-
Notifications
You must be signed in to change notification settings - Fork 11.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[CostModel][X86] Add initial costs for non-lane-crossing one/two input shuffles #114254
base: main
Are you sure you want to change the base?
Conversation
…t shuffles Most of the x86 shuffle instructions operate within each 128-bit subvector lane, but our shuffle costs struggle to handle this and have to fallback to worst case shuffles that reference elements from any lane. This patch detects shuffle masks that we know are "inlane" and enable us to assume a cheaper shuffle cost.
@llvm/pr-subscribers-backend-x86 Author: Simon Pilgrim (RKSimon) ChangesMost of the x86 shuffle instructions operate within each 128-bit subvector lane, but our shuffle costs struggle to handle this and have to fallback to worst case shuffles that reference elements from any lane. This patch detects shuffle masks that we know are "inlane" and enable us to assume a cheaper shuffle cost. Patch is 192.03 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/114254.diff 17 Files Affected:
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 520284d1d7a488..109125bbc43285 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1766,6 +1766,21 @@ InstructionCost X86TTIImpl::getShuffleCost(
LT.first = NumOfDests * NumOfShufflesPerDest;
}
+ // Attempt to detect a cheaper inlane shuffle, avoiding subvector permutation.
+ bool IsInLaneShuffle = false;
+ if ((Kind == TTI::SK_PermuteSingleSrc || Kind == TTI::SK_PermuteTwoSrc) &&
+ LT.first == 1 && LT.second.isVector() &&
+ LT.second.getVectorNumElements() == Mask.size() &&
+ (LT.second.is256BitVector() || LT.second.is512BitVector())) {
+ IsInLaneShuffle = true;
+ unsigned NumLanes = LT.second.getSizeInBits() / 128;
+ unsigned NumEltPerLane = Mask.size() / NumLanes;
+ for (auto [I, M] : enumerate(Mask))
+ if (0 <= M)
+ IsInLaneShuffle &=
+ ((M % Mask.size()) / NumEltPerLane) == (I / NumEltPerLane);
+ }
+
static const CostTblEntry AVX512VBMIShuffleTbl[] = {
{TTI::SK_Reverse, MVT::v64i8, 1}, // vpermb
{TTI::SK_Reverse, MVT::v32i8, 1}, // vpermb
@@ -1897,6 +1912,25 @@ InstructionCost X86TTIImpl::getShuffleCost(
if (auto KindCost = Entry->Cost[CostKind])
return LT.first * *KindCost;
+ static const CostTblEntry AVX2InLaneShuffleTbl[] = {
+ {TTI::SK_PermuteSingleSrc, MVT::v16i16, 1}, // vpshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v16f16, 1}, // vpshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 1}, // vpshufb
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 2}, // 2*vpshufb + vpor
+ };
+
+ if (IsInLaneShuffle && ST->hasAVX2())
+ if (const auto *Entry =
+ CostTableLookup(AVX2InLaneShuffleTbl, Kind, LT.second))
+ return LT.first * Entry->Cost;
+
static const CostTblEntry AVX2ShuffleTbl[] = {
{TTI::SK_Broadcast, MVT::v4f64, 1}, // vbroadcastpd
{TTI::SK_Broadcast, MVT::v8f32, 1}, // vbroadcastps
@@ -1973,6 +2007,31 @@ InstructionCost X86TTIImpl::getShuffleCost(
if (const auto *Entry = CostTableLookup(XOPShuffleTbl, Kind, LT.second))
return LT.first * Entry->Cost;
+ static const CostTblEntry AVX1InLaneShuffleTbl[] = {
+ {TTI::SK_PermuteSingleSrc, MVT::v16i16, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+ {TTI::SK_PermuteSingleSrc, MVT::v16f16, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpermilpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpermilps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ };
+
+ if (IsInLaneShuffle && ST->hasAVX())
+ if (const auto *Entry =
+ CostTableLookup(AVX1InLaneShuffleTbl, Kind, LT.second))
+ return LT.first * Entry->Cost;
+
static const CostTblEntry AVX1ShuffleTbl[] = {
{TTI::SK_Broadcast, MVT::v4f64, 2}, // vperm2f128 + vpermilpd
{TTI::SK_Broadcast, MVT::v8f32, 2}, // vperm2f128 + vpermilps
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
index 91314d39690520..adaae37929ee3b 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
index 33431083c68bb3..f2e2b3dd394781 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
index 039758e0b6e384..3117d9c280da16 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
index 6a82a4a7432ef8..e91db1b0cb14a3 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
index 1af0b9d0fac69a..392b2358e39fc0 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
@@ -236,7 +236,7 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
@@ -267,7 +267,7 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instructi...
[truncated]
|
@llvm/pr-subscribers-llvm-analysis Author: Simon Pilgrim (RKSimon) ChangesMost of the x86 shuffle instructions operate within each 128-bit subvector lane, but our shuffle costs struggle to handle this and have to fallback to worst case shuffles that reference elements from any lane. This patch detects shuffle masks that we know are "inlane" and enable us to assume a cheaper shuffle cost. Patch is 192.03 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/114254.diff 17 Files Affected:
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 520284d1d7a488..109125bbc43285 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1766,6 +1766,21 @@ InstructionCost X86TTIImpl::getShuffleCost(
LT.first = NumOfDests * NumOfShufflesPerDest;
}
+ // Attempt to detect a cheaper inlane shuffle, avoiding subvector permutation.
+ bool IsInLaneShuffle = false;
+ if ((Kind == TTI::SK_PermuteSingleSrc || Kind == TTI::SK_PermuteTwoSrc) &&
+ LT.first == 1 && LT.second.isVector() &&
+ LT.second.getVectorNumElements() == Mask.size() &&
+ (LT.second.is256BitVector() || LT.second.is512BitVector())) {
+ IsInLaneShuffle = true;
+ unsigned NumLanes = LT.second.getSizeInBits() / 128;
+ unsigned NumEltPerLane = Mask.size() / NumLanes;
+ for (auto [I, M] : enumerate(Mask))
+ if (0 <= M)
+ IsInLaneShuffle &=
+ ((M % Mask.size()) / NumEltPerLane) == (I / NumEltPerLane);
+ }
+
static const CostTblEntry AVX512VBMIShuffleTbl[] = {
{TTI::SK_Reverse, MVT::v64i8, 1}, // vpermb
{TTI::SK_Reverse, MVT::v32i8, 1}, // vpermb
@@ -1897,6 +1912,25 @@ InstructionCost X86TTIImpl::getShuffleCost(
if (auto KindCost = Entry->Cost[CostKind])
return LT.first * *KindCost;
+ static const CostTblEntry AVX2InLaneShuffleTbl[] = {
+ {TTI::SK_PermuteSingleSrc, MVT::v16i16, 1}, // vpshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v16f16, 1}, // vpshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 1}, // vpshufb
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 2}, // 2*vpshufb + vpor
+ };
+
+ if (IsInLaneShuffle && ST->hasAVX2())
+ if (const auto *Entry =
+ CostTableLookup(AVX2InLaneShuffleTbl, Kind, LT.second))
+ return LT.first * Entry->Cost;
+
static const CostTblEntry AVX2ShuffleTbl[] = {
{TTI::SK_Broadcast, MVT::v4f64, 1}, // vbroadcastpd
{TTI::SK_Broadcast, MVT::v8f32, 1}, // vbroadcastps
@@ -1973,6 +2007,31 @@ InstructionCost X86TTIImpl::getShuffleCost(
if (const auto *Entry = CostTableLookup(XOPShuffleTbl, Kind, LT.second))
return LT.first * Entry->Cost;
+ static const CostTblEntry AVX1InLaneShuffleTbl[] = {
+ {TTI::SK_PermuteSingleSrc, MVT::v16i16, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+ {TTI::SK_PermuteSingleSrc, MVT::v16f16, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpermilpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpermilps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ };
+
+ if (IsInLaneShuffle && ST->hasAVX())
+ if (const auto *Entry =
+ CostTableLookup(AVX1InLaneShuffleTbl, Kind, LT.second))
+ return LT.first * Entry->Cost;
+
static const CostTblEntry AVX1ShuffleTbl[] = {
{TTI::SK_Broadcast, MVT::v4f64, 2}, // vperm2f128 + vpermilpd
{TTI::SK_Broadcast, MVT::v8f32, 2}, // vperm2f128 + vpermilps
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
index 91314d39690520..adaae37929ee3b 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
index 33431083c68bb3..f2e2b3dd394781 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
index 039758e0b6e384..3117d9c280da16 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
index 6a82a4a7432ef8..e91db1b0cb14a3 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
index 1af0b9d0fac69a..392b2358e39fc0 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
@@ -236,7 +236,7 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
@@ -267,7 +267,7 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instructi...
[truncated]
|
You can test this locally with the following command:git-clang-format --diff 45f420e34476d2963e13b2f916be1e5a73ec95ae d3d459d64743c33444af04a73d1ca0f56b5e0b1a --extensions cpp -- llvm/lib/Target/X86/X86TargetTransformInfo.cpp View the diff from clang-format here.diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 109125bbc4..8a912c76f8 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1915,15 +1915,15 @@ InstructionCost X86TTIImpl::getShuffleCost(
static const CostTblEntry AVX2InLaneShuffleTbl[] = {
{TTI::SK_PermuteSingleSrc, MVT::v16i16, 1}, // vpshufb
{TTI::SK_PermuteSingleSrc, MVT::v16f16, 1}, // vpshufb
- {TTI::SK_PermuteSingleSrc, MVT::v32i8, 1}, // vpshufb
-
- {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
- {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
- {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpshufd + vpblendd
- {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpshufd + vpblendd
- {TTI::SK_PermuteTwoSrc, MVT::v16i16, 2}, // 2*vpshufb + vpor
- {TTI::SK_PermuteTwoSrc, MVT::v16f16, 2}, // 2*vpshufb + vpor
- {TTI::SK_PermuteTwoSrc, MVT::v32i8, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 1}, // vpshufb
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 2}, // 2*vpshufb + vpor
};
if (IsInLaneShuffle && ST->hasAVX2())
@@ -2012,19 +2012,19 @@ InstructionCost X86TTIImpl::getShuffleCost(
// + vpor + vinsertf128
{TTI::SK_PermuteSingleSrc, MVT::v16f16, 4}, // vextractf128 + 2*pshufb
// + vpor + vinsertf128
- {TTI::SK_PermuteSingleSrc, MVT::v32i8, 4}, // vextractf128 + 2*pshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 4}, // vextractf128 + 2*pshufb
// + vpor + vinsertf128
- {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
- {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
- {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpermilpd + vblendpd
- {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpermilps + vblendps
- {TTI::SK_PermuteTwoSrc, MVT::v16i16, 9}, // 2*vextractf128 + 4*pshufb
- // + 2*vpor + vinsertf128
- {TTI::SK_PermuteTwoSrc, MVT::v16f16, 9}, // 2*vextractf128 + 4*pshufb
- // + 2*vpor + vinsertf128
- {TTI::SK_PermuteTwoSrc, MVT::v32i8, 9}, // 2*vextractf128 + 4*pshufb
- // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpermilpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpermilps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
};
if (IsInLaneShuffle && ST->hasAVX())
|
Most of the x86 shuffle instructions operate within each 128-bit subvector lane, but our shuffle costs struggle to handle this and have to fallback to worst case shuffles that reference elements from any lane.
This patch detects shuffle masks that we know are "inlane" and enable us to assume a cheaper shuffle cost.