[AMDGPU] Do not select llvm.amdgcn.inverse.ballot with wrong wave size (

llvm#99470) This produces a "cannot select" error, instead of failing later with an illegal vgpr to sgpr copy.
sgundapa · Jul 23, 2024 · afbb61a · afbb61a
1 parent ebe7b9c
commit afbb61a
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 4 deletions.
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -212,11 +212,13 @@ def EXIT_STRICT_WQM : SPseudoInstSI <(outs SReg_1:$sdst), (ins SReg_1:$src0)> {
 }
 
 let usesCustomInserter = 1 in {
+let WaveSizePredicate = isWave32 in
 def S_INVERSE_BALLOT_U32 : SPseudoInstSI<
   (outs SReg_32:$sdst), (ins SSrc_b32:$mask),
   [(set i1:$sdst, (int_amdgcn_inverse_ballot i32:$mask))]
 >;
 
+let WaveSizePredicate = isWave64 in
 def S_INVERSE_BALLOT_U64 : SPseudoInstSI<
   (outs SReg_64:$sdst), (ins SSrc_b64:$mask),
   [(set i1:$sdst, (int_amdgcn_inverse_ballot i64:$mask))]

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i32.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i32.ll
@@ -1,6 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=+wavefrontsize32,-wavefrontsize64 -global-isel=1 -verify-machineinstrs < %s | FileCheck  -check-prefixes=GFX11,GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=+wavefrontsize32,-wavefrontsize64 -global-isel=0 -verify-machineinstrs < %s | FileCheck  -check-prefixes=GFX11,SDAG %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=+wavefrontsize32 -global-isel=1 -verify-machineinstrs < %s | FileCheck  -check-prefixes=GFX11,GISEL %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=+wavefrontsize32 -global-isel=0 -verify-machineinstrs < %s | FileCheck  -check-prefixes=GFX11,SDAG %s
+
+; RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -global-isel=1 < %s 2>&1 | FileCheck  -check-prefix=GISEL-ERR %s
+; RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -global-isel=0 < %s 2>&1 | FileCheck  -check-prefix=SDAG-ERR %s
+
+; GISEL-ERR: LLVM ERROR: cannot select: {{.*}}  = G_INTRINSIC intrinsic(@llvm.amdgcn.inverse.ballot)
+; SDAG-ERR: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.inverse.ballot
 
 declare i1 @llvm.amdgcn.inverse.ballot(i32)
 

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i64.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i64.ll
@@ -1,6 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=-wavefrontsize32,+wavefrontsize64 -global-isel=1 -verify-machineinstrs < %s | FileCheck -check-prefixes=GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=-wavefrontsize32,+wavefrontsize64 -global-isel=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=SDAG %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=+wavefrontsize64 -global-isel=1 -verify-machineinstrs < %s | FileCheck -check-prefixes=GISEL %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -mattr=+wavefrontsize64 -global-isel=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=SDAG %s
+
+; RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -global-isel=1 < %s 2>&1 | FileCheck  -check-prefix=GISEL-ERR %s
+; RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -global-isel=0 < %s 2>&1 | FileCheck  -check-prefix=SDAG-ERR %s
+
+; GISEL-ERR: LLVM ERROR: cannot select: {{.*}}  = G_INTRINSIC intrinsic(@llvm.amdgcn.inverse.ballot)
+; SDAG-ERR: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.inverse.ballot
 
 declare i1 @llvm.amdgcn.inverse.ballot.i64(i64)