ScratchSize = GetSymRefExpr(RIK::RIK_PrivateSegSize); + ProgInfo.VCCUsed = GetSymRefExpr(RIK::RIK_UsesVCC); + ProgInfo.FlatUsed = GetSymRefExpr(RIK::RIK_UsesFlatScratch); ProgInfo.DynamicCallStack = - CreateExpr(Info.HasDynamicallySizedStack || Info.HasRecursion); - - const uint64_t MaxScratchPerWorkitem = - STM.getMaxWaveScratchSize() / STM.getWavefrontSize(); - uint64_t ScratchSize; - if (TryGetMCExprValue(ProgInfo.ScratchSize, ScratchSize) && - ScratchSize > MaxScratchPerWorkitem) { - DiagnosticInfoStackSize DiagStackSize(MF.getFunction(), ScratchSize, - MaxScratchPerWorkitem, DS_Error); - MF.getFunction().getContext().diagnose(DiagStackSize); - } + MCBinaryExpr::createOr(GetSymRefExpr(RIK::RIK_HasDynSizedStack), + GetSymRefExpr(RIK::RIK_HasRecursion), Ctx); const SIMachineFunctionInfo *MFI = MF.getInfo(); @@ -1477,6 +1643,8 @@ bool AMDGPUAsmPrinter::PrintAsmOperand(const MachineInstr *MI, unsigned OpNo, void AMDGPUAsmPrinter::getAnalysisUsage(AnalysisUsage &AU) const { AU.addRequired(); AU.addPreserved(); + AU.addRequired(); + AU.addPreserved(); AsmPrinter::getAnalysisUsage(AU); } @@ -1522,7 +1690,7 @@ void AMDGPUAsmPrinter::emitResourceUsageRemarks( // printing multiple diagnostic location and diag opts. EmitResourceUsageRemark("FunctionName", "Function Name", MF.getFunction().getName()); - EmitResourceUsageRemark("NumSGPR", "SGPRs", + EmitResourceUsageRemark("NumSGPR", "TotalSGPRs", getMCExprStr(CurrentProgramInfo.NumSGPR)); EmitResourceUsageRemark("NumVGPR", "VGPRs", getMCExprStr(CurrentProgramInfo.NumArchVGPR)); diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h index f66bbde42ce278..cc8c4411805e23 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h +++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h @@ -14,6 +14,7 @@ #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUASMPRINTER_H #define LLVM_LIB_TARGET_AMDGPU_AMDGPUASMPRINTER_H +#include "AMDGPUMCResourceInfo.h" #include "SIProgramInfo.h" #include "llvm/CodeGen/AsmPrinter.h" @@ -24,6 +25,7 @@ struct AMDGPUResourceUsageAnalysis; class AMDGPUTargetStreamer; class MCCodeEmitter; class MCOperand; +class MCResourceInfo; namespace AMDGPU { struct MCKernelDescriptor; @@ -40,6 +42,8 @@ class AMDGPUAsmPrinter final : public AsmPrinter { AMDGPUResourceUsageAnalysis *ResourceUsage; + MCResourceInfo RI; + SIProgramInfo CurrentProgramInfo; std::unique_ptr HSAMetadataStream; @@ -60,11 +64,6 @@ class AMDGPUAsmPrinter final : public AsmPrinter { void EmitPALMetadata(const MachineFunction &MF, const SIProgramInfo &KernelInfo); void emitPALFunctionMetadata(const MachineFunction &MF); - void emitCommonFunctionComments(uint32_t NumVGPR, - std::optional NumAGPR, - uint32_t TotalNumVGPR, uint32_t NumSGPR, - uint64_t ScratchSize, uint64_t CodeSize, - const AMDGPUMachineFunction *MFI); void emitCommonFunctionComments(const MCExpr *NumVGPR, const MCExpr *NumAGPR, const MCExpr *TotalNumVGPR, const MCExpr *NumSGPR, @@ -84,6 +83,11 @@ class AMDGPUAsmPrinter final : public AsmPrinter { SmallString<128> getMCExprStr(const MCExpr *Value); + /// Attempts to replace the validation that is missed in getSIProgramInfo due + /// to MCExpr being unknown. Invoked during doFinalization such that the + /// MCResourceInfo symbols are known. + void validateMCResourceInfo(Function &F); + public: explicit AMDGPUAsmPrinter(TargetMachine &TM, std::unique_ptr Streamer); diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp new file mode 100644 index 00000000000000..b5f53290eff3ac --- /dev/null +++ b/llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp @@ -0,0 +1,224 @@ +//===- AMDGPUMCResourceInfo.cpp --- MC Resource Info ----------------------===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +/// \file +/// \brief MC infrastructure to propagate the function level resource usage +/// info. +/// +//===----------------------------------------------------------------------===// + +#include "AMDGPUMCResourceInfo.h" +#include "Utils/AMDGPUBaseInfo.h" +#include "llvm/ADT/SmallSet.h" +#include "llvm/ADT/StringRef.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCSymbol.h" + +using namespace llvm; + +MCSymbol *MCResourceInfo::getSymbol(StringRef FuncName, ResourceInfoKind RIK, + MCContext &OutContext) { + auto GOCS = [this, FuncName, &OutContext](StringRef Suffix) { + return OutContext.getOrCreateSymbol(FuncName + Twine(Suffix)); + }; + switch (RIK) { + case RIK_NumVGPR: + return GOCS(".num_vgpr"); + case RIK_NumAGPR: + return GOCS(".num_agpr"); + case RIK_NumSGPR: + return GOCS(".numbered_sgpr"); + case RIK_PrivateSegSize: + return GOCS(".private_seg_size"); + case RIK_UsesVCC: + return GOCS(".uses_vcc"); + case RIK_UsesFlatScratch: + return GOCS(".uses_flat_scratch"); + case RIK_HasDynSizedStack: + return GOCS(".has_dyn_sized_stack"); + case RIK_HasRecursion: + return GOCS(".has_recursion"); + case RIK_HasIndirectCall: + return GOCS(".has_indirect_call"); + } + llvm_unreachable("Unexpected ResourceInfoKind."); +} + +const MCExpr *MCResourceInfo::getSymRefExpr(StringRef FuncName, + ResourceInfoKind RIK, + MCContext &Ctx) { + return MCSymbolRefExpr::create(getSymbol(FuncName, RIK, Ctx), Ctx); +} + +void MCResourceInfo::assignMaxRegs(MCContext &OutContext) { + // Assign expression to get the max register use to the max_num_Xgpr symbol. + MCSymbol *MaxVGPRSym = getMaxVGPRSymbol(OutContext); + MCSymbol *MaxAGPRSym = getMaxAGPRSymbol(OutContext); + MCSymbol *MaxSGPRSym = getMaxSGPRSymbol(OutContext); + + auto assignMaxRegSym = [this, &OutContext](MCSymbol *Sym, int32_t RegCount) { + const MCExpr *MaxExpr = MCConstantExpr::create(RegCount, OutContext); + Sym->setVariableValue(MaxExpr); + }; + + assignMaxRegSym(MaxVGPRSym, MaxVGPR); + assignMaxRegSym(MaxAGPRSym, MaxAGPR); + assignMaxRegSym(MaxSGPRSym, MaxSGPR); +} + +void MCResourceInfo::finalize(MCContext &OutContext) { + assert(!Finalized && "Cannot finalize ResourceInfo again."); + Finalized = true; + assignMaxRegs(OutContext); +} + +MCSymbol *MCResourceInfo::getMaxVGPRSymbol(MCContext &OutContext) { + return OutContext.getOrCreateSymbol("amdgpu.max_num_vgpr"); +} + +MCSymbol *MCResourceInfo::getMaxAGPRSymbol(MCContext &OutContext) { + return OutContext.getOrCreateSymbol("amdgpu.max_num_agpr"); +} + +MCSymbol *MCResourceInfo::getMaxSGPRSymbol(MCContext &OutContext) { + return OutContext.getOrCreateSymbol("amdgpu.max_num_sgpr"); +} + +void MCResourceInfo::assignResourceInfoExpr( + int64_t LocalValue, ResourceInfoKind RIK, AMDGPUMCExpr::VariantKind Kind, + const MachineFunction &MF, const SmallVectorImpl &Callees, + MCContext &OutContext) { + const MCConstantExpr *LocalConstExpr = + MCConstantExpr::create(LocalValue, OutContext); + const MCExpr *SymVal = LocalConstExpr; + if (!Callees.empty()) { + SmallVector ArgExprs; + // Avoid recursive symbol assignment. + SmallPtrSet Seen; + ArgExprs.push_back(LocalConstExpr); + const Function &F = MF.getFunction(); + Seen.insert(&F); + + for (const Function *Callee : Callees) { + if (!Seen.insert(Callee).second) + continue; + MCSymbol *CalleeValSym = getSymbol(Callee->getName(), RIK, OutContext); + ArgExprs.push_back(MCSymbolRefExpr::create(CalleeValSym, OutContext)); + } + SymVal = AMDGPUMCExpr::create(Kind, ArgExprs, OutContext); + } + MCSymbol *Sym = getSymbol(MF.getName(), RIK, OutContext); + Sym->setVariableValue(SymVal); +} + +void MCResourceInfo::gatherResourceInfo( + const MachineFunction &MF, + const AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo &FRI, + MCContext &OutContext) { + // Worst case VGPR use for non-hardware-entrypoints. + MCSymbol *MaxVGPRSym = getMaxVGPRSymbol(OutContext); + MCSymbol *MaxAGPRSym = getMaxAGPRSymbol(OutContext); + MCSymbol *MaxSGPRSym = getMaxSGPRSymbol(OutContext); + + if (!AMDGPU::isEntryFunctionCC(MF.getFunction().getCallingConv())) { + addMaxVGPRCandidate(FRI.NumVGPR); + addMaxAGPRCandidate(FRI.NumAGPR); + addMaxSGPRCandidate(FRI.NumExplicitSGPR); + } + + auto SetMaxReg = [&](MCSymbol *MaxSym, int32_t numRegs, + ResourceInfoKind RIK) { + if (!FRI.HasIndirectCall) { + assignResourceInfoExpr(numRegs, RIK, AMDGPUMCExpr::AGVK_Max, MF, + FRI.Callees, OutContext); + } else { + const MCExpr *SymRef = MCSymbolRefExpr::create(MaxSym, OutContext); + MCSymbol *LocalNumSym = getSymbol(MF.getName(), RIK, OutContext); + const MCExpr *MaxWithLocal = AMDGPUMCExpr::createMax( + {MCConstantExpr::create(numRegs, OutContext), SymRef}, OutContext); + LocalNumSym->setVariableValue(MaxWithLocal); + } + }; + + SetMaxReg(MaxVGPRSym, FRI.NumVGPR, RIK_NumVGPR); + SetMaxReg(MaxAGPRSym, FRI.NumAGPR, RIK_NumAGPR); + SetMaxReg(MaxSGPRSym, FRI.NumExplicitSGPR, RIK_NumSGPR); + + { + // The expression for private segment size should be: FRI.PrivateSegmentSize + // + max(FRI.Callees, FRI.CalleeSegmentSize) + SmallVector ArgExprs; + if (FRI.CalleeSegmentSize) + ArgExprs.push_back( + MCConstantExpr::create(FRI.CalleeSegmentSize, OutContext)); + + if (!FRI.HasIndirectCall) { + for (const Function *Callee : FRI.Callees) { + MCSymbol *calleeValSym = + getSymbol(Callee->getName(), RIK_PrivateSegSize, OutContext); + ArgExprs.push_back(MCSymbolRefExpr::create(calleeValSym, OutContext)); + } + } + const MCExpr *localConstExpr = + MCConstantExpr::create(FRI.PrivateSegmentSize, OutContext); + if (!ArgExprs.empty()) { + const AMDGPUMCExpr *transitiveExpr = + AMDGPUMCExpr::createMax(ArgExprs, OutContext); + localConstExpr = + MCBinaryExpr::createAdd(localConstExpr, transitiveExpr, OutContext); + } + getSymbol(MF.getName(), RIK_PrivateSegSize, OutContext) + ->setVariableValue(localConstExpr); + } + + auto SetToLocal = [&](int64_t LocalValue, ResourceInfoKind RIK) { + MCSymbol *Sym = getSymbol(MF.getName(), RIK, OutContext); + Sym->setVariableValue(MCConstantExpr::create(LocalValue, OutContext)); + }; + + if (!FRI.HasIndirectCall) { + assignResourceInfoExpr(FRI.UsesVCC, ResourceInfoKind::RIK_UsesVCC, + AMDGPUMCExpr::AGVK_Or, MF, FRI.Callees, OutContext); + assignResourceInfoExpr(FRI.UsesFlatScratch, + ResourceInfoKind::RIK_UsesFlatScratch, + AMDGPUMCExpr::AGVK_Or, MF, FRI.Callees, OutContext); + assignResourceInfoExpr(FRI.HasDynamicallySizedStack, + ResourceInfoKind::RIK_HasDynSizedStack, + AMDGPUMCExpr::AGVK_Or, MF, FRI.Callees, OutContext); + assignResourceInfoExpr(FRI.HasRecursion, ResourceInfoKind::RIK_HasRecursion, + AMDGPUMCExpr::AGVK_Or, MF, FRI.Callees, OutContext); + assignResourceInfoExpr(FRI.HasIndirectCall, + ResourceInfoKind::RIK_HasIndirectCall, + AMDGPUMCExpr::AGVK_Or, MF, FRI.Callees, OutContext); + } else { + SetToLocal(FRI.UsesVCC, ResourceInfoKind::RIK_UsesVCC); + SetToLocal(FRI.UsesFlatScratch, ResourceInfoKind::RIK_UsesFlatScratch); + SetToLocal(FRI.HasDynamicallySizedStack, + ResourceInfoKind::RIK_HasDynSizedStack); + SetToLocal(FRI.HasRecursion, ResourceInfoKind::RIK_HasRecursion); + SetToLocal(FRI.HasIndirectCall, ResourceInfoKind::RIK_HasIndirectCall); + } +} + +const MCExpr *MCResourceInfo::createTotalNumVGPRs(const MachineFunction &MF, + MCContext &Ctx) { + return AMDGPUMCExpr::createTotalNumVGPR( + getSymRefExpr(MF.getName(), RIK_NumAGPR, Ctx), + getSymRefExpr(MF.getName(), RIK_NumVGPR, Ctx), Ctx); +} + +const MCExpr *MCResourceInfo::createTotalNumSGPRs(const MachineFunction &MF, + bool hasXnack, + MCContext &Ctx) { + return MCBinaryExpr::createAdd( + getSymRefExpr(MF.getName(), RIK_NumSGPR, Ctx), + AMDGPUMCExpr::createExtraSGPRs( + getSymRefExpr(MF.getName(), RIK_UsesVCC, Ctx), + getSymRefExpr(MF.getName(), RIK_UsesFlatScratch, Ctx), hasXnack, Ctx), + Ctx); +} diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.h new file mode 100644 index 00000000000000..08c0c106d5aa9b --- /dev/null +++ b/llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.h @@ -0,0 +1,102 @@ +//===- AMDGPUMCResourceInfo.h ----- MC Resource Info --------------*- C++ -*-=// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +/// \file +/// \brief MC infrastructure to propagate the function level resource usage +/// info. +/// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUMCRESOURCEINFO_H +#define LLVM_LIB_TARGET_AMDGPU_AMDGPUMCRESOURCEINFO_H + +#include "AMDGPUResourceUsageAnalysis.h" +#include "MCTargetDesc/AMDGPUMCExpr.h" + +namespace llvm { + +class MCContext; +class MCSymbol; +class StringRef; +class MachineFunction; + +class MCResourceInfo { +public: + enum ResourceInfoKind { + RIK_NumVGPR, + RIK_NumAGPR, + RIK_NumSGPR, + RIK_PrivateSegSize, + RIK_UsesVCC, + RIK_UsesFlatScratch, + RIK_HasDynSizedStack, + RIK_HasRecursion, + RIK_HasIndirectCall + }; + +private: + int32_t MaxVGPR = 0; + int32_t MaxAGPR = 0; + int32_t MaxSGPR = 0; + + // Whether the MCResourceInfo has been finalized through finalize(MCContext + // &). Should only be called once, at the end of AsmPrinting to assign MaxXGPR + // symbols to their final value. + bool Finalized = false; + + void assignResourceInfoExpr(int64_t localValue, ResourceInfoKind RIK, + AMDGPUMCExpr::VariantKind Kind, + const MachineFunction &MF, + const SmallVectorImpl &Callees, + MCContext &OutContext); + + // Assigns expression for Max S/V/A-GPRs to the referenced symbols. + void assignMaxRegs(MCContext &OutContext); + +public: + MCResourceInfo() = default; + void addMaxVGPRCandidate(int32_t candidate) { + MaxVGPR = std::max(MaxVGPR, candidate); + } + void addMaxAGPRCandidate(int32_t candidate) { + MaxAGPR = std::max(MaxAGPR, candidate); + } + void addMaxSGPRCandidate(int32_t candidate) { + MaxSGPR = std::max(MaxSGPR, candidate); + } + + MCSymbol *getSymbol(StringRef FuncName, ResourceInfoKind RIK, + MCContext &OutContext); + const MCExpr *getSymRefExpr(StringRef FuncName, ResourceInfoKind RIK, + MCContext &Ctx); + + // Resolves the final symbols that requires the inter-function resource info + // to be resolved. + void finalize(MCContext &OutContext); + + MCSymbol *getMaxVGPRSymbol(MCContext &OutContext); + MCSymbol *getMaxAGPRSymbol(MCContext &OutContext); + MCSymbol *getMaxSGPRSymbol(MCContext &OutContext); + + /// AMDGPUResourceUsageAnalysis gathers resource usage on a per-function + /// granularity. However, some resource info has to be assigned the call + /// transitive maximum or accumulative. For example, if A calls B and B's VGPR + /// usage exceeds A's, A should be assigned B's VGPR usage. Furthermore, + /// functions with indirect calls should be assigned the module level maximum. + void gatherResourceInfo( + const MachineFunction &MF, + const AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo &FRI, + MCContext &OutContext); + + const MCExpr *createTotalNumVGPRs(const MachineFunction &MF, MCContext &Ctx); + const MCExpr *createTotalNumSGPRs(const MachineFunction &MF, bool hasXnack, + MCContext &Ctx); +}; +} // namespace llvm + +#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUMCRESOURCEINFO_H diff --git a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp index 0aca99a82d1978..1ee3c40d69a3b3 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp @@ -13,14 +13,6 @@ /// The results of this analysis are used to fill the register usage, flat /// usage, etc. into hardware registers. /// -/// The analysis takes callees into account. E.g. if a function A that needs 10 -/// VGPRs calls a function B that needs 20 VGPRs, querying the VGPR usage of A -/// will return 20. -/// It is assumed that an indirect call can go into any function except -/// hardware-entrypoints. Therefore the register usage of functions with -/// indirect calls is estimated as the maximum of all non-entrypoint functions -/// in the module. -/// //===----------------------------------------------------------------------===// #include "AMDGPUResourceUsageAnalysis.h" @@ -28,8 +20,8 @@ #include "GCNSubtarget.h" #include "SIMachineFunctionInfo.h" #include "llvm/ADT/PostOrderIterator.h" -#include "llvm/Analysis/CallGraph.h" #include "llvm/CodeGen/MachineFrameInfo.h" +#include "llvm/CodeGen/MachineModuleInfo.h" #include "llvm/CodeGen/TargetPassConfig.h" #include "llvm/IR/GlobalAlias.h" #include "llvm/IR/GlobalValue.h" @@ -78,92 +70,37 @@ static bool hasAnyNonFlatUseOfReg(const MachineRegisterInfo &MRI, return false; } -int32_t AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo::getTotalNumSGPRs( - const GCNSubtarget &ST) const { - return NumExplicitSGPR + - IsaInfo::getNumExtraSGPRs(&ST, UsesVCC, UsesFlatScratch, - ST.getTargetID().isXnackOnOrAny()); -} - -int32_t AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo::getTotalNumVGPRs( - const GCNSubtarget &ST) const { - return AMDGPU::getTotalNumVGPRs(ST.hasGFX90AInsts(), NumAGPR, NumVGPR); -} - -bool AMDGPUResourceUsageAnalysis::runOnModule(Module &M) { +bool AMDGPUResourceUsageAnalysis::runOnMachineFunction(MachineFunction &MF) { auto *TPC = getAnalysisIfAvailable(); if (!TPC) return false; - MachineModuleInfo &MMI = getAnalysis().getMMI(); const TargetMachine &TM = TPC->getTM(); const MCSubtargetInfo &STI = *TM.getMCSubtargetInfo(); - bool HasIndirectCall = false; - - CallGraph CG = CallGraph(M); - auto End = po_end(&CG); // By default, for code object v5 and later, track only the minimum scratch // size uint32_t AssumedStackSizeForDynamicSizeObjects = clAssumedStackSizeForDynamicSizeObjects; uint32_t AssumedStackSizeForExternalCall = clAssumedStackSizeForExternalCall; - if (AMDGPU::getAMDHSACodeObjectVersion(M) >= AMDGPU::AMDHSA_COV5 || + if (AMDGPU::getAMDHSACodeObjectVersion(*MF.getFunction().getParent()) >= + AMDGPU::AMDHSA_COV5 || STI.getTargetTriple().getOS() == Triple::AMDPAL) { - if (clAssumedStackSizeForDynamicSizeObjects.getNumOccurrences() == 0) + if (!clAssumedStackSizeForDynamicSizeObjects.getNumOccurrences()) AssumedStackSizeForDynamicSizeObjects = 0; - if (clAssumedStackSizeForExternalCall.getNumOccurrences() == 0) + if (!clAssumedStackSizeForExternalCall.getNumOccurrences()) AssumedStackSizeForExternalCall = 0; } - for (auto IT = po_begin(&CG); IT != End; ++IT) { - Function *F = IT->getFunction(); - if (!F || F->isDeclaration()) - continue; - - MachineFunction *MF = MMI.getMachineFunction(*F); - assert(MF && "function must have been generated already"); - - auto CI = - CallGraphResourceInfo.insert(std::pair(F, SIFunctionResourceInfo())); - SIFunctionResourceInfo &Info = CI.first->second; - assert(CI.second && "should only be called once per function"); - Info = analyzeResourceUsage(*MF, TM, AssumedStackSizeForDynamicSizeObjects, - AssumedStackSizeForExternalCall); - HasIndirectCall |= Info.HasIndirectCall; - } - - // It's possible we have unreachable functions in the module which weren't - // visited by the PO traversal. Make sure we have some resource counts to - // report. - for (const auto &IT : CG) { - const Function *F = IT.first; - if (!F || F->isDeclaration()) - continue; - - auto CI = - CallGraphResourceInfo.insert(std::pair(F, SIFunctionResourceInfo())); - if (!CI.second) // Skip already visited functions - continue; - - SIFunctionResourceInfo &Info = CI.first->second; - MachineFunction *MF = MMI.getMachineFunction(*F); - assert(MF && "function must have been generated already"); - Info = analyzeResourceUsage(*MF, TM, AssumedStackSizeForDynamicSizeObjects, - AssumedStackSizeForExternalCall); - HasIndirectCall |= Info.HasIndirectCall; - } - - if (HasIndirectCall) - propagateIndirectCallRegisterUsage(); + ResourceInfo = analyzeResourceUsage(MF, AssumedStackSizeForDynamicSizeObjects, + AssumedStackSizeForExternalCall); return false; } AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo AMDGPUResourceUsageAnalysis::analyzeResourceUsage( - const MachineFunction &MF, const TargetMachine &TM, - uint32_t AssumedStackSizeForDynamicSizeObjects, + const MachineFunction &MF, uint32_t AssumedStackSizeForDynamicSizeObjects, uint32_t AssumedStackSizeForExternalCall) const { SIFunctionResourceInfo Info; @@ -253,7 +190,7 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage( int32_t MaxVGPR = -1; int32_t MaxAGPR = -1; int32_t MaxSGPR = -1; - uint64_t CalleeFrameSize = 0; + Info.CalleeSegmentSize = 0; for (const MachineBasicBlock &MBB : MF) { for (const MachineInstr &MI : MBB) { @@ -512,8 +449,6 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage( TII->getNamedOperand(MI, AMDGPU::OpName::callee); const Function *Callee = getCalleeFunction(*CalleeOp); - DenseMap::const_iterator I = - CallGraphResourceInfo.end(); // Avoid crashing on undefined behavior with an illegal call to a // kernel. If a callsite's calling convention doesn't match the @@ -522,9 +457,14 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage( if (Callee && AMDGPU::isEntryFunctionCC(Callee->getCallingConv())) report_fatal_error("invalid call to entry function"); + auto isSameFunction = [](const MachineFunction &MF, const Function *F) { + return F == &MF.getFunction(); + }; + + if (Callee && !isSameFunction(MF, Callee)) + Info.Callees.push_back(Callee); + bool IsIndirect = !Callee || Callee->isDeclaration(); - if (!IsIndirect) - I = CallGraphResourceInfo.find(Callee); // FIXME: Call site could have norecurse on it if (!Callee || !Callee->doesNotRecurse()) { @@ -539,15 +479,15 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage( // directly call the tail called function. If a kernel directly // calls a tail recursive function, we'll assume maximum stack size // based on the regular call instruction. - CalleeFrameSize = std::max( - CalleeFrameSize, + Info.CalleeSegmentSize = std::max( + Info.CalleeSegmentSize, static_cast(AssumedStackSizeForExternalCall)); } } - if (IsIndirect || I == CallGraphResourceInfo.end()) { - CalleeFrameSize = - std::max(CalleeFrameSize, + if (IsIndirect) { + Info.CalleeSegmentSize = + std::max(Info.CalleeSegmentSize, static_cast(AssumedStackSizeForExternalCall)); // Register usage of indirect calls gets handled later @@ -555,19 +495,6 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage( Info.UsesFlatScratch = ST.hasFlatAddressSpace(); Info.HasDynamicallySizedStack = true; Info.HasIndirectCall = true; - } else { - // We force CodeGen to run in SCC order, so the callee's register - // usage etc. should be the cumulative usage of all callees. - MaxSGPR = std::max(I->second.NumExplicitSGPR - 1, MaxSGPR); - MaxVGPR = std::max(I->second.NumVGPR - 1, MaxVGPR); - MaxAGPR = std::max(I->second.NumAGPR - 1, MaxAGPR); - CalleeFrameSize = - std::max(I->second.PrivateSegmentSize, CalleeFrameSize); - Info.UsesVCC |= I->second.UsesVCC; - Info.UsesFlatScratch |= I->second.UsesFlatScratch; - Info.HasDynamicallySizedStack |= I->second.HasDynamicallySizedStack; - Info.HasRecursion |= I->second.HasRecursion; - Info.HasIndirectCall |= I->second.HasIndirectCall; } } } @@ -576,36 +503,6 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage( Info.NumExplicitSGPR = MaxSGPR + 1; Info.NumVGPR = MaxVGPR + 1; Info.NumAGPR = MaxAGPR + 1; - Info.PrivateSegmentSize += CalleeFrameSize; return Info; } - -void AMDGPUResourceUsageAnalysis::propagateIndirectCallRegisterUsage() { - // Collect the maximum number of registers from non-hardware-entrypoints. - // All these functions are potential targets for indirect calls. - int32_t NonKernelMaxSGPRs = 0; - int32_t NonKernelMaxVGPRs = 0; - int32_t NonKernelMaxAGPRs = 0; - - for (const auto &I : CallGraphResourceInfo) { - if (!AMDGPU::isEntryFunctionCC(I.getFirst()->getCallingConv())) { - auto &Info = I.getSecond(); - NonKernelMaxSGPRs = std::max(NonKernelMaxSGPRs, Info.NumExplicitSGPR); - NonKernelMaxVGPRs = std::max(NonKernelMaxVGPRs, Info.NumVGPR); - NonKernelMaxAGPRs = std::max(NonKernelMaxAGPRs, Info.NumAGPR); - } - } - - // Add register usage for functions with indirect calls. - // For calls to unknown functions, we assume the maximum register usage of - // all non-hardware-entrypoints in the current module. - for (auto &I : CallGraphResourceInfo) { - auto &Info = I.getSecond(); - if (Info.HasIndirectCall) { - Info.NumExplicitSGPR = std::max(Info.NumExplicitSGPR, NonKernelMaxSGPRs); - Info.NumVGPR = std::max(Info.NumVGPR, NonKernelMaxVGPRs); - Info.NumAGPR = std::max(Info.NumAGPR, NonKernelMaxAGPRs); - } - } -} diff --git a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.h b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.h index 7f71de6749dcef..92ef41f49b3ba8 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.h +++ b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.h @@ -15,8 +15,8 @@ #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPURESOURCEUSAGEANALYSIS_H #define LLVM_LIB_TARGET_AMDGPU_AMDGPURESOURCEUSAGEANALYSIS_H -#include "llvm/Analysis/CallGraphSCCPass.h" -#include "llvm/CodeGen/MachineModuleInfo.h" +#include "llvm/ADT/SmallVector.h" +#include "llvm/CodeGen/MachineFunctionPass.h" namespace llvm { @@ -24,10 +24,9 @@ class GCNSubtarget; class MachineFunction; class TargetMachine; -struct AMDGPUResourceUsageAnalysis : public ModulePass { - static char ID; - +struct AMDGPUResourceUsageAnalysis : public MachineFunctionPass { public: + static char ID; // Track resource usage for callee functions. struct SIFunctionResourceInfo { // Track the number of explicitly used VGPRs. Special registers reserved at @@ -35,48 +34,33 @@ struct AMDGPUResourceUsageAnalysis : public ModulePass { int32_t NumVGPR = 0; int32_t NumAGPR = 0; int32_t NumExplicitSGPR = 0; + uint64_t CalleeSegmentSize = 0; uint64_t PrivateSegmentSize = 0; bool UsesVCC = false; bool UsesFlatScratch = false; bool HasDynamicallySizedStack = false; bool HasRecursion = false; bool HasIndirectCall = false; - - int32_t getTotalNumSGPRs(const GCNSubtarget &ST) const; - // Total number of VGPRs is actually a combination of AGPR and VGPR - // depending on architecture - and some alignment constraints - int32_t getTotalNumVGPRs(const GCNSubtarget &ST) const; + SmallVector Callees; }; - AMDGPUResourceUsageAnalysis() : ModulePass(ID) {} + AMDGPUResourceUsageAnalysis() : MachineFunctionPass(ID) {} - bool doInitialization(Module &M) override { - CallGraphResourceInfo.clear(); - return ModulePass::doInitialization(M); - } + bool runOnMachineFunction(MachineFunction &MF) override; - bool runOnModule(Module &M) override; + const SIFunctionResourceInfo &getResourceInfo() const { return ResourceInfo; } void getAnalysisUsage(AnalysisUsage &AU) const override { - AU.addRequired(); AU.setPreservesAll(); - } - - const SIFunctionResourceInfo &getResourceInfo(const Function *F) const { - auto Info = CallGraphResourceInfo.find(F); - assert(Info != CallGraphResourceInfo.end() && - "Failed to find resource info for function"); - return Info->getSecond(); + MachineFunctionPass::getAnalysisUsage(AU); } private: SIFunctionResourceInfo - analyzeResourceUsage(const MachineFunction &MF, const TargetMachine &TM, + analyzeResourceUsage(const MachineFunction &MF, uint32_t AssumedStackSizeForDynamicSizeObjects, uint32_t AssumedStackSizeForExternalCall) const; - void propagateIndirectCallRegisterUsage(); - - DenseMap CallGraphResourceInfo; + SIFunctionResourceInfo ResourceInfo; }; } // namespace llvm #endif // LLVM_LIB_TARGET_AMDGPU_AMDGPURESOURCEUSAGEANALYSIS_H diff --git a/llvm/lib/Target/AMDGPU/CMakeLists.txt b/llvm/lib/Target/AMDGPU/CMakeLists.txt index 7c883cc2017ddd..4605be344f7316 100644 --- a/llvm/lib/Target/AMDGPU/CMakeLists.txt +++ b/llvm/lib/Target/AMDGPU/CMakeLists.txt @@ -81,6 +81,7 @@ add_llvm_target(AMDGPUCodeGen AMDGPUMCInstLower.cpp AMDGPUMemoryUtils.cpp AMDGPUIGroupLP.cpp + AMDGPUMCResourceInfo.cpp AMDGPUMarkLastScratchLoad.cpp AMDGPUMIRFormatter.cpp AMDGPUOpenCLEnqueuedBlockLowering.cpp diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp index 73d466abc66f7b..a1a41d6cc8c6a0 100644 --- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp +++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp @@ -271,6 +271,47 @@ void AMDGPUTargetAsmStreamer::emitAMDGPULDS(MCSymbol *Symbol, unsigned Size, << Alignment.value() << '\n'; } +void AMDGPUTargetAsmStreamer::EmitMCResourceInfo( + const MCSymbol *NumVGPR, const MCSymbol *NumAGPR, + const MCSymbol *NumExplicitSGPR, const MCSymbol *PrivateSegmentSize, + const MCSymbol *UsesVCC, const MCSymbol *UsesFlatScratch, + const MCSymbol *HasDynamicallySizedStack, const MCSymbol *HasRecursion, + const MCSymbol *HasIndirectCall) { +#define PRINT_RES_INFO(ARG) \ + OS << "\t.set "; \ + ARG->print(OS, getContext().getAsmInfo()); \ + OS << ", "; \ + ARG->getVariableValue()->print(OS, getContext().getAsmInfo()); \ + Streamer.addBlankLine(); + + PRINT_RES_INFO(NumVGPR); + PRINT_RES_INFO(NumAGPR); + PRINT_RES_INFO(NumExplicitSGPR); + PRINT_RES_INFO(PrivateSegmentSize); + PRINT_RES_INFO(UsesVCC); + PRINT_RES_INFO(UsesFlatScratch); + PRINT_RES_INFO(HasDynamicallySizedStack); + PRINT_RES_INFO(HasRecursion); + PRINT_RES_INFO(HasIndirectCall); +#undef PRINT_RES_INFO +} + +void AMDGPUTargetAsmStreamer::EmitMCResourceMaximums(const MCSymbol *MaxVGPR, + const MCSymbol *MaxAGPR, + const MCSymbol *MaxSGPR) { +#define PRINT_RES_INFO(ARG) \ + OS << "\t.set "; \ + ARG->print(OS, getContext().getAsmInfo()); \ + OS << ", "; \ + ARG->getVariableValue()->print(OS, getContext().getAsmInfo()); \ + Streamer.addBlankLine(); + + PRINT_RES_INFO(MaxVGPR); + PRINT_RES_INFO(MaxAGPR); + PRINT_RES_INFO(MaxSGPR); +#undef PRINT_RES_INFO +} + bool AMDGPUTargetAsmStreamer::EmitISAVersion() { OS << "\t.amd_amdgpu_isa \"" << getTargetID()->toString() << "\"\n"; return true; diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h index bf1538c71d1543..6a91ad06de5d12 100644 --- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h +++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h @@ -60,6 +60,17 @@ class AMDGPUTargetStreamer : public MCTargetStreamer { virtual void emitAMDGPULDS(MCSymbol *Symbol, unsigned Size, Align Alignment) { } + virtual void EmitMCResourceInfo( + const MCSymbol *NumVGPR, const MCSymbol *NumAGPR, + const MCSymbol *NumExplicitSGPR, const MCSymbol *PrivateSegmentSize, + const MCSymbol *UsesVCC, const MCSymbol *UsesFlatScratch, + const MCSymbol *HasDynamicallySizedStack, const MCSymbol *HasRecursion, + const MCSymbol *HasIndirectCall) {}; + + virtual void EmitMCResourceMaximums(const MCSymbol *MaxVGPR, + const MCSymbol *MaxAGPR, + const MCSymbol *MaxSGPR) {}; + /// \returns True on success, false on failure. virtual bool EmitISAVersion() { return true; } @@ -136,6 +147,18 @@ class AMDGPUTargetAsmStreamer final : public AMDGPUTargetStreamer { void emitAMDGPULDS(MCSymbol *Sym, unsigned Size, Align Alignment) override; + void EmitMCResourceInfo(const MCSymbol *NumVGPR, const MCSymbol *NumAGPR, + const MCSymbol *NumExplicitSGPR, + const MCSymbol *PrivateSegmentSize, + const MCSymbol *UsesVCC, + const MCSymbol *UsesFlatScratch, + const MCSymbol *HasDynamicallySizedStack, + const MCSymbol *HasRecursion, + const MCSymbol *HasIndirectCall) override; + + void EmitMCResourceMaximums(const MCSymbol *MaxVGPR, const MCSymbol *MaxAGPR, + const MCSymbol *MaxSGPR) override; + /// \returns True on success, false on failure. bool EmitISAVersion() override; diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp index a53bf70d77717b..92d09b3afa77d7 100644 --- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp +++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp @@ -215,15 +215,15 @@ void AMDGPUPALMetadata::setRegister(unsigned Reg, const MCExpr *Val, const MCExpr *NExpr = MCConstantExpr::create(N.getUInt(), Ctx); Val = MCBinaryExpr::createOr(Val, NExpr, Ctx); } - ExprIt->getSecond() = Val; } else if (N.getKind() == msgpack::Type::UInt) { const MCExpr *NExpr = MCConstantExpr::create(N.getUInt(), Ctx); Val = MCBinaryExpr::createOr(Val, NExpr, Ctx); - int64_t Unused; - if (!Val->evaluateAsAbsolute(Unused)) - REM[Reg] = Val; - (void)Unused; + } else { + // Default to uint64_t 0 so additional calls to setRegister will allow + // propagate ORs. + N = (uint64_t)0; } + REM[Reg] = Val; DelayedExprs.assignDocNode(N, msgpack::Type::UInt, Val); } diff --git a/llvm/test/CodeGen/AMDGPU/agpr-register-count.ll b/llvm/test/CodeGen/AMDGPU/agpr-register-count.ll index 8d87b53efb4e73..0e16ea10c019ac 100644 --- a/llvm/test/CodeGen/AMDGPU/agpr-register-count.ll +++ b/llvm/test/CodeGen/AMDGPU/agpr-register-count.ll @@ -154,25 +154,28 @@ bb: declare void @undef_func() ; GCN-LABEL: {{^}}kernel_call_undef_func: -; GFX908: .amdhsa_next_free_vgpr 32 -; GFX90A: .amdhsa_next_free_vgpr 64 -; GFX90A: .amdhsa_accum_offset 32 -; GCN: NumVgprs: 32 -; GCN: NumAgprs: 32 -; GFX908: TotalNumVgprs: 32 -; GFX90A: TotalNumVgprs: 64 -; GFX908: VGPRBlocks: 7 -; GFX90A: VGPRBlocks: 7 -; GFX908: NumVGPRsForWavesPerEU: 32 -; GFX90A: NumVGPRsForWavesPerEU: 64 -; GFX90A: AccumOffset: 32 -; GFX908: Occupancy: 8 -; GFX90A: Occupancy: 8 -; GFX90A: COMPUTE_PGM_RSRC3_GFX90A:ACCUM_OFFSET: 7 +; GCN: .amdhsa_next_free_vgpr max(totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr), 1, 0) +; GFX90A: .amdhsa_accum_offset ((((((alignto(max(1, kernel_call_undef_func.num_vgpr), 4))/4)-1)&(~65536))&63)+1)*4 +; GCN: .set kernel_call_undef_func.num_vgpr, max(32, amdgpu.max_num_vgpr) +; GCN: .set kernel_call_undef_func.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: NumVgprs: kernel_call_undef_func.num_vgpr +; GCN: NumAgprs: kernel_call_undef_func.num_agpr +; GCN: TotalNumVgprs: totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr) +; GFX908: VGPRBlocks: ((alignto(max(max(totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr), 1, 0), 1), 4))/4)-1 +; GFX90A: VGPRBlocks: ((alignto(max(max(totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr), 1, 0), 1), 8))/8)-1 +; GCN: NumVGPRsForWavesPerEU: max(totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr), 1, 0) +; GFX90A: AccumOffset: ((((alignto(max(1, kernel_call_undef_func.num_vgpr), 4))/4)-1)+1)*4 +; GFX908: Occupancy: occupancy(10, 4, 256, 8, 10, max(kernel_call_undef_func.numbered_sgpr+(extrasgprs(kernel_call_undef_func.uses_vcc, kernel_call_undef_func.uses_flat_scratch, 1)), 1, 0), max(totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr), 1, 0)) +; GFX90A: Occupancy: occupancy(8, 8, 512, 8, 8, max(kernel_call_undef_func.numbered_sgpr+(extrasgprs(kernel_call_undef_func.uses_vcc, kernel_call_undef_func.uses_flat_scratch, 1)), 1, 0), max(totalnumvgprs(kernel_call_undef_func.num_agpr, kernel_call_undef_func.num_vgpr), 1, 0)) +; GFX90A: COMPUTE_PGM_RSRC3_GFX90A:ACCUM_OFFSET: ((((alignto(max(1, kernel_call_undef_func.num_vgpr), 4))/4)-1)&(~65536))&63 define amdgpu_kernel void @kernel_call_undef_func() #0 { bb: call void @undef_func() ret void } +; GCN: .set amdgpu.max_num_vgpr, 32 +; GCN-NEXT: .set amdgpu.max_num_agpr, 32 +; GCN-NEXT: .set amdgpu.max_num_sgpr, 34 + attributes #0 = { nounwind noinline "amdgpu-flat-work-group-size"="1,512" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" } diff --git a/llvm/test/CodeGen/AMDGPU/amdhsa-kernarg-preload-num-sgprs.ll b/llvm/test/CodeGen/AMDGPU/amdhsa-kernarg-preload-num-sgprs.ll index c8ba6722d9d85e..122fc42ef9b62a 100644 --- a/llvm/test/CodeGen/AMDGPU/amdhsa-kernarg-preload-num-sgprs.ll +++ b/llvm/test/CodeGen/AMDGPU/amdhsa-kernarg-preload-num-sgprs.ll @@ -11,7 +11,7 @@ ; ASM-LABEL: amdhsa_kernarg_preload_4_implicit_6: ; ASM: .amdhsa_user_sgpr_count 10 ; ASM: .amdhsa_next_free_sgpr 10 -; ASM: ; NumSgprs: 16 +; ASM: ; TotalNumSgprs: 16 ; ASM: ; NumSGPRsForWavesPerEU: 16 ; Test that we include preloaded SGPRs in the GRANULATED_WAVEFRONT_SGPR_COUNT @@ -31,7 +31,7 @@ define amdgpu_kernel void @amdhsa_kernarg_preload_4_implicit_6(i128 inreg) { ret ; ASM-LABEL: amdhsa_kernarg_preload_8_implicit_2: ; ASM: .amdhsa_user_sgpr_count 10 ; ASM: .amdhsa_next_free_sgpr 10 -; ASM: ; NumSgprs: 16 +; ASM: ; TotalNumSgprs: 16 ; ASM: ; NumSGPRsForWavesPerEU: 16 ; Only the kernarg_ptr is enabled so we should have 8 preload kernarg SGPRs, 2 @@ -47,7 +47,7 @@ define amdgpu_kernel void @amdhsa_kernarg_preload_8_implicit_2(i256 inreg) #0 { ; ASM-LABEL: amdhsa_kernarg_preload_1_implicit_2: ; ASM: .amdhsa_user_sgpr_count 3 ; ASM: .amdhsa_next_free_sgpr 3 -; ASM: ; NumSgprs: 9 +; ASM: ; TotalNumSgprs: 9 ; ASM: ; NumSGPRsForWavesPerEU: 9 ; 1 preload, 2 implicit, 6 extra. Rounds up to 16 SGPRs in the KD. @@ -62,7 +62,7 @@ define amdgpu_kernel void @amdhsa_kernarg_preload_1_implicit_2(i32 inreg) #0 { r ; ASM-LABEL: amdhsa_kernarg_preload_0_implicit_2: ; ASM: .amdhsa_user_sgpr_count 2 ; ASM: .amdhsa_next_free_sgpr 0 -; ASM: ; NumSgprs: 6 +; ASM: ; TotalNumSgprs: 6 ; ASM: ; NumSGPRsForWavesPerEU: 6 ; 0 preload kernarg SGPRs, 2 implicit, 6 extra. Rounds up to 8 SGPRs in the KD. diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-metadata-agpr-register-count.ll b/llvm/test/CodeGen/AMDGPU/amdpal-metadata-agpr-register-count.ll index 99a7ae37e0e78d..8f4cb364751d88 100644 --- a/llvm/test/CodeGen/AMDGPU/amdpal-metadata-agpr-register-count.ll +++ b/llvm/test/CodeGen/AMDGPU/amdpal-metadata-agpr-register-count.ll @@ -60,7 +60,9 @@ bb: declare void @undef_func() ; CHECK: .type kernel_call_undef_func -; CHECK: NumAgprs: 32 +; CHECK: .set kernel_call_undef_func.num_agpr, max(0, amdgpu.max_num_agpr) +; CHECK: NumAgprs: kernel_call_undef_func.num_agpr +; CHECK: .set amdgpu.max_num_agpr, 32 define amdgpu_kernel void @kernel_call_undef_func() #0 { bb: call void @undef_func() diff --git a/llvm/test/CodeGen/AMDGPU/attr-amdgpu-flat-work-group-size-vgpr-limit.ll b/llvm/test/CodeGen/AMDGPU/attr-amdgpu-flat-work-group-size-vgpr-limit.ll index e4d427a0b826f8..d45e116beb4e3e 100644 --- a/llvm/test/CodeGen/AMDGPU/attr-amdgpu-flat-work-group-size-vgpr-limit.ll +++ b/llvm/test/CodeGen/AMDGPU/attr-amdgpu-flat-work-group-size-vgpr-limit.ll @@ -547,18 +547,20 @@ define amdgpu_kernel void @f256() #256 { attributes #256 = { nounwind "amdgpu-flat-work-group-size"="256,256" } ; GCN-LABEL: {{^}}f512: -; GFX9: NumVgprs: 128 -; GFX90A: NumVgprs: 128 -; GFX90A: NumAgprs: 128 -; GFX90A: TotalNumVgprs: 256 -; GFX10WGP-WAVE32: NumVgprs: 256 -; GFX10WGP-WAVE64: NumVgprs: 256 -; GFX10CU-WAVE32: NumVgprs: 128 -; GFX10CU-WAVE64: NumVgprs: 128 -; GFX11WGP-WAVE32: NumVgprs: 256 -; GFX11WGP-WAVE64: NumVgprs: 256 -; GFX11CU-WAVE32: NumVgprs: 192 -; GFX11CU-WAVE64: NumVgprs: 192 +; GFX9: .set f512.num_vgpr, max(128, amdgpu.max_num_vgpr) +; GFX90A: .set f512.num_vgpr, max(128, amdgpu.max_num_vgpr) +; GFX90A: .set f512.num_agpr, max(128, amdgpu.max_num_agpr) +; GFX10WGP-WAVE32: .set f512.num_vgpr, max(256, amdgpu.max_num_vgpr) +; GFX10WGP-WAVE64: .set f512.num_vgpr, max(256, amdgpu.max_num_vgpr) +; GFX10CU-WAVE32: .set f512.num_vgpr, max(128, amdgpu.max_num_vgpr) +; GFX10CU-WAVE64: .set f512.num_vgpr, max(128, amdgpu.max_num_vgpr) +; GFX11WGP-WAVE32: .set f512.num_vgpr, max(256, amdgpu.max_num_vgpr) +; GFX11WGP-WAVE64: .set f512.num_vgpr, max(256, amdgpu.max_num_vgpr) +; GFX11CU-WAVE32: .set f512.num_vgpr, max(192, amdgpu.max_num_vgpr) +; GFX11CU-WAVE64: .set f512.num_vgpr, max(192, amdgpu.max_num_vgpr) +; GCN: NumVgprs: f512.num_vgpr +; GFX90A: NumAgprs: f512.num_agpr +; GFX90A: TotalNumVgprs: totalnumvgprs(f512.num_agpr, f512.num_vgpr) define amdgpu_kernel void @f512() #512 { call void @foo() call void @use256vgprs() @@ -567,17 +569,20 @@ define amdgpu_kernel void @f512() #512 { attributes #512 = { nounwind "amdgpu-flat-work-group-size"="512,512" } ; GCN-LABEL: {{^}}f1024: -; GFX9: NumVgprs: 64 -; GFX90A: NumAgprs: 64 -; GFX90A: TotalNumVgprs: 128 -; GFX10WGP-WAVE32: NumVgprs: 128 -; GFX10WGP-WAVE64: NumVgprs: 128 -; GFX10CU-WAVE32: NumVgprs: 64 -; GFX10CU-WAVE64: NumVgprs: 64 -; GFX11WGP-WAVE32: NumVgprs: 192 -; GFX11WGP-WAVE64: NumVgprs: 192 -; GFX11CU-WAVE32: NumVgprs: 96 -; GFX11CU-WAVE64: NumVgprs: 96 +; GFX9: .set f1024.num_vgpr, max(64, amdgpu.max_num_vgpr) +; GFX90A: .set f1024.num_vgpr, max(64, amdgpu.max_num_vgpr) +; GFX90A: .set f1024.num_agpr, max(64, amdgpu.max_num_agpr) +; GFX10WGP-WAVE32: .set f1024.num_vgpr, max(128, amdgpu.max_num_vgpr) +; GFX10WGP-WAVE64: .set f1024.num_vgpr, max(128, amdgpu.max_num_vgpr) +; GFX10CU-WAVE32: .set f1024.num_vgpr, max(64, amdgpu.max_num_vgpr) +; GFX10CU-WAVE64: .set f1024.num_vgpr, max(64, amdgpu.max_num_vgpr) +; GFX11WGP-WAVE32: .set f1024.num_vgpr, max(192, amdgpu.max_num_vgpr) +; GFX11WGP-WAVE64: .set f1024.num_vgpr, max(192, amdgpu.max_num_vgpr) +; GFX11CU-WAVE32: .set f1024.num_vgpr, max(96, amdgpu.max_num_vgpr) +; GFX11CU-WAVE64: .set f1024.num_vgpr, max(96, amdgpu.max_num_vgpr) +; GCN: NumVgprs: f1024.num_vgpr +; GFX90A: NumAgprs: f1024.num_agpr +; GFX90A: TotalNumVgprs: totalnumvgprs(f1024.num_agpr, f1024.num_vgpr) define amdgpu_kernel void @f1024() #1024 { call void @foo() call void @use256vgprs() diff --git a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage-agpr.ll b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage-agpr.ll index a795e995603410..e8898d6a7001cc 100644 --- a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage-agpr.ll +++ b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage-agpr.ll @@ -1,4 +1,4 @@ -; RUN: llc -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 < %s | FileCheck -check-prefixes=ALL,GFX908 %s +; RUN: llc -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 < %s | FileCheck -check-prefix=ALL %s ; RUN: llc -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL,GFX90A %s ; CallGraphAnalysis, which CodeGenSCC order depends on, does not look @@ -8,12 +8,13 @@ @alias = hidden alias void (), ptr @aliasee_default ; ALL-LABEL: {{^}}kernel: -; GFX908: .amdhsa_next_free_vgpr 32 -; GFX908-NEXT: .amdhsa_next_free_sgpr 33 +; ALL: .amdhsa_next_free_vgpr max(totalnumvgprs(kernel.num_agpr, kernel.num_vgpr), 1, 0) +; ALL-NEXT: .amdhsa_next_free_sgpr (max(kernel.numbered_sgpr+(extrasgprs(kernel.uses_vcc, kernel.uses_flat_scratch, 1)), 1, 0))-(extrasgprs(kernel.uses_vcc, kernel.uses_flat_scratch, 1)) +; GFX90A-NEXT: .amdhsa_accum_offset ((((((alignto(max(1, kernel.num_vgpr), 4))/4)-1)&(~65536))&63)+1)*4 -; GFX90A: .amdhsa_next_free_vgpr 59 -; GFX90A-NEXT: .amdhsa_next_free_sgpr 33 -; GFX90A-NEXT: .amdhsa_accum_offset 32 +; ALL: .set kernel.num_vgpr, max(32, aliasee_default.num_vgpr) +; ALL-NEXT: .set kernel.num_agpr, max(0, aliasee_default.num_agpr) +; ALL-NEXT: .set kernel.numbered_sgpr, max(33, aliasee_default.numbered_sgpr) define amdgpu_kernel void @kernel() #0 { bb: call void @alias() #2 @@ -25,6 +26,9 @@ bb: call void asm sideeffect "; clobber a26 ", "~{a26}"() ret void } +; ALL: .set aliasee_default.num_vgpr, 0 +; ALL-NEXT: .set aliasee_default.num_agpr, 27 +; ALL-NEXT: .set aliasee_default.numbered_sgpr, 32 attributes #0 = { noinline norecurse nounwind optnone } attributes #1 = { noinline norecurse nounwind readnone willreturn } diff --git a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage0.ll b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage0.ll index c976cc3d53b5eb..a01268625cedbd 100644 --- a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage0.ll +++ b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage0.ll @@ -7,14 +7,18 @@ @alias0 = hidden alias void (), ptr @aliasee_default_vgpr64_sgpr102 ; CHECK-LABEL: {{^}}kernel0: -; CHECK: .amdhsa_next_free_vgpr 53 -; CHECK-NEXT: .amdhsa_next_free_sgpr 33 +; CHECK: .set kernel0.num_vgpr, max(32, aliasee_default_vgpr64_sgpr102.num_vgpr) +; CHECK-NEXT: .set kernel0.num_agpr, max(0, aliasee_default_vgpr64_sgpr102.num_agpr) +; CHECK-NEXT: .set kernel0.numbered_sgpr, max(33, aliasee_default_vgpr64_sgpr102.numbered_sgpr) define amdgpu_kernel void @kernel0() #0 { bb: call void @alias0() #2 ret void } +; CHECK: .set aliasee_default_vgpr64_sgpr102.num_vgpr, 53 +; CHECK-NEXT: .set aliasee_default_vgpr64_sgpr102.num_agpr, 0 +; CHECK-NEXT: .set aliasee_default_vgpr64_sgpr102.numbered_sgpr, 32 define internal void @aliasee_default_vgpr64_sgpr102() #1 { bb: call void asm sideeffect "; clobber v52 ", "~{v52}"() diff --git a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage1.ll b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage1.ll index edef71ef143dfd..86defe3ba7ec08 100644 --- a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage1.ll +++ b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage1.ll @@ -9,8 +9,12 @@ ; The parent kernel has a higher VGPR usage than the possible callees. ; CHECK-LABEL: {{^}}kernel1: -; CHECK: .amdhsa_next_free_vgpr 41 -; CHECK-NEXT: .amdhsa_next_free_sgpr 33 +; CHECK: .amdhsa_next_free_vgpr max(totalnumvgprs(kernel1.num_agpr, kernel1.num_vgpr), 1, 0) +; CHECK-NEXT: .amdhsa_next_free_sgpr (max(kernel1.numbered_sgpr+(extrasgprs(kernel1.uses_vcc, kernel1.uses_flat_scratch, 1)), 1, 0))-(extrasgprs(kernel1.uses_vcc, kernel1.uses_flat_scratch, 1)) + +; CHECK: .set kernel1.num_vgpr, max(41, aliasee_vgpr32_sgpr76.num_vgpr) +; CHECK-NEXT: .set kernel1.num_agpr, max(0, aliasee_vgpr32_sgpr76.num_agpr) +; CHECK-NEXT: .set kernel1.numbered_sgpr, max(33, aliasee_vgpr32_sgpr76.numbered_sgpr) define amdgpu_kernel void @kernel1() #0 { bb: call void asm sideeffect "; clobber v40 ", "~{v40}"() @@ -18,6 +22,9 @@ bb: ret void } +; CHECK: .set aliasee_vgpr32_sgpr76.num_vgpr, 27 +; CHECK-NEXT: .set aliasee_vgpr32_sgpr76.num_agpr, 0 +; CHECK-NEXT: .set aliasee_vgpr32_sgpr76.numbered_sgpr, 32 define internal void @aliasee_vgpr32_sgpr76() #1 { bb: call void asm sideeffect "; clobber v26 ", "~{v26}"() diff --git a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage2.ll b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage2.ll index bb34ef1a15d2b9..6b1fbd9b6e16a2 100644 --- a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage2.ll +++ b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage2.ll @@ -7,14 +7,21 @@ @alias2 = hidden alias void (), ptr @aliasee_vgpr64_sgpr102 ; CHECK-LABEL: {{^}}kernel2: -; CHECK: .amdhsa_next_free_vgpr 53 -; CHECK-NEXT: .amdhsa_next_free_sgpr 33 +; CHECK: .amdhsa_next_free_vgpr max(totalnumvgprs(kernel2.num_agpr, kernel2.num_vgpr), 1, 0) +; CHECK-NEXT: .amdhsa_next_free_sgpr (max(kernel2.numbered_sgpr+(extrasgprs(kernel2.uses_vcc, kernel2.uses_flat_scratch, 1)), 1, 0))-(extrasgprs(kernel2.uses_vcc, kernel2.uses_flat_scratch, 1)) + +; CHECK: .set kernel2.num_vgpr, max(32, aliasee_vgpr64_sgpr102.num_vgpr) +; CHECK-NEXT: .set kernel2.num_agpr, max(0, aliasee_vgpr64_sgpr102.num_agpr) +; CHECK-NEXT: .set kernel2.numbered_sgpr, max(33, aliasee_vgpr64_sgpr102.numbered_sgpr) define amdgpu_kernel void @kernel2() #0 { bb: call void @alias2() #2 ret void } +; CHECK: .set aliasee_vgpr64_sgpr102.num_vgpr, 53 +; CHECK-NEXT: .set aliasee_vgpr64_sgpr102.num_agpr, 0 +; CHECK-NEXT: .set aliasee_vgpr64_sgpr102.numbered_sgpr, 32 define internal void @aliasee_vgpr64_sgpr102() #1 { bb: call void asm sideeffect "; clobber v52 ", "~{v52}"() diff --git a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage3.ll b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage3.ll index 8a88eb7e51ad72..c81181cd826677 100644 --- a/llvm/test/CodeGen/AMDGPU/call-alias-register-usage3.ll +++ b/llvm/test/CodeGen/AMDGPU/call-alias-register-usage3.ll @@ -7,14 +7,21 @@ @alias3 = hidden alias void (), ptr @aliasee_vgpr256_sgpr102 ; CHECK-LABEL: {{^}}kernel3: -; CHECK: .amdhsa_next_free_vgpr 253 -; CHECK-NEXT: .amdhsa_next_free_sgpr 33 +; CHECK: .amdhsa_next_free_vgpr max(totalnumvgprs(kernel3.num_agpr, kernel3.num_vgpr), 1, 0) +; CHECK-NEXT: .amdhsa_next_free_sgpr (max(kernel3.numbered_sgpr+(extrasgprs(kernel3.uses_vcc, kernel3.uses_flat_scratch, 1)), 1, 0))-(extrasgprs(kernel3.uses_vcc, kernel3.uses_flat_scratch, 1)) + +; CHECK: .set kernel3.num_vgpr, max(32, aliasee_vgpr256_sgpr102.num_vgpr) +; CHECK-NEXT: .set kernel3.num_agpr, max(0, aliasee_vgpr256_sgpr102.num_agpr) +; CHECK-NEXT: .set kernel3.numbered_sgpr, max(33, aliasee_vgpr256_sgpr102.numbered_sgpr) define amdgpu_kernel void @kernel3() #0 { bb: call void @alias3() #2 ret void } +; CHECK: .set aliasee_vgpr256_sgpr102.num_vgpr, 253 +; CHECK-NEXT: .set aliasee_vgpr256_sgpr102.num_agpr, 0 +; CHECK-NEXT: .set aliasee_vgpr256_sgpr102.numbered_sgpr, 33 define internal void @aliasee_vgpr256_sgpr102() #1 { bb: call void asm sideeffect "; clobber v252 ", "~{v252}"() diff --git a/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll b/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll index 6af45035d394f8..dbd00f09943c01 100644 --- a/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll +++ b/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll @@ -7,7 +7,7 @@ ; Make sure to run a GPU with the SGPR allocation bug. ; GCN-LABEL: {{^}}use_vcc: -; GCN: ; NumSgprs: 34 +; GCN: ; TotalNumSgprs: 34 ; GCN: ; NumVgprs: 0 define void @use_vcc() #1 { call void asm sideeffect "", "~{vcc}" () #0 @@ -25,7 +25,7 @@ define void @use_vcc() #1 { ; GCN: v_readlane_b32 s4, v40, 2 ; GCN: s_mov_b32 s33, s4 ; GCN: s_setpc_b64 s[30:31] -; GCN: ; NumSgprs: 36 +; GCN: ; TotalNumSgprs: 36 ; GCN: ; NumVgprs: 41 define void @indirect_use_vcc() #1 { call void @use_vcc() @@ -33,9 +33,9 @@ define void @indirect_use_vcc() #1 { } ; GCN-LABEL: {{^}}indirect_2level_use_vcc_kernel: -; CI: ; NumSgprs: 38 -; VI-NOBUG: ; NumSgprs: 40 -; VI-BUG: ; NumSgprs: 96 +; CI: ; TotalNumSgprs: 38 +; VI-NOBUG: ; TotalNumSgprs: 40 +; VI-BUG: ; TotalNumSgprs: 96 ; GCN: ; NumVgprs: 41 define amdgpu_kernel void @indirect_2level_use_vcc_kernel(ptr addrspace(1) %out) #0 { call void @indirect_use_vcc() @@ -43,8 +43,8 @@ define amdgpu_kernel void @indirect_2level_use_vcc_kernel(ptr addrspace(1) %out) } ; GCN-LABEL: {{^}}use_flat_scratch: -; CI: ; NumSgprs: 36 -; VI: ; NumSgprs: 38 +; CI: ; TotalNumSgprs: 36 +; VI: ; TotalNumSgprs: 38 ; GCN: ; NumVgprs: 0 define void @use_flat_scratch() #1 { call void asm sideeffect "", "~{flat_scratch}" () #0 @@ -52,8 +52,8 @@ define void @use_flat_scratch() #1 { } ; GCN-LABEL: {{^}}indirect_use_flat_scratch: -; CI: ; NumSgprs: 38 -; VI: ; NumSgprs: 40 +; CI: ; TotalNumSgprs: 38 +; VI: ; TotalNumSgprs: 40 ; GCN: ; NumVgprs: 41 define void @indirect_use_flat_scratch() #1 { call void @use_flat_scratch() @@ -61,9 +61,9 @@ define void @indirect_use_flat_scratch() #1 { } ; GCN-LABEL: {{^}}indirect_2level_use_flat_scratch_kernel: -; CI: ; NumSgprs: 38 -; VI-NOBUG: ; NumSgprs: 40 -; VI-BUG: ; NumSgprs: 96 +; CI: ; TotalNumSgprs: 38 +; VI-NOBUG: ; TotalNumSgprs: 40 +; VI-BUG: ; TotalNumSgprs: 96 ; GCN: ; NumVgprs: 41 define amdgpu_kernel void @indirect_2level_use_flat_scratch_kernel(ptr addrspace(1) %out) #0 { call void @indirect_use_flat_scratch() @@ -107,23 +107,23 @@ define void @indirect_use_50_vgpr() #0 { } ; GCN-LABEL: {{^}}use_80_sgpr: -; GCN: ; NumSgprs: 80 +; GCN: ; TotalNumSgprs: 80 define void @use_80_sgpr() #1 { call void asm sideeffect "", "~{s79}"() #0 ret void } ; GCN-LABEL: {{^}}indirect_use_80_sgpr: -; GCN: ; NumSgprs: 82 +; GCN: ; TotalNumSgprs: 82 define void @indirect_use_80_sgpr() #1 { call void @use_80_sgpr() ret void } ; GCN-LABEL: {{^}}indirect_2_level_use_80_sgpr: -; CI: ; NumSgprs: 84 -; VI-NOBUG: ; NumSgprs: 86 -; VI-BUG: ; NumSgprs: 96 +; CI: ; TotalNumSgprs: 84 +; VI-NOBUG: ; TotalNumSgprs: 86 +; VI-BUG: ; TotalNumSgprs: 96 define amdgpu_kernel void @indirect_2_level_use_80_sgpr() #0 { call void @indirect_use_80_sgpr() ret void @@ -176,7 +176,7 @@ define amdgpu_kernel void @multi_call_use_use_stack() #0 { declare void @external() #0 ; GCN-LABEL: {{^}}usage_external: -; NumSgprs: 48 +; TotalNumSgprs: 48 ; NumVgprs: 24 ; GCN: ScratchSize: 16384 ; @@ -190,7 +190,7 @@ define amdgpu_kernel void @usage_external() #0 { declare void @external_recurse() #2 ; GCN-LABEL: {{^}}usage_external_recurse: -; NumSgprs: 48 +; TotalNumSgprs: 48 ; NumVgprs: 24 ; GCN: ScratchSize: 16384 ; @@ -234,10 +234,11 @@ define amdgpu_kernel void @usage_direct_recursion(i32 %n) #0 { ; Make sure there's no assert when a sgpr96 is used. ; GCN-LABEL: {{^}}count_use_sgpr96_external_call ; GCN: ; sgpr96 s[{{[0-9]+}}:{{[0-9]+}}] -; CI: NumSgprs: 84 -; VI-NOBUG: NumSgprs: 86 -; VI-BUG: NumSgprs: 96 -; GCN: NumVgprs: 50 +; GCN: .set count_use_sgpr96_external_call.num_vgpr, max(0, amdgpu.max_num_vgpr) +; GCN: .set count_use_sgpr96_external_call.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; CI: TotalNumSgprs: count_use_sgpr96_external_call.numbered_sgpr+4 +; VI-BUG: TotalNumSgprs: 96 +; GCN: NumVgprs: count_use_sgpr96_external_call.num_vgpr define amdgpu_kernel void @count_use_sgpr96_external_call() { entry: tail call void asm sideeffect "; sgpr96 $0", "s"(<3 x i32> ) #1 @@ -248,10 +249,11 @@ entry: ; Make sure there's no assert when a sgpr160 is used. ; GCN-LABEL: {{^}}count_use_sgpr160_external_call ; GCN: ; sgpr160 s[{{[0-9]+}}:{{[0-9]+}}] -; CI: NumSgprs: 84 -; VI-NOBUG: NumSgprs: 86 -; VI-BUG: NumSgprs: 96 -; GCN: NumVgprs: 50 +; GCN: .set count_use_sgpr160_external_call.num_vgpr, max(0, amdgpu.max_num_vgpr) +; GCN: .set count_use_sgpr160_external_call.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; CI: TotalNumSgprs: count_use_sgpr160_external_call.numbered_sgpr+4 +; VI-BUG: TotalNumSgprs: 96 +; GCN: NumVgprs: count_use_sgpr160_external_call.num_vgpr define amdgpu_kernel void @count_use_sgpr160_external_call() { entry: tail call void asm sideeffect "; sgpr160 $0", "s"(<5 x i32> ) #1 @@ -262,10 +264,11 @@ entry: ; Make sure there's no assert when a vgpr160 is used. ; GCN-LABEL: {{^}}count_use_vgpr160_external_call ; GCN: ; vgpr160 v[{{[0-9]+}}:{{[0-9]+}}] -; CI: NumSgprs: 84 -; VI-NOBUG: NumSgprs: 86 -; VI-BUG: NumSgprs: 96 -; GCN: NumVgprs: 50 +; GCN: .set count_use_vgpr160_external_call.num_vgpr, max(5, amdgpu.max_num_vgpr) +; GCN: .set count_use_vgpr160_external_call.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; CI: TotalNumSgprs: count_use_vgpr160_external_call.numbered_sgpr+4 +; VI-BUG: TotalNumSgprs: 96 +; GCN: NumVgprs: count_use_vgpr160_external_call.num_vgpr define amdgpu_kernel void @count_use_vgpr160_external_call() { entry: tail call void asm sideeffect "; vgpr160 $0", "v"(<5 x i32> ) #1 @@ -273,6 +276,27 @@ entry: ret void } +; GCN: .set amdgpu.max_num_vgpr, 50 +; GCN: .set amdgpu.max_num_agpr, 0 +; GCN: .set amdgpu.max_num_sgpr, 80 + +; GCN-LABEL: amdhsa.kernels: +; GCN: .name: count_use_sgpr96_external_call +; CI: .sgpr_count: 84 +; VI-NOBUG: .sgpr_count: 86 +; VI-BUG: .sgpr_count: 96 +; GCN: .vgpr_count: 50 +; GCN: .name: count_use_sgpr160_external_call +; CI: .sgpr_count: 84 +; VI-NOBUG: .sgpr_count: 86 +; VI-BUG: .sgpr_count: 96 +; GCN: .vgpr_count: 50 +; GCN: .name: count_use_vgpr160_external_call +; CI: .sgpr_count: 84 +; VI-NOBUG: .sgpr_count: 86 +; VI-BUG: .sgpr_count: 96 +; GCN: .vgpr_count: 50 + attributes #0 = { nounwind noinline norecurse "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" } attributes #1 = { nounwind noinline norecurse "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" } attributes #2 = { nounwind noinline } diff --git a/llvm/test/CodeGen/AMDGPU/cndmask-no-def-vcc.ll b/llvm/test/CodeGen/AMDGPU/cndmask-no-def-vcc.ll index 643f2619840a22..ede57f1a0a04ce 100644 --- a/llvm/test/CodeGen/AMDGPU/cndmask-no-def-vcc.ll +++ b/llvm/test/CodeGen/AMDGPU/cndmask-no-def-vcc.ll @@ -33,6 +33,7 @@ bb2: ; GCN-LABEL: {{^}}preserve_condition_undef_flag: ; GCN-NOT: vcc +; GCN: s_endpgm define amdgpu_kernel void @preserve_condition_undef_flag(float %arg, i32 %arg1, float %arg2) { bb0: %tmp = icmp sgt i32 %arg1, 4 diff --git a/llvm/test/CodeGen/AMDGPU/codegen-internal-only-func.ll b/llvm/test/CodeGen/AMDGPU/codegen-internal-only-func.ll index 9d93609b1e8813..f198833059572b 100644 --- a/llvm/test/CodeGen/AMDGPU/codegen-internal-only-func.ll +++ b/llvm/test/CodeGen/AMDGPU/codegen-internal-only-func.ll @@ -1,8 +1,8 @@ ; REQUIRES: asserts -; RUN: not --crash llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=null %s 2>&1 | FileCheck %s -; RUN: not --crash llc -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=null %s 2>&1 | FileCheck %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s +; RUN: llc -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s -; CHECK: function must have been generated already +; CHECK-NOT: func define internal i32 @func() { ret i32 0 diff --git a/llvm/test/CodeGen/AMDGPU/flat-scratch-reg.ll b/llvm/test/CodeGen/AMDGPU/flat-scratch-reg.ll index e4ffedd686ac93..02eb1ad9453291 100644 --- a/llvm/test/CodeGen/AMDGPU/flat-scratch-reg.ll +++ b/llvm/test/CodeGen/AMDGPU/flat-scratch-reg.ll @@ -25,11 +25,11 @@ ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: ; NumSgprs: 8 -; VI-NOXNACK: ; NumSgprs: 8 -; VI-XNACK: ; NumSgprs: 12 -; GFX9-ARCH-FLAT: ; NumSgprs: 14 -; GFX10-ARCH-FLAT: ; NumSgprs: 8 +; CI: ; TotalNumSgprs: 8 +; VI-NOXNACK: ; TotalNumSgprs: 8 +; VI-XNACK: ; TotalNumSgprs: 12 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 14 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 8 define amdgpu_kernel void @no_vcc_no_flat() { entry: call void asm sideeffect "", "~{s7}"() @@ -42,11 +42,11 @@ entry: ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: ; NumSgprs: 10 -; VI-NOXNACK: ; NumSgprs: 10 -; VI-XNACK: ; NumSgprs: 12 -; GFX9-ARCH-FLAT: ; NumSgprs: 14 -; GFX10-ARCH-FLAT: ; NumSgprs: 10 +; CI: ; TotalNumSgprs: 10 +; VI-NOXNACK: ; TotalNumSgprs: 10 +; VI-XNACK: ; TotalNumSgprs: 12 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 14 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 10 define amdgpu_kernel void @vcc_no_flat() { entry: call void asm sideeffect "", "~{s7},~{vcc}"() @@ -59,11 +59,11 @@ entry: ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: ; NumSgprs: 12 -; VI-NOXNACK: ; NumSgprs: 14 -; VI-XNACK: ; NumSgprs: 14 -; GFX9-ARCH-FLAT: ; NumSgprs: 14 -; GFX10-ARCH-FLAT: ; NumSgprs: 8 +; CI: ; TotalNumSgprs: 12 +; VI-NOXNACK: ; TotalNumSgprs: 14 +; VI-XNACK: ; TotalNumSgprs: 14 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 14 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 8 define amdgpu_kernel void @no_vcc_flat() { entry: call void asm sideeffect "", "~{s7},~{flat_scratch}"() @@ -76,11 +76,11 @@ entry: ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: ; NumSgprs: 12 -; VI-NOXNACK: ; NumSgprs: 14 -; VI-XNACK: ; NumSgprs: 14 -; GFX9-ARCH-FLAT: ; NumSgprs: 14 -; GFX10-ARCH-FLAT: ; NumSgprs: 10 +; CI: ; TotalNumSgprs: 12 +; VI-NOXNACK: ; TotalNumSgprs: 14 +; VI-XNACK: ; TotalNumSgprs: 14 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 14 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 10 define amdgpu_kernel void @vcc_flat() { entry: call void asm sideeffect "", "~{s7},~{vcc},~{flat_scratch}"() @@ -96,11 +96,11 @@ entry: ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: NumSgprs: 4 -; VI-NOXNACK: NumSgprs: 6 -; VI-XNACK: NumSgprs: 6 -; GFX9-ARCH-FLAT: ; NumSgprs: 6 -; GFX10-ARCH-FLAT: ; NumSgprs: 0 +; CI: TotalNumSgprs: 4 +; VI-NOXNACK: TotalNumSgprs: 6 +; VI-XNACK: TotalNumSgprs: 6 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 6 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 0 define amdgpu_kernel void @use_flat_scr() #0 { entry: call void asm sideeffect "; clobber ", "~{flat_scratch}"() @@ -113,11 +113,11 @@ entry: ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: NumSgprs: 4 -; VI-NOXNACK: NumSgprs: 6 -; VI-XNACK: NumSgprs: 6 -; GFX9-ARCH-FLAT: ; NumSgprs: 6 -; GFX10-ARCH-FLAT: ; NumSgprs: 0 +; CI: TotalNumSgprs: 4 +; VI-NOXNACK: TotalNumSgprs: 6 +; VI-XNACK: TotalNumSgprs: 6 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 6 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 0 define amdgpu_kernel void @use_flat_scr_lo() #0 { entry: call void asm sideeffect "; clobber ", "~{flat_scratch_lo}"() @@ -130,11 +130,11 @@ entry: ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1 -; CI: NumSgprs: 4 -; VI-NOXNACK: NumSgprs: 6 -; VI-XNACK: NumSgprs: 6 -; GFX9-ARCH-FLAT: ; NumSgprs: 6 -; GFX10-ARCH-FLAT: ; NumSgprs: 0 +; CI: TotalNumSgprs: 4 +; VI-NOXNACK: TotalNumSgprs: 6 +; VI-XNACK: TotalNumSgprs: 6 +; GFX9-ARCH-FLAT: ; TotalNumSgprs: 6 +; GFX10-ARCH-FLAT: ; TotalNumSgprs: 0 define amdgpu_kernel void @use_flat_scr_hi() #0 { entry: call void asm sideeffect "; clobber ", "~{flat_scratch_hi}"() diff --git a/llvm/test/CodeGen/AMDGPU/function-resource-usage.ll b/llvm/test/CodeGen/AMDGPU/function-resource-usage.ll new file mode 100644 index 00000000000000..9e3264eb9c07f2 --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/function-resource-usage.ll @@ -0,0 +1,531 @@ +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-ipra=0 < %s | FileCheck -check-prefix=GCN %s + +; Functions that don't make calls should have constants as its resource usage as no resource information has to be propagated. + +; GCN-LABEL: {{^}}use_vcc: +; GCN: .set use_vcc.num_vgpr, 0 +; GCN: .set use_vcc.num_agpr, 0 +; GCN: .set use_vcc.numbered_sgpr, 32 +; GCN: .set use_vcc.private_seg_size, 0 +; GCN: .set use_vcc.uses_vcc, 1 +; GCN: .set use_vcc.uses_flat_scratch, 0 +; GCN: .set use_vcc.has_dyn_sized_stack, 0 +; GCN: .set use_vcc.has_recursion, 0 +; GCN: .set use_vcc.has_indirect_call, 0 +; GCN: TotalNumSgprs: 36 +; GCN: NumVgprs: 0 +; GCN: ScratchSize: 0 +define void @use_vcc() #1 { + call void asm sideeffect "", "~{vcc}" () #0 + ret void +} + +; GCN-LABEL: {{^}}indirect_use_vcc: +; GCN: .set indirect_use_vcc.num_vgpr, max(41, use_vcc.num_vgpr) +; GCN: .set indirect_use_vcc.num_agpr, max(0, use_vcc.num_agpr) +; GCN: .set indirect_use_vcc.numbered_sgpr, max(34, use_vcc.numbered_sgpr) +; GCN: .set indirect_use_vcc.private_seg_size, 16+(max(use_vcc.private_seg_size)) +; GCN: .set indirect_use_vcc.uses_vcc, or(1, use_vcc.uses_vcc) +; GCN: .set indirect_use_vcc.uses_flat_scratch, or(0, use_vcc.uses_flat_scratch) +; GCN: .set indirect_use_vcc.has_dyn_sized_stack, or(0, use_vcc.has_dyn_sized_stack) +; GCN: .set indirect_use_vcc.has_recursion, or(0, use_vcc.has_recursion) +; GCN: .set indirect_use_vcc.has_indirect_call, or(0, use_vcc.has_indirect_call) +; GCN: TotalNumSgprs: 38 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 16 +define void @indirect_use_vcc() #1 { + call void @use_vcc() + ret void +} + +; GCN-LABEL: {{^}}indirect_2level_use_vcc_kernel: +; GCN: .set indirect_2level_use_vcc_kernel.num_vgpr, max(32, indirect_use_vcc.num_vgpr) +; GCN: .set indirect_2level_use_vcc_kernel.num_agpr, max(0, indirect_use_vcc.num_agpr) +; GCN: .set indirect_2level_use_vcc_kernel.numbered_sgpr, max(33, indirect_use_vcc.numbered_sgpr) +; GCN: .set indirect_2level_use_vcc_kernel.private_seg_size, 0+(max(indirect_use_vcc.private_seg_size)) +; GCN: .set indirect_2level_use_vcc_kernel.uses_vcc, or(1, indirect_use_vcc.uses_vcc) +; GCN: .set indirect_2level_use_vcc_kernel.uses_flat_scratch, or(1, indirect_use_vcc.uses_flat_scratch) +; GCN: .set indirect_2level_use_vcc_kernel.has_dyn_sized_stack, or(0, indirect_use_vcc.has_dyn_sized_stack) +; GCN: .set indirect_2level_use_vcc_kernel.has_recursion, or(0, indirect_use_vcc.has_recursion) +; GCN: .set indirect_2level_use_vcc_kernel.has_indirect_call, or(0, indirect_use_vcc.has_indirect_call) +; GCN: TotalNumSgprs: 40 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 16 +define amdgpu_kernel void @indirect_2level_use_vcc_kernel(ptr addrspace(1) %out) #0 { + call void @indirect_use_vcc() + ret void +} + +; GCN-LABEL: {{^}}use_flat_scratch: +; GCN: .set use_flat_scratch.num_vgpr, 0 +; GCN: .set use_flat_scratch.num_agpr, 0 +; GCN: .set use_flat_scratch.numbered_sgpr, 32 +; GCN: .set use_flat_scratch.private_seg_size, 0 +; GCN: .set use_flat_scratch.uses_vcc, 0 +; GCN: .set use_flat_scratch.uses_flat_scratch, 1 +; GCN: .set use_flat_scratch.has_dyn_sized_stack, 0 +; GCN: .set use_flat_scratch.has_recursion, 0 +; GCN: .set use_flat_scratch.has_indirect_call, 0 +; GCN: TotalNumSgprs: 38 +; GCN: NumVgprs: 0 +; GCN: ScratchSize: 0 +define void @use_flat_scratch() #1 { + call void asm sideeffect "", "~{flat_scratch}" () #0 + ret void +} + +; GCN-LABEL: {{^}}indirect_use_flat_scratch: +; GCN: .set indirect_use_flat_scratch.num_vgpr, max(41, use_flat_scratch.num_vgpr) +; GCN: .set indirect_use_flat_scratch.num_agpr, max(0, use_flat_scratch.num_agpr) +; GCN: .set indirect_use_flat_scratch.numbered_sgpr, max(34, use_flat_scratch.numbered_sgpr) +; GCN: .set indirect_use_flat_scratch.private_seg_size, 16+(max(use_flat_scratch.private_seg_size)) +; GCN: .set indirect_use_flat_scratch.uses_vcc, or(1, use_flat_scratch.uses_vcc) +; GCN: .set indirect_use_flat_scratch.uses_flat_scratch, or(0, use_flat_scratch.uses_flat_scratch) +; GCN: .set indirect_use_flat_scratch.has_dyn_sized_stack, or(0, use_flat_scratch.has_dyn_sized_stack) +; GCN: .set indirect_use_flat_scratch.has_recursion, or(0, use_flat_scratch.has_recursion) +; GCN: .set indirect_use_flat_scratch.has_indirect_call, or(0, use_flat_scratch.has_indirect_call) +; GCN: TotalNumSgprs: 40 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 16 +define void @indirect_use_flat_scratch() #1 { + call void @use_flat_scratch() + ret void +} + +; GCN-LABEL: {{^}}indirect_2level_use_flat_scratch_kernel: +; GCN: .set indirect_2level_use_flat_scratch_kernel.num_vgpr, max(32, indirect_use_flat_scratch.num_vgpr) +; GCN: .set indirect_2level_use_flat_scratch_kernel.num_agpr, max(0, indirect_use_flat_scratch.num_agpr) +; GCN: .set indirect_2level_use_flat_scratch_kernel.numbered_sgpr, max(33, indirect_use_flat_scratch.numbered_sgpr) +; GCN: .set indirect_2level_use_flat_scratch_kernel.private_seg_size, 0+(max(indirect_use_flat_scratch.private_seg_size)) +; GCN: .set indirect_2level_use_flat_scratch_kernel.uses_vcc, or(1, indirect_use_flat_scratch.uses_vcc) +; GCN: .set indirect_2level_use_flat_scratch_kernel.uses_flat_scratch, or(1, indirect_use_flat_scratch.uses_flat_scratch) +; GCN: .set indirect_2level_use_flat_scratch_kernel.has_dyn_sized_stack, or(0, indirect_use_flat_scratch.has_dyn_sized_stack) +; GCN: .set indirect_2level_use_flat_scratch_kernel.has_recursion, or(0, indirect_use_flat_scratch.has_recursion) +; GCN: .set indirect_2level_use_flat_scratch_kernel.has_indirect_call, or(0, indirect_use_flat_scratch.has_indirect_call) +; GCN: TotalNumSgprs: 40 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 16 +define amdgpu_kernel void @indirect_2level_use_flat_scratch_kernel(ptr addrspace(1) %out) #0 { + call void @indirect_use_flat_scratch() + ret void +} + +; GCN-LABEL: {{^}}use_10_vgpr: +; GCN: .set use_10_vgpr.num_vgpr, 10 +; GCN: .set use_10_vgpr.num_agpr, 0 +; GCN: .set use_10_vgpr.numbered_sgpr, 32 +; GCN: .set use_10_vgpr.private_seg_size, 0 +; GCN: .set use_10_vgpr.uses_vcc, 0 +; GCN: .set use_10_vgpr.uses_flat_scratch, 0 +; GCN: .set use_10_vgpr.has_dyn_sized_stack, 0 +; GCN: .set use_10_vgpr.has_recursion, 0 +; GCN: .set use_10_vgpr.has_indirect_call, 0 +; GCN: TotalNumSgprs: 36 +; GCN: NumVgprs: 10 +; GCN: ScratchSize: 0 +define void @use_10_vgpr() #1 { + call void asm sideeffect "", "~{v0},~{v1},~{v2},~{v3},~{v4}"() #0 + call void asm sideeffect "", "~{v5},~{v6},~{v7},~{v8},~{v9}"() #0 + ret void +} + +; GCN-LABEL: {{^}}indirect_use_10_vgpr: +; GCN: .set indirect_use_10_vgpr.num_vgpr, max(41, use_10_vgpr.num_vgpr) +; GCN: .set indirect_use_10_vgpr.num_agpr, max(0, use_10_vgpr.num_agpr) +; GCN: .set indirect_use_10_vgpr.numbered_sgpr, max(34, use_10_vgpr.numbered_sgpr) +; GCN: .set indirect_use_10_vgpr.private_seg_size, 16+(max(use_10_vgpr.private_seg_size)) +; GCN: .set indirect_use_10_vgpr.uses_vcc, or(1, use_10_vgpr.uses_vcc) +; GCN: .set indirect_use_10_vgpr.uses_flat_scratch, or(0, use_10_vgpr.uses_flat_scratch) +; GCN: .set indirect_use_10_vgpr.has_dyn_sized_stack, or(0, use_10_vgpr.has_dyn_sized_stack) +; GCN: .set indirect_use_10_vgpr.has_recursion, or(0, use_10_vgpr.has_recursion) +; GCN: .set indirect_use_10_vgpr.has_indirect_call, or(0, use_10_vgpr.has_indirect_call) +; GCN: TotalNumSgprs: 38 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 16 +define void @indirect_use_10_vgpr() #0 { + call void @use_10_vgpr() + ret void +} + +; GCN-LABEL: {{^}}indirect_2_level_use_10_vgpr: +; GCN: .set indirect_2_level_use_10_vgpr.num_vgpr, max(32, indirect_use_10_vgpr.num_vgpr) +; GCN: .set indirect_2_level_use_10_vgpr.num_agpr, max(0, indirect_use_10_vgpr.num_agpr) +; GCN: .set indirect_2_level_use_10_vgpr.numbered_sgpr, max(33, indirect_use_10_vgpr.numbered_sgpr) +; GCN: .set indirect_2_level_use_10_vgpr.private_seg_size, 0+(max(indirect_use_10_vgpr.private_seg_size)) +; GCN: .set indirect_2_level_use_10_vgpr.uses_vcc, or(1, indirect_use_10_vgpr.uses_vcc) +; GCN: .set indirect_2_level_use_10_vgpr.uses_flat_scratch, or(1, indirect_use_10_vgpr.uses_flat_scratch) +; GCN: .set indirect_2_level_use_10_vgpr.has_dyn_sized_stack, or(0, indirect_use_10_vgpr.has_dyn_sized_stack) +; GCN: .set indirect_2_level_use_10_vgpr.has_recursion, or(0, indirect_use_10_vgpr.has_recursion) +; GCN: .set indirect_2_level_use_10_vgpr.has_indirect_call, or(0, indirect_use_10_vgpr.has_indirect_call) +; GCN: TotalNumSgprs: 40 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 16 +define amdgpu_kernel void @indirect_2_level_use_10_vgpr() #0 { + call void @indirect_use_10_vgpr() + ret void +} + +; GCN-LABEL: {{^}}use_50_vgpr: +; GCN: .set use_50_vgpr.num_vgpr, 50 +; GCN: .set use_50_vgpr.num_agpr, 0 +; GCN: .set use_50_vgpr.numbered_sgpr, 32 +; GCN: .set use_50_vgpr.private_seg_size, 0 +; GCN: .set use_50_vgpr.uses_vcc, 0 +; GCN: .set use_50_vgpr.uses_flat_scratch, 0 +; GCN: .set use_50_vgpr.has_dyn_sized_stack, 0 +; GCN: .set use_50_vgpr.has_recursion, 0 +; GCN: .set use_50_vgpr.has_indirect_call, 0 +; GCN: TotalNumSgprs: 36 +; GCN: NumVgprs: 50 +; GCN: ScratchSize: 0 +define void @use_50_vgpr() #1 { + call void asm sideeffect "", "~{v49}"() #0 + ret void +} + +; GCN-LABEL: {{^}}indirect_use_50_vgpr: +; GCN: .set indirect_use_50_vgpr.num_vgpr, max(41, use_50_vgpr.num_vgpr) +; GCN: .set indirect_use_50_vgpr.num_agpr, max(0, use_50_vgpr.num_agpr) +; GCN: .set indirect_use_50_vgpr.numbered_sgpr, max(34, use_50_vgpr.numbered_sgpr) +; GCN: .set indirect_use_50_vgpr.private_seg_size, 16+(max(use_50_vgpr.private_seg_size)) +; GCN: .set indirect_use_50_vgpr.uses_vcc, or(1, use_50_vgpr.uses_vcc) +; GCN: .set indirect_use_50_vgpr.uses_flat_scratch, or(0, use_50_vgpr.uses_flat_scratch) +; GCN: .set indirect_use_50_vgpr.has_dyn_sized_stack, or(0, use_50_vgpr.has_dyn_sized_stack) +; GCN: .set indirect_use_50_vgpr.has_recursion, or(0, use_50_vgpr.has_recursion) +; GCN: .set indirect_use_50_vgpr.has_indirect_call, or(0, use_50_vgpr.has_indirect_call) +; GCN: TotalNumSgprs: 38 +; GCN: NumVgprs: 50 +; GCN: ScratchSize: 16 +define void @indirect_use_50_vgpr() #0 { + call void @use_50_vgpr() + ret void +} + +; GCN-LABEL: {{^}}use_80_sgpr: +; GCN: .set use_80_sgpr.num_vgpr, 1 +; GCN: .set use_80_sgpr.num_agpr, 0 +; GCN: .set use_80_sgpr.numbered_sgpr, 80 +; GCN: .set use_80_sgpr.private_seg_size, 8 +; GCN: .set use_80_sgpr.uses_vcc, 0 +; GCN: .set use_80_sgpr.uses_flat_scratch, 0 +; GCN: .set use_80_sgpr.has_dyn_sized_stack, 0 +; GCN: .set use_80_sgpr.has_recursion, 0 +; GCN: .set use_80_sgpr.has_indirect_call, 0 +; GCN: TotalNumSgprs: 84 +; GCN: NumVgprs: 1 +; GCN: ScratchSize: 8 +define void @use_80_sgpr() #1 { + call void asm sideeffect "", "~{s79}"() #0 + ret void +} + +; GCN-LABEL: {{^}}indirect_use_80_sgpr: +; GCN: .set indirect_use_80_sgpr.num_vgpr, max(41, use_80_sgpr.num_vgpr) +; GCN: .set indirect_use_80_sgpr.num_agpr, max(0, use_80_sgpr.num_agpr) +; GCN: .set indirect_use_80_sgpr.numbered_sgpr, max(34, use_80_sgpr.numbered_sgpr) +; GCN: .set indirect_use_80_sgpr.private_seg_size, 16+(max(use_80_sgpr.private_seg_size)) +; GCN: .set indirect_use_80_sgpr.uses_vcc, or(1, use_80_sgpr.uses_vcc) +; GCN: .set indirect_use_80_sgpr.uses_flat_scratch, or(0, use_80_sgpr.uses_flat_scratch) +; GCN: .set indirect_use_80_sgpr.has_dyn_sized_stack, or(0, use_80_sgpr.has_dyn_sized_stack) +; GCN: .set indirect_use_80_sgpr.has_recursion, or(0, use_80_sgpr.has_recursion) +; GCN: .set indirect_use_80_sgpr.has_indirect_call, or(0, use_80_sgpr.has_indirect_call) +; GCN: TotalNumSgprs: 84 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 24 +define void @indirect_use_80_sgpr() #1 { + call void @use_80_sgpr() + ret void +} + +; GCN-LABEL: {{^}}indirect_2_level_use_80_sgpr: +; GCN: .set indirect_2_level_use_80_sgpr.num_vgpr, max(32, indirect_use_80_sgpr.num_vgpr) +; GCN: .set indirect_2_level_use_80_sgpr.num_agpr, max(0, indirect_use_80_sgpr.num_agpr) +; GCN: .set indirect_2_level_use_80_sgpr.numbered_sgpr, max(33, indirect_use_80_sgpr.numbered_sgpr) +; GCN: .set indirect_2_level_use_80_sgpr.private_seg_size, 0+(max(indirect_use_80_sgpr.private_seg_size)) +; GCN: .set indirect_2_level_use_80_sgpr.uses_vcc, or(1, indirect_use_80_sgpr.uses_vcc) +; GCN: .set indirect_2_level_use_80_sgpr.uses_flat_scratch, or(1, indirect_use_80_sgpr.uses_flat_scratch) +; GCN: .set indirect_2_level_use_80_sgpr.has_dyn_sized_stack, or(0, indirect_use_80_sgpr.has_dyn_sized_stack) +; GCN: .set indirect_2_level_use_80_sgpr.has_recursion, or(0, indirect_use_80_sgpr.has_recursion) +; GCN: .set indirect_2_level_use_80_sgpr.has_indirect_call, or(0, indirect_use_80_sgpr.has_indirect_call) +; GCN: TotalNumSgprs: 86 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 24 +define amdgpu_kernel void @indirect_2_level_use_80_sgpr() #0 { + call void @indirect_use_80_sgpr() + ret void +} + +; GCN-LABEL: {{^}}use_stack0: +; GCN: .set use_stack0.num_vgpr, 1 +; GCN: .set use_stack0.num_agpr, 0 +; GCN: .set use_stack0.numbered_sgpr, 33 +; GCN: .set use_stack0.private_seg_size, 2052 +; GCN: .set use_stack0.uses_vcc, 0 +; GCN: .set use_stack0.uses_flat_scratch, 0 +; GCN: .set use_stack0.has_dyn_sized_stack, 0 +; GCN: .set use_stack0.has_recursion, 0 +; GCN: .set use_stack0.has_indirect_call, 0 +; GCN: TotalNumSgprs: 37 +; GCN: NumVgprs: 1 +; GCN: ScratchSize: 2052 +define void @use_stack0() #1 { + %alloca = alloca [512 x i32], align 4, addrspace(5) + call void asm sideeffect "; use $0", "v"(ptr addrspace(5) %alloca) #0 + ret void +} + +; GCN-LABEL: {{^}}use_stack1: +; GCN: .set use_stack1.num_vgpr, 1 +; GCN: .set use_stack1.num_agpr, 0 +; GCN: .set use_stack1.numbered_sgpr, 33 +; GCN: .set use_stack1.private_seg_size, 404 +; GCN: .set use_stack1.uses_vcc, 0 +; GCN: .set use_stack1.uses_flat_scratch, 0 +; GCN: .set use_stack1.has_dyn_sized_stack, 0 +; GCN: .set use_stack1.has_recursion, 0 +; GCN: .set use_stack1.has_indirect_call, 0 +; GCN: TotalNumSgprs: 37 +; GCN: NumVgprs: 1 +; GCN: ScratchSize: 404 +define void @use_stack1() #1 { + %alloca = alloca [100 x i32], align 4, addrspace(5) + call void asm sideeffect "; use $0", "v"(ptr addrspace(5) %alloca) #0 + ret void +} + +; GCN-LABEL: {{^}}indirect_use_stack: +; GCN: .set indirect_use_stack.num_vgpr, max(41, use_stack0.num_vgpr) +; GCN: .set indirect_use_stack.num_agpr, max(0, use_stack0.num_agpr) +; GCN: .set indirect_use_stack.numbered_sgpr, max(34, use_stack0.numbered_sgpr) +; GCN: .set indirect_use_stack.private_seg_size, 80+(max(use_stack0.private_seg_size)) +; GCN: .set indirect_use_stack.uses_vcc, or(1, use_stack0.uses_vcc) +; GCN: .set indirect_use_stack.uses_flat_scratch, or(0, use_stack0.uses_flat_scratch) +; GCN: .set indirect_use_stack.has_dyn_sized_stack, or(0, use_stack0.has_dyn_sized_stack) +; GCN: .set indirect_use_stack.has_recursion, or(0, use_stack0.has_recursion) +; GCN: .set indirect_use_stack.has_indirect_call, or(0, use_stack0.has_indirect_call) +; GCN: TotalNumSgprs: 38 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 2132 +define void @indirect_use_stack() #1 { + %alloca = alloca [16 x i32], align 4, addrspace(5) + call void asm sideeffect "; use $0", "v"(ptr addrspace(5) %alloca) #0 + call void @use_stack0() + ret void +} + +; GCN-LABEL: {{^}}indirect_2_level_use_stack: +; GCN: .set indirect_2_level_use_stack.num_vgpr, max(32, indirect_use_stack.num_vgpr) +; GCN: .set indirect_2_level_use_stack.num_agpr, max(0, indirect_use_stack.num_agpr) +; GCN: .set indirect_2_level_use_stack.numbered_sgpr, max(33, indirect_use_stack.numbered_sgpr) +; GCN: .set indirect_2_level_use_stack.private_seg_size, 0+(max(indirect_use_stack.private_seg_size)) +; GCN: .set indirect_2_level_use_stack.uses_vcc, or(1, indirect_use_stack.uses_vcc) +; GCN: .set indirect_2_level_use_stack.uses_flat_scratch, or(1, indirect_use_stack.uses_flat_scratch) +; GCN: .set indirect_2_level_use_stack.has_dyn_sized_stack, or(0, indirect_use_stack.has_dyn_sized_stack) +; GCN: .set indirect_2_level_use_stack.has_recursion, or(0, indirect_use_stack.has_recursion) +; GCN: .set indirect_2_level_use_stack.has_indirect_call, or(0, indirect_use_stack.has_indirect_call) +; GCN: TotalNumSgprs: 40 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 2132 +define amdgpu_kernel void @indirect_2_level_use_stack() #0 { + call void @indirect_use_stack() + ret void +} + + +; Should be maximum of callee usage +; GCN-LABEL: {{^}}multi_call_use_use_stack: +; GCN: .set multi_call_use_use_stack.num_vgpr, max(41, use_stack0.num_vgpr, use_stack1.num_vgpr) +; GCN: .set multi_call_use_use_stack.num_agpr, max(0, use_stack0.num_agpr, use_stack1.num_agpr) +; GCN: .set multi_call_use_use_stack.numbered_sgpr, max(42, use_stack0.numbered_sgpr, use_stack1.numbered_sgpr) +; GCN: .set multi_call_use_use_stack.private_seg_size, 0+(max(use_stack0.private_seg_size, use_stack1.private_seg_size)) +; GCN: .set multi_call_use_use_stack.uses_vcc, or(1, use_stack0.uses_vcc, use_stack1.uses_vcc) +; GCN: .set multi_call_use_use_stack.uses_flat_scratch, or(1, use_stack0.uses_flat_scratch, use_stack1.uses_flat_scratch) +; GCN: .set multi_call_use_use_stack.has_dyn_sized_stack, or(0, use_stack0.has_dyn_sized_stack, use_stack1.has_dyn_sized_stack) +; GCN: .set multi_call_use_use_stack.has_recursion, or(0, use_stack0.has_recursion, use_stack1.has_recursion) +; GCN: .set multi_call_use_use_stack.has_indirect_call, or(0, use_stack0.has_indirect_call, use_stack1.has_indirect_call) +; GCN: TotalNumSgprs: 48 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 2052 +define amdgpu_kernel void @multi_call_use_use_stack() #0 { + call void @use_stack0() + call void @use_stack1() + ret void +} + +declare void @external() #0 + +; GCN-LABEL: {{^}}multi_call_with_external: +; GCN: .set multi_call_with_external.num_vgpr, max(41, amdgpu.max_num_vgpr) +; GCN: .set multi_call_with_external.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: .set multi_call_with_external.numbered_sgpr, max(42, amdgpu.max_num_sgpr) +; GCN: .set multi_call_with_external.private_seg_size, 0 +; GCN: .set multi_call_with_external.uses_vcc, 1 +; GCN: .set multi_call_with_external.uses_flat_scratch, 1 +; GCN: .set multi_call_with_external.has_dyn_sized_stack, 1 +; GCN: .set multi_call_with_external.has_recursion, 0 +; GCN: .set multi_call_with_external.has_indirect_call, 1 +; GCN: TotalNumSgprs: multi_call_with_external.numbered_sgpr+6 +; GCN: NumVgprs: multi_call_with_external.num_vgpr +; GCN: ScratchSize: 0 +define amdgpu_kernel void @multi_call_with_external() #0 { + call void @use_stack0() + call void @use_stack1() + call void @external() + ret void +} + +; GCN-LABEL: {{^}}usage_external: +; GCN: .set usage_external.num_vgpr, max(32, amdgpu.max_num_vgpr) +; GCN: .set usage_external.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: .set usage_external.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; GCN: .set usage_external.private_seg_size, 0 +; GCN: .set usage_external.uses_vcc, 1 +; GCN: .set usage_external.uses_flat_scratch, 1 +; GCN: .set usage_external.has_dyn_sized_stack, 1 +; GCN: .set usage_external.has_recursion, 0 +; GCN: .set usage_external.has_indirect_call, 1 +; GCN: TotalNumSgprs: usage_external.numbered_sgpr+6 +; GCN: NumVgprs: usage_external.num_vgpr +; GCN: ScratchSize: 0 +define amdgpu_kernel void @usage_external() #0 { + call void @external() + ret void +} + +declare void @external_recurse() #2 + +; GCN-LABEL: {{^}}usage_external_recurse: +; GCN: .set usage_external_recurse.num_vgpr, max(32, amdgpu.max_num_vgpr) +; GCN: .set usage_external_recurse.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: .set usage_external_recurse.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; GCN: .set usage_external_recurse.private_seg_size, 0 +; GCN: .set usage_external_recurse.uses_vcc, 1 +; GCN: .set usage_external_recurse.uses_flat_scratch, 1 +; GCN: .set usage_external_recurse.has_dyn_sized_stack, 1 +; GCN: .set usage_external_recurse.has_recursion, 1 +; GCN: .set usage_external_recurse.has_indirect_call, 1 +; GCN: TotalNumSgprs: usage_external_recurse.numbered_sgpr+6 +; GCN: NumVgprs: usage_external_recurse.num_vgpr +; GCN: ScratchSize: 0 +define amdgpu_kernel void @usage_external_recurse() #0 { + call void @external_recurse() + ret void +} + +; GCN-LABEL: {{^}}direct_recursion_use_stack: +; GCN: .set direct_recursion_use_stack.num_vgpr, 41 +; GCN: .set direct_recursion_use_stack.num_agpr, 0 +; GCN: .set direct_recursion_use_stack.numbered_sgpr, 36 +; GCN: .set direct_recursion_use_stack.private_seg_size, 2064 +; GCN: .set direct_recursion_use_stack.uses_vcc, 1 +; GCN: .set direct_recursion_use_stack.uses_flat_scratch, 0 +; GCN: .set direct_recursion_use_stack.has_dyn_sized_stack, 0 +; GCN: .set direct_recursion_use_stack.has_recursion, 1 +; GCN: .set direct_recursion_use_stack.has_indirect_call, 0 +; GCN: TotalNumSgprs: 40 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 2064 +define void @direct_recursion_use_stack(i32 %val) #2 { + %alloca = alloca [512 x i32], align 4, addrspace(5) + call void asm sideeffect "; use $0", "v"(ptr addrspace(5) %alloca) #0 + %cmp = icmp eq i32 %val, 0 + br i1 %cmp, label %ret, label %call + +call: + %val.sub1 = sub i32 %val, 1 + call void @direct_recursion_use_stack(i32 %val.sub1) + br label %ret + +ret: + ret void +} + +; GCN-LABEL: {{^}}usage_direct_recursion: +; GCN: .set usage_direct_recursion.num_vgpr, max(32, direct_recursion_use_stack.num_vgpr) +; GCN: .set usage_direct_recursion.num_agpr, max(0, direct_recursion_use_stack.num_agpr) +; GCN: .set usage_direct_recursion.numbered_sgpr, max(33, direct_recursion_use_stack.numbered_sgpr) +; GCN: .set usage_direct_recursion.private_seg_size, 0+(max(direct_recursion_use_stack.private_seg_size)) +; GCN: .set usage_direct_recursion.uses_vcc, or(1, direct_recursion_use_stack.uses_vcc) +; GCN: .set usage_direct_recursion.uses_flat_scratch, or(1, direct_recursion_use_stack.uses_flat_scratch) +; GCN: .set usage_direct_recursion.has_dyn_sized_stack, or(0, direct_recursion_use_stack.has_dyn_sized_stack) +; GCN: .set usage_direct_recursion.has_recursion, or(1, direct_recursion_use_stack.has_recursion) +; GCN: .set usage_direct_recursion.has_indirect_call, or(0, direct_recursion_use_stack.has_indirect_call) +; GCN: TotalNumSgprs: 42 +; GCN: NumVgprs: 41 +; GCN: ScratchSize: 2064 +define amdgpu_kernel void @usage_direct_recursion(i32 %n) #0 { + call void @direct_recursion_use_stack(i32 %n) + ret void +} + +; Make sure there's no assert when a sgpr96 is used. +; GCN-LABEL: {{^}}count_use_sgpr96_external_call +; GCN: .set count_use_sgpr96_external_call.num_vgpr, max(32, amdgpu.max_num_vgpr) +; GCN: .set count_use_sgpr96_external_call.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: .set count_use_sgpr96_external_call.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; GCN: .set count_use_sgpr96_external_call.private_seg_size, 0 +; GCN: .set count_use_sgpr96_external_call.uses_vcc, 1 +; GCN: .set count_use_sgpr96_external_call.uses_flat_scratch, 1 +; GCN: .set count_use_sgpr96_external_call.has_dyn_sized_stack, 1 +; GCN: .set count_use_sgpr96_external_call.has_recursion, 0 +; GCN: .set count_use_sgpr96_external_call.has_indirect_call, 1 +; GCN: TotalNumSgprs: count_use_sgpr96_external_call.numbered_sgpr+6 +; GCN: NumVgprs: count_use_sgpr96_external_call.num_vgpr +; GCN: ScratchSize: 0 +define amdgpu_kernel void @count_use_sgpr96_external_call() { +entry: + tail call void asm sideeffect "; sgpr96 $0", "s"(<3 x i32> ) #1 + call void @external() + ret void +} + +; Make sure there's no assert when a sgpr160 is used. +; GCN-LABEL: {{^}}count_use_sgpr160_external_call +; GCN: .set count_use_sgpr160_external_call.num_vgpr, max(32, amdgpu.max_num_vgpr) +; GCN: .set count_use_sgpr160_external_call.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: .set count_use_sgpr160_external_call.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; GCN: .set count_use_sgpr160_external_call.private_seg_size, 0 +; GCN: .set count_use_sgpr160_external_call.uses_vcc, 1 +; GCN: .set count_use_sgpr160_external_call.uses_flat_scratch, 1 +; GCN: .set count_use_sgpr160_external_call.has_dyn_sized_stack, 1 +; GCN: .set count_use_sgpr160_external_call.has_recursion, 0 +; GCN: .set count_use_sgpr160_external_call.has_indirect_call, 1 +; GCN: TotalNumSgprs: count_use_sgpr160_external_call.numbered_sgpr+6 +; GCN: NumVgprs: count_use_sgpr160_external_call.num_vgpr +; GCN: ScratchSize: 0 +define amdgpu_kernel void @count_use_sgpr160_external_call() { +entry: + tail call void asm sideeffect "; sgpr160 $0", "s"(<5 x i32> ) #1 + call void @external() + ret void +} + +; Make sure there's no assert when a vgpr160 is used. +; GCN-LABEL: {{^}}count_use_vgpr160_external_call +; GCN: .set count_use_vgpr160_external_call.num_vgpr, max(32, amdgpu.max_num_vgpr) +; GCN: .set count_use_vgpr160_external_call.num_agpr, max(0, amdgpu.max_num_agpr) +; GCN: .set count_use_vgpr160_external_call.numbered_sgpr, max(33, amdgpu.max_num_sgpr) +; GCN: .set count_use_vgpr160_external_call.private_seg_size, 0 +; GCN: .set count_use_vgpr160_external_call.uses_vcc, 1 +; GCN: .set count_use_vgpr160_external_call.uses_flat_scratch, 1 +; GCN: .set count_use_vgpr160_external_call.has_dyn_sized_stack, 1 +; GCN: .set count_use_vgpr160_external_call.has_recursion, 0 +; GCN: .set count_use_vgpr160_external_call.has_indirect_call, 1 +; GCN: TotalNumSgprs: count_use_vgpr160_external_call.numbered_sgpr+6 +; GCN: NumVgprs: count_use_vgpr160_external_call.num_vgpr +; GCN: ScratchSize: 0 +define amdgpu_kernel void @count_use_vgpr160_external_call() { +entry: + tail call void asm sideeffect "; vgpr160 $0", "v"(<5 x i32> ) #1 + call void @external() + ret void +} + +; Added at the of the .s are the module level maximums +; GCN: .set amdgpu.max_num_vgpr, 50 +; GCN: .set amdgpu.max_num_agpr, 0 +; GCN: .set amdgpu.max_num_sgpr, 80 + +attributes #0 = { nounwind noinline norecurse } +attributes #1 = { nounwind noinline norecurse } +attributes #2 = { nounwind noinline } diff --git a/llvm/test/CodeGen/AMDGPU/inline-asm-reserved-regs.ll b/llvm/test/CodeGen/AMDGPU/inline-asm-reserved-regs.ll index f20d720c3876ba..dce4162c246247 100644 --- a/llvm/test/CodeGen/AMDGPU/inline-asm-reserved-regs.ll +++ b/llvm/test/CodeGen/AMDGPU/inline-asm-reserved-regs.ll @@ -41,7 +41,7 @@ entry: } ; FIXME: This should warn too -; ERR-NOT: warning +; ERR-NOT: warning: inline asm clobber list contains reserved registers define amdgpu_kernel void @def_exec(ptr addrspace(1) %ptr) { entry: %exec = call i64 asm sideeffect "; def $0", "={exec}"() diff --git a/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll b/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll index 9d1368b2ec105a..e7c77d3123e825 100644 --- a/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll +++ b/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll @@ -3,6 +3,18 @@ declare i32 @llvm.amdgcn.workitem.id.x() +define <2 x i64> @f1() #0 { +; GFX11-LABEL: f1: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_mov_b32_e32 v0, 0 +; GFX11-NEXT: v_mov_b32_e32 v1, 0 +; GFX11-NEXT: v_mov_b32_e32 v2, 0 +; GFX11-NEXT: v_mov_b32_e32 v3, 0 +; GFX11-NEXT: s_setpc_b64 s[30:31] + ret <2 x i64> zeroinitializer +} + define void @f0() { ; GFX11-LABEL: f0: ; GFX11: ; %bb.0: ; %bb @@ -36,18 +48,6 @@ bb: ret void } -define <2 x i64> @f1() #0 { -; GFX11-LABEL: f1: -; GFX11: ; %bb.0: -; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) -; GFX11-NEXT: v_mov_b32_e32 v0, 0 -; GFX11-NEXT: v_mov_b32_e32 v1, 0 -; GFX11-NEXT: v_mov_b32_e32 v2, 0 -; GFX11-NEXT: v_mov_b32_e32 v3, 0 -; GFX11-NEXT: s_setpc_b64 s[30:31] - ret <2 x i64> zeroinitializer -} - ; FIXME: This generates "instid1(/* invalid instid value */)". define amdgpu_kernel void @f2(i32 %arg, i32 %arg1, i32 %arg2, i1 %arg3, i32 %arg4, i1 %arg5, ptr %arg6, i32 %arg7, i32 %arg8, i32 %arg9, i32 %arg10, i1 %arg11) { ; GFX11-LABEL: f2: diff --git a/llvm/test/CodeGen/AMDGPU/ipra.ll b/llvm/test/CodeGen/AMDGPU/ipra.ll index b49931379b84a5..957f404c8cdbed 100644 --- a/llvm/test/CodeGen/AMDGPU/ipra.ll +++ b/llvm/test/CodeGen/AMDGPU/ipra.ll @@ -30,7 +30,7 @@ define hidden void @func() #1 { ; GCN-NOT: writelane ; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v8 -; GCN: ; NumSgprs: 37 +; GCN: ; TotalNumSgprs: 37 ; GCN: ; NumVgprs: 9 define amdgpu_kernel void @kernel_call() #0 { %vgpr = load volatile i32, ptr addrspace(1) undef @@ -48,7 +48,7 @@ define amdgpu_kernel void @kernel_call() #0 { ; GCN-NOT: readlane ; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v8 -; GCN: ; NumSgprs: 34 +; GCN: ; TotalNumSgprs: 34 ; GCN: ; NumVgprs: 10 define void @func_regular_call() #1 { %vgpr = load volatile i32, ptr addrspace(1) undef @@ -64,7 +64,7 @@ define void @func_regular_call() #1 { ; GCN-NEXT: s_addc_u32 s17, ; GCN-NEXT: s_setpc_b64 s[16:17] -; GCN: ; NumSgprs: 32 +; GCN: ; TotalNumSgprs: 32 ; GCN: ; NumVgprs: 8 define void @func_tail_call() #1 { tail call void @func() @@ -77,7 +77,7 @@ define void @func_tail_call() #1 { ; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v8 ; GCN: s_setpc_b64 -; GCN: ; NumSgprs: 34 +; GCN: ; TotalNumSgprs: 34 ; GCN: ; NumVgprs: 10 define void @func_call_tail_call() #1 { %vgpr = load volatile i32, ptr addrspace(1) undef @@ -105,13 +105,6 @@ define void @test_funcx2() #0 { ret void } -; GCN-LABEL: {{^}}wombat: -define weak amdgpu_kernel void @wombat(ptr %arg, ptr %arg2) { -bb: - call void @hoge() #0 - ret void -} - ; Make sure we save/restore the return address around the call. ; Function Attrs: norecurse define internal void @hoge() #2 { @@ -128,6 +121,13 @@ bb: ret void } +; GCN-LABEL: {{^}}wombat: +define weak amdgpu_kernel void @wombat(ptr %arg, ptr %arg2) { +bb: + call void @hoge() #0 + ret void +} + declare dso_local void @eggs() diff --git a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll index 7bf1b8746fd87b..c9e24b721c41e1 100644 --- a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll +++ b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll @@ -149,12 +149,9 @@ ; GCN-O0-NEXT: Lazy Machine Block Frequency Analysis ; GCN-O0-NEXT: Machine Optimization Remark Emitter ; GCN-O0-NEXT: Stack Frame Layout Analysis -; GCN-O0-NEXT: Function register usage analysis -; GCN-O0-NEXT: FunctionPass Manager -; GCN-O0-NEXT: Lazy Machine Block Frequency Analysis -; GCN-O0-NEXT: Machine Optimization Remark Emitter -; GCN-O0-NEXT: AMDGPU Assembly Printer -; GCN-O0-NEXT: Free MachineFunction +; GCN-O0-NEXT: Function register usage analysis +; GCN-O0-NEXT: AMDGPU Assembly Printer +; GCN-O0-NEXT: Free MachineFunction ; GCN-O1:Target Library Information ; GCN-O1-NEXT:Target Pass Configuration @@ -427,12 +424,9 @@ ; GCN-O1-NEXT: Lazy Machine Block Frequency Analysis ; GCN-O1-NEXT: Machine Optimization Remark Emitter ; GCN-O1-NEXT: Stack Frame Layout Analysis -; GCN-O1-NEXT: Function register usage analysis -; GCN-O1-NEXT: FunctionPass Manager -; GCN-O1-NEXT: Lazy Machine Block Frequency Analysis -; GCN-O1-NEXT: Machine Optimization Remark Emitter -; GCN-O1-NEXT: AMDGPU Assembly Printer -; GCN-O1-NEXT: Free MachineFunction +; GCN-O1-NEXT: Function register usage analysis +; GCN-O1-NEXT: AMDGPU Assembly Printer +; GCN-O1-NEXT: Free MachineFunction ; GCN-O1-OPTS:Target Library Information ; GCN-O1-OPTS-NEXT:Target Pass Configuration @@ -733,12 +727,9 @@ ; GCN-O1-OPTS-NEXT: Lazy Machine Block Frequency Analysis ; GCN-O1-OPTS-NEXT: Machine Optimization Remark Emitter ; GCN-O1-OPTS-NEXT: Stack Frame Layout Analysis -; GCN-O1-OPTS-NEXT: Function register usage analysis -; GCN-O1-OPTS-NEXT: FunctionPass Manager -; GCN-O1-OPTS-NEXT: Lazy Machine Block Frequency Analysis -; GCN-O1-OPTS-NEXT: Machine Optimization Remark Emitter -; GCN-O1-OPTS-NEXT: AMDGPU Assembly Printer -; GCN-O1-OPTS-NEXT: Free MachineFunction +; GCN-O1-OPTS-NEXT: Function register usage analysis +; GCN-O1-OPTS-NEXT: AMDGPU Assembly Printer +; GCN-O1-OPTS-NEXT: Free MachineFunction ; GCN-O2:Target Library Information ; GCN-O2-NEXT:Target Pass Configuration @@ -1045,12 +1036,9 @@ ; GCN-O2-NEXT: Lazy Machine Block Frequency Analysis ; GCN-O2-NEXT: Machine Optimization Remark Emitter ; GCN-O2-NEXT: Stack Frame Layout Analysis -; GCN-O2-NEXT: Function register usage analysis -; GCN-O2-NEXT: FunctionPass Manager -; GCN-O2-NEXT: Lazy Machine Block Frequency Analysis -; GCN-O2-NEXT: Machine Optimization Remark Emitter -; GCN-O2-NEXT: AMDGPU Assembly Printer -; GCN-O2-NEXT: Free MachineFunction +; GCN-O2-NEXT: Function register usage analysis +; GCN-O2-NEXT: AMDGPU Assembly Printer +; GCN-O2-NEXT: Free MachineFunction ; GCN-O3:Target Library Information ; GCN-O3-NEXT:Target Pass Configuration @@ -1369,12 +1357,9 @@ ; GCN-O3-NEXT: Lazy Machine Block Frequency Analysis ; GCN-O3-NEXT: Machine Optimization Remark Emitter ; GCN-O3-NEXT: Stack Frame Layout Analysis -; GCN-O3-NEXT: Function register usage analysis -; GCN-O3-NEXT: FunctionPass Manager -; GCN-O3-NEXT: Lazy Machine Block Frequency Analysis -; GCN-O3-NEXT: Machine Optimization Remark Emitter -; GCN-O3-NEXT: AMDGPU Assembly Printer -; GCN-O3-NEXT: Free MachineFunction +; GCN-O3-NEXT: Function register usage analysis +; GCN-O3-NEXT: AMDGPU Assembly Printer +; GCN-O3-NEXT: Free MachineFunction define void @empty() { ret void diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll index 34dcdaf29677e4..b508ffff8050a8 100644 --- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll +++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll @@ -9,6 +9,19 @@ @lds.size.1.align.1 = internal unnamed_addr addrspace(3) global [1 x i8] undef, align 1 @lds.size.16.align.16 = internal unnamed_addr addrspace(3) global [16 x i8] undef, align 16 +; GCN-LABEL: {{^}}f0: +; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0 +; GCN-DAG: v_mov_b32_e32 [[TREE:v[0-9]+]], 3 +; GCN: ds_write_b8 [[NULL]], [[TREE]] +define void @f0() { +; OPT-LABEL: @f0() { +; OPT-NEXT: store i8 3, ptr addrspace(3) @llvm.amdgcn.module.lds, align 1 +; OPT-NEXT: ret void +; + store i8 3, ptr addrspace(3) @lds.size.1.align.1, align 1 + ret void +} + ; GCN-LABEL: {{^}}k0: ; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0 ; GCN-DAG: v_mov_b32_e32 [[ONE:v[0-9]+]], 1 @@ -29,16 +42,3 @@ define amdgpu_kernel void @k0() { call void @f0() ret void } - -; GCN-LABEL: {{^}}f0: -; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0 -; GCN-DAG: v_mov_b32_e32 [[TREE:v[0-9]+]], 3 -; GCN: ds_write_b8 [[NULL]], [[TREE]] -define void @f0() { -; OPT-LABEL: @f0() { -; OPT-NEXT: store i8 3, ptr addrspace(3) @llvm.amdgcn.module.lds, align 1 -; OPT-NEXT: ret void -; - store i8 3, ptr addrspace(3) @lds.size.1.align.1, align 1 - ret void -} diff --git a/llvm/test/CodeGen/AMDGPU/module-lds-false-sharing.ll b/llvm/test/CodeGen/AMDGPU/module-lds-false-sharing.ll index 27b71dd471a839..aa16937d7d897d 100644 --- a/llvm/test/CodeGen/AMDGPU/module-lds-false-sharing.ll +++ b/llvm/test/CodeGen/AMDGPU/module-lds-false-sharing.ll @@ -24,6 +24,55 @@ store i32 0, ptr addrspace(3) @used_by_kernel } ; CHECK: ; LDSByteSize: 4 bytes +define void @nonkernel() { +; GFX9-LABEL: nonkernel: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_mov_b32_e32 v0, 0 +; GFX9-NEXT: v_mov_b32_e32 v1, v0 +; GFX9-NEXT: ds_write_b32 v0, v0 offset:8 +; GFX9-NEXT: ds_write_b64 v0, v[0:1] +; GFX9-NEXT: s_waitcnt lgkmcnt(0) +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: nonkernel: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_mov_b32_e32 v0, 0 +; GFX10-NEXT: v_mov_b32_e32 v1, v0 +; GFX10-NEXT: ds_write_b32 v0, v0 offset:8 +; GFX10-NEXT: ds_write_b64 v0, v[0:1] +; GFX10-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; G_GFX9-LABEL: nonkernel: +; G_GFX9: ; %bb.0: +; G_GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; G_GFX9-NEXT: v_mov_b32_e32 v2, 0 +; G_GFX9-NEXT: v_mov_b32_e32 v3, 8 +; G_GFX9-NEXT: v_mov_b32_e32 v0, 0 +; G_GFX9-NEXT: v_mov_b32_e32 v1, 0 +; G_GFX9-NEXT: ds_write_b32 v3, v2 +; G_GFX9-NEXT: ds_write_b64 v2, v[0:1] +; G_GFX9-NEXT: s_waitcnt lgkmcnt(0) +; G_GFX9-NEXT: s_setpc_b64 s[30:31] +; +; G_GFX10-LABEL: nonkernel: +; G_GFX10: ; %bb.0: +; G_GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; G_GFX10-NEXT: v_mov_b32_e32 v2, 0 +; G_GFX10-NEXT: v_mov_b32_e32 v3, 8 +; G_GFX10-NEXT: v_mov_b32_e32 v0, 0 +; G_GFX10-NEXT: v_mov_b32_e32 v1, 0 +; G_GFX10-NEXT: ds_write_b32 v3, v2 +; G_GFX10-NEXT: ds_write_b64 v2, v[0:1] +; G_GFX10-NEXT: s_waitcnt lgkmcnt(0) +; G_GFX10-NEXT: s_setpc_b64 s[30:31] + store i32 0, ptr addrspace(3) @used_by_both + store double 0.0, ptr addrspace(3) @used_by_function + ret void +} + ; Needs to allocate both variables, store to used_by_both is at sizeof(double) define amdgpu_kernel void @withcall() { ; GFX9-LABEL: withcall: @@ -171,55 +220,5 @@ define amdgpu_kernel void @nocall_false_sharing() { } ; CHECK: ; LDSByteSize: 4 bytes - -define void @nonkernel() { -; GFX9-LABEL: nonkernel: -; GFX9: ; %bb.0: -; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) -; GFX9-NEXT: v_mov_b32_e32 v0, 0 -; GFX9-NEXT: v_mov_b32_e32 v1, v0 -; GFX9-NEXT: ds_write_b32 v0, v0 offset:8 -; GFX9-NEXT: ds_write_b64 v0, v[0:1] -; GFX9-NEXT: s_waitcnt lgkmcnt(0) -; GFX9-NEXT: s_setpc_b64 s[30:31] -; -; GFX10-LABEL: nonkernel: -; GFX10: ; %bb.0: -; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) -; GFX10-NEXT: v_mov_b32_e32 v0, 0 -; GFX10-NEXT: v_mov_b32_e32 v1, v0 -; GFX10-NEXT: ds_write_b32 v0, v0 offset:8 -; GFX10-NEXT: ds_write_b64 v0, v[0:1] -; GFX10-NEXT: s_waitcnt lgkmcnt(0) -; GFX10-NEXT: s_setpc_b64 s[30:31] -; -; G_GFX9-LABEL: nonkernel: -; G_GFX9: ; %bb.0: -; G_GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) -; G_GFX9-NEXT: v_mov_b32_e32 v2, 0 -; G_GFX9-NEXT: v_mov_b32_e32 v3, 8 -; G_GFX9-NEXT: v_mov_b32_e32 v0, 0 -; G_GFX9-NEXT: v_mov_b32_e32 v1, 0 -; G_GFX9-NEXT: ds_write_b32 v3, v2 -; G_GFX9-NEXT: ds_write_b64 v2, v[0:1] -; G_GFX9-NEXT: s_waitcnt lgkmcnt(0) -; G_GFX9-NEXT: s_setpc_b64 s[30:31] -; -; G_GFX10-LABEL: nonkernel: -; G_GFX10: ; %bb.0: -; G_GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) -; G_GFX10-NEXT: v_mov_b32_e32 v2, 0 -; G_GFX10-NEXT: v_mov_b32_e32 v3, 8 -; G_GFX10-NEXT: v_mov_b32_e32 v0, 0 -; G_GFX10-NEXT: v_mov_b32_e32 v1, 0 -; G_GFX10-NEXT: ds_write_b32 v3, v2 -; G_GFX10-NEXT: ds_write_b64 v2, v[0:1] -; G_GFX10-NEXT: s_waitcnt lgkmcnt(0) -; G_GFX10-NEXT: s_setpc_b64 s[30:31] - store i32 0, ptr addrspace(3) @used_by_both - store double 0.0, ptr addrspace(3) @used_by_function - ret void -} - !llvm.module.flags = !{!0} !0 = !{i32 1, !"amdhsa_code_object_version", i32 500} diff --git a/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll b/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll index 6d18f354e65422..a2baa56ea0c989 100644 --- a/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll +++ b/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll @@ -1,7 +1,7 @@ ; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1100 <%s | FileCheck %s ; CHECK-LABEL: {{^}}_amdgpu_cs_main: -; CHECK: ; NumSgprs: 4 +; CHECK: ; TotalNumSgprs: 4 ; CHECK: ; NumVgprs: 2 ; CHECK: .amdgpu_pal_metadata ; CHECK-NEXT: --- diff --git a/llvm/test/CodeGen/AMDGPU/recursion.ll b/llvm/test/CodeGen/AMDGPU/recursion.ll index d58477c194ea62..c0d228e1254e64 100644 --- a/llvm/test/CodeGen/AMDGPU/recursion.ll +++ b/llvm/test/CodeGen/AMDGPU/recursion.ll @@ -3,7 +3,11 @@ ; RUN: sed 's/CODE_OBJECT_VERSION/600/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefixes=V5 %s ; CHECK-LABEL: {{^}}recursive: +; CHECK: .set recursive.private_seg_size, 16+(max(16384)) ; CHECK: ScratchSize: 16 + +; V5-LABEL: {{^}}recursive: +; V5: .set recursive.has_recursion, 1 define void @recursive() { call void @recursive() store volatile i32 0, ptr addrspace(1) undef @@ -11,18 +15,22 @@ define void @recursive() { } ; CHECK-LABEL: {{^}}tail_recursive: +; CHECK: .set tail_recursive.private_seg_size, 0 ; CHECK: ScratchSize: 0 define void @tail_recursive() { tail call void @tail_recursive() ret void } +; CHECK: .set calls_tail_recursive.private_seg_size, 0+(max(tail_recursive.private_seg_size)) define void @calls_tail_recursive() norecurse { tail call void @tail_recursive() ret void } ; CHECK-LABEL: {{^}}tail_recursive_with_stack: +; CHECK: .set tail_recursive_with_stack.private_seg_size, 8 +; CHECK: .set tail_recursive_with_stack.has_recursion, 1 define void @tail_recursive_with_stack() { %alloca = alloca i32, addrspace(5) store volatile i32 0, ptr addrspace(5) %alloca @@ -33,11 +41,11 @@ define void @tail_recursive_with_stack() { ; For an arbitrary recursive call, report a large number for unknown stack ; usage for code object v4 and older ; CHECK-LABEL: {{^}}calls_recursive: -; CHECK: .amdhsa_private_segment_fixed_size 16400{{$}} +; CHECK: .set calls_recursive.private_seg_size, 0+(max(16384, recursive.private_seg_size)) ; ; V5-LABEL: {{^}}calls_recursive: -; V5: .amdhsa_private_segment_fixed_size 0{{$}} -; V5: .amdhsa_uses_dynamic_stack 1 +; V5: .set calls_recursive.private_seg_size, 0+(max(recursive.private_seg_size)) +; V5: .set calls_recursive.has_dyn_sized_stack, or(0, recursive.has_dyn_sized_stack) define amdgpu_kernel void @calls_recursive() { call void @recursive() ret void @@ -46,7 +54,7 @@ define amdgpu_kernel void @calls_recursive() { ; Make sure we do not report a huge stack size for tail recursive ; functions ; CHECK-LABEL: {{^}}kernel_indirectly_calls_tail_recursive: -; CHECK: .amdhsa_private_segment_fixed_size 0{{$}} +; CHECK: .set kernel_indirectly_calls_tail_recursive.private_seg_size, 0+(max(calls_tail_recursive.private_seg_size)) define amdgpu_kernel void @kernel_indirectly_calls_tail_recursive() { call void @calls_tail_recursive() ret void @@ -57,22 +65,22 @@ define amdgpu_kernel void @kernel_indirectly_calls_tail_recursive() { ; in the kernel. ; CHECK-LABEL: {{^}}kernel_calls_tail_recursive: -; CHECK: .amdhsa_private_segment_fixed_size 16384{{$}} +; CHECK: .set kernel_calls_tail_recursive.private_seg_size, 0+(max(16384, tail_recursive.private_seg_size)) ; ; V5-LABEL: {{^}}kernel_calls_tail_recursive: -; V5: .amdhsa_private_segment_fixed_size 0{{$}} -; V5: .amdhsa_uses_dynamic_stack 1 +; V5: .set kernel_calls_tail_recursive.private_seg_size, 0+(max(tail_recursive.private_seg_size)) +; V5: .set kernel_calls_tail_recursive.has_recursion, or(1, tail_recursive.has_recursion) define amdgpu_kernel void @kernel_calls_tail_recursive() { call void @tail_recursive() ret void } ; CHECK-LABEL: {{^}}kernel_calls_tail_recursive_with_stack: -; CHECK: .amdhsa_private_segment_fixed_size 16384{{$}} +; CHECK: .set kernel_calls_tail_recursive_with_stack.private_seg_size, 0+(max(16384, tail_recursive_with_stack.private_seg_size)) ; ; V5-LABEL: {{^}}kernel_calls_tail_recursive_with_stack: -; V5: .amdhsa_private_segment_fixed_size 8{{$}} -; V5: .amdhsa_uses_dynamic_stack 1 +; V5: .set kernel_calls_tail_recursive_with_stack.private_seg_size, 0+(max(tail_recursive_with_stack.private_seg_size)) +; V5: .set kernel_calls_tail_recursive_with_stack.has_dyn_sized_stack, or(0, tail_recursive_with_stack.has_dyn_sized_stack) define amdgpu_kernel void @kernel_calls_tail_recursive_with_stack() { call void @tail_recursive_with_stack() ret void diff --git a/llvm/test/CodeGen/AMDGPU/register-count-comments.ll b/llvm/test/CodeGen/AMDGPU/register-count-comments.ll index 8d12b3fe626da8..35e11ad6a648ba 100644 --- a/llvm/test/CodeGen/AMDGPU/register-count-comments.ll +++ b/llvm/test/CodeGen/AMDGPU/register-count-comments.ll @@ -7,7 +7,7 @@ declare i32 @llvm.amdgcn.mbcnt.hi(i32, i32) #0 ; SI-LABEL: {{^}}foo: ; SI: .section .AMDGPU.csdata ; SI: ; Kernel info: -; SI: ; NumSgprs: {{[0-9]+}} +; SI: ; TotalNumSgprs: {{[0-9]+}} ; SI: ; NumVgprs: {{[0-9]+}} define amdgpu_kernel void @foo(ptr addrspace(1) noalias %out, ptr addrspace(1) %abase, ptr addrspace(1) %bbase) nounwind { %mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0); diff --git a/llvm/test/CodeGen/AMDGPU/resource-optimization-remarks.ll b/llvm/test/CodeGen/AMDGPU/resource-optimization-remarks.ll index 002de8bb4eb510..8bbae59f468f1d 100644 --- a/llvm/test/CodeGen/AMDGPU/resource-optimization-remarks.ll +++ b/llvm/test/CodeGen/AMDGPU/resource-optimization-remarks.ll @@ -2,7 +2,7 @@ ; RUN: FileCheck -check-prefix=REMARK %s < %t ; STDERR: remark: foo.cl:27:0: Function Name: test_kernel -; STDERR-NEXT: remark: foo.cl:27:0: SGPRs: 28 +; STDERR-NEXT: remark: foo.cl:27:0: TotalSGPRs: 28 ; STDERR-NEXT: remark: foo.cl:27:0: VGPRs: 9 ; STDERR-NEXT: remark: foo.cl:27:0: AGPRs: 43 ; STDERR-NEXT: remark: foo.cl:27:0: ScratchSize [bytes/lane]: 0 @@ -27,7 +27,7 @@ ; REMARK-NEXT: DebugLoc: { File: foo.cl, Line: 27, Column: 0 } ; REMARK-NEXT: Function: test_kernel ; REMARK-NEXT: Args: -; REMARK-NEXT: - String: ' SGPRs: ' +; REMARK-NEXT: - String: ' TotalSGPRs: ' ; REMARK-NEXT: - NumSGPR: '28' ; REMARK-NEXT: ... ; REMARK-NEXT: --- !Analysis @@ -122,7 +122,7 @@ define void @test_func() !dbg !6 { } ; STDERR: remark: foo.cl:8:0: Function Name: empty_kernel -; STDERR-NEXT: remark: foo.cl:8:0: SGPRs: 4 +; STDERR-NEXT: remark: foo.cl:8:0: TotalSGPRs: 4 ; STDERR-NEXT: remark: foo.cl:8:0: VGPRs: 0 ; STDERR-NEXT: remark: foo.cl:8:0: AGPRs: 0 ; STDERR-NEXT: remark: foo.cl:8:0: ScratchSize [bytes/lane]: 0 @@ -141,12 +141,12 @@ define void @empty_func() !dbg !8 { } ; STDERR: remark: foo.cl:64:0: Function Name: test_indirect_call -; STDERR-NEXT: remark: foo.cl:64:0: SGPRs: 39 -; STDERR-NEXT: remark: foo.cl:64:0: VGPRs: 32 -; STDERR-NEXT: remark: foo.cl:64:0: AGPRs: 10 +; STDERR-NEXT: remark: foo.cl:64:0: TotalSGPRs: test_indirect_call.numbered_sgpr+6 +; STDERR-NEXT: remark: foo.cl:64:0: VGPRs: test_indirect_call.num_vgpr +; STDERR-NEXT: remark: foo.cl:64:0: AGPRs: test_indirect_call.num_agpr ; STDERR-NEXT: remark: foo.cl:64:0: ScratchSize [bytes/lane]: 0 ; STDERR-NEXT: remark: foo.cl:64:0: Dynamic Stack: True -; STDERR-NEXT: remark: foo.cl:64:0: Occupancy [waves/SIMD]: 8 +; STDERR-NEXT: remark: foo.cl:64:0: Occupancy [waves/SIMD]: occupancy(10, 4, 256, 8, 8, max(test_indirect_call.numbered_sgpr+(extrasgprs(test_indirect_call.uses_vcc, test_indirect_call.uses_flat_scratch, 1)), 1, 0), max(totalnumvgprs(test_indirect_call.num_agpr, test_indirect_call.num_vgpr), 1, 0)) ; STDERR-NEXT: remark: foo.cl:64:0: SGPRs Spill: 0 ; STDERR-NEXT: remark: foo.cl:64:0: VGPRs Spill: 0 ; STDERR-NEXT: remark: foo.cl:64:0: LDS Size [bytes/block]: 0 @@ -159,12 +159,12 @@ define amdgpu_kernel void @test_indirect_call() !dbg !9 { } ; STDERR: remark: foo.cl:74:0: Function Name: test_indirect_w_static_stack -; STDERR-NEXT: remark: foo.cl:74:0: SGPRs: 39 -; STDERR-NEXT: remark: foo.cl:74:0: VGPRs: 32 -; STDERR-NEXT: remark: foo.cl:74:0: AGPRs: 10 +; STDERR-NEXT: remark: foo.cl:74:0: TotalSGPRs: test_indirect_w_static_stack.numbered_sgpr+6 +; STDERR-NEXT: remark: foo.cl:74:0: VGPRs: test_indirect_w_static_stack.num_vgpr +; STDERR-NEXT: remark: foo.cl:74:0: AGPRs: test_indirect_w_static_stack.num_agpr ; STDERR-NEXT: remark: foo.cl:74:0: ScratchSize [bytes/lane]: 144 ; STDERR-NEXT: remark: foo.cl:74:0: Dynamic Stack: True -; STDERR-NEXT: remark: foo.cl:74:0: Occupancy [waves/SIMD]: 8 +; STDERR-NEXT: remark: foo.cl:74:0: Occupancy [waves/SIMD]: occupancy(10, 4, 256, 8, 8, max(test_indirect_w_static_stack.numbered_sgpr+(extrasgprs(test_indirect_w_static_stack.uses_vcc, test_indirect_w_static_stack.uses_flat_scratch, 1)), 1, 0), max(totalnumvgprs(test_indirect_w_static_stack.num_agpr, test_indirect_w_static_stack.num_vgpr), 1, 0)) ; STDERR-NEXT: remark: foo.cl:74:0: SGPRs Spill: 0 ; STDERR-NEXT: remark: foo.cl:74:0: VGPRs Spill: 0 ; STDERR-NEXT: remark: foo.cl:74:0: LDS Size [bytes/block]: 0 diff --git a/llvm/test/CodeGen/AMDGPU/resource-usage-dead-function.ll b/llvm/test/CodeGen/AMDGPU/resource-usage-dead-function.ll index bba59ba4d80302..5d5aad76afd095 100644 --- a/llvm/test/CodeGen/AMDGPU/resource-usage-dead-function.ll +++ b/llvm/test/CodeGen/AMDGPU/resource-usage-dead-function.ll @@ -1,6 +1,6 @@ -; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - | FileCheck -check-prefix=GCN %s -; RUN: sed 's/CODE_OBJECT_VERSION/500/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - | FileCheck -check-prefix=GCN-V5 %s -; RUN: sed 's/CODE_OBJECT_VERSION/600/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - | FileCheck -check-prefix=GCN-V5 %s +; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - | FileCheck -check-prefixes=GCN,ALL %s +; RUN: sed 's/CODE_OBJECT_VERSION/500/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - | FileCheck -check-prefixes=GCN-V5,ALL %s +; RUN: sed 's/CODE_OBJECT_VERSION/600/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - | FileCheck -check-prefixes=GCN-V5,ALL %s ; Make sure there's no assertion when trying to report the resource ; usage for a function which becomes dead during codegen. @@ -21,9 +21,10 @@ define internal fastcc void @unreachable() { ; GCN-NOT: s_swappc_b64 ; GCN: s_endpgm -; GCN: .amdhsa_private_segment_fixed_size 0 -; GCN-NOT: .amdhsa_uses_dynamic_stack 0 -; GCN-V5: .amdhsa_uses_dynamic_stack 0 +; GCN-NOT: .amdhsa_uses_dynamic_stack +; GCN-V5: .amdhsa_uses_dynamic_stack +; ALL: .set entry.private_seg_size, 0 +; ALL: .set entry.has_dyn_sized_stack, 0 define amdgpu_kernel void @entry() { bb0: br i1 false, label %bb1, label %bb2