From 7d91037fd2f71f1253bd8751a887eb4b6ed7d2ec Mon Sep 17 00:00:00 2001 From: Roman Lebedev Date: Mon, 4 Oct 2021 19:30:14 +0300 Subject: [PATCH] [X86][Costmodel] Load/store i32/f32 Stride=4 VF=16 interleaving costs This one required quite a bit of assembly surgery, but the trend continues, so i think this is right. The only sched models that for cpu's that support avx2 but not avx512 are: haswell, broadwell, skylake, zen1-3 For load we have: https://godbolt.org/z/EKWdj8cKT - for intels `Block RThroughput: <=32.0`; for ryzens, `Block RThroughput: <=24.0` So could pick cost of `32`. For store we have: https://godbolt.org/z/zj4bb9P75 - for intels `Block RThroughput: =32.0`; for ryzens, `Block RThroughput: <=16.0` So we could pick cost of `32`. I'm directly using the shuffling asm the llc produced, without any manual fixups that may be needed to ensure sequential execution. Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D111064 --- llvm/lib/Target/X86/X86TargetTransformInfo.cpp | 2 ++ llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll | 2 +- llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll | 2 +- llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll | 2 +- llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll | 2 +- 5 files changed, 6 insertions(+), 4 deletions(-) diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp index 7819b8c..563b468 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -5131,6 +5131,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2( {4, MVT::v2i32, 4}, // (load 8i32 and) deinterleave into 4 x 2i32 {4, MVT::v4i32, 8}, // (load 16i32 and) deinterleave into 4 x 4i32 {4, MVT::v8i32, 16}, // (load 32i32 and) deinterleave into 4 x 8i32 + {4, MVT::v16i32, 32}, // (load 64i32 and) deinterleave into 4 x 16i32 {6, MVT::v2i8, 6}, // (load 12i8 and) deinterleave into 6 x 2i8 {6, MVT::v4i8, 14}, // (load 24i8 and) deinterleave into 6 x 4i8 @@ -5207,6 +5208,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2( {4, MVT::v2i32, 5}, // interleave 4 x 2i32 into 8i32 (and store) {4, MVT::v4i32, 6}, // interleave 4 x 4i32 into 16i32 (and store) {4, MVT::v8i32, 16}, // interleave 4 x 8i32 into 32i32 (and store) + {4, MVT::v16i32, 32}, // interleave 4 x 16i32 into 64i32 (and store) {6, MVT::v2i8, 7}, // interleave 6 x 2i8 into 12i8 (and store) {6, MVT::v4i8, 9}, // interleave 6 x 4i8 into 24i8 (and store) diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll index 3e56c52..850d5cb 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll @@ -27,7 +27,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load float, float* %in0, align 4 ; AVX2: LV: Found an estimated cost of 10 for VF 4 For instruction: %v0 = load float, float* %in0, align 4 ; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load float, float* %in0, align 4 -; AVX2: LV: Found an estimated cost of 152 for VF 16 For instruction: %v0 = load float, float* %in0, align 4 +; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load float, float* %in0, align 4 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4 ; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load float, float* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll index 854384a..c9abb10 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll @@ -27,7 +27,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 ; AVX2: LV: Found an estimated cost of 10 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4 ; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4 -; AVX2: LV: Found an estimated cost of 184 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4 +; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll index dffa5ed..6b52019 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll @@ -27,7 +27,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store float %v3, float* %out3, align 4 ; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: store float %v3, float* %out3, align 4 ; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: store float %v3, float* %out3, align 4 -; AVX2: LV: Found an estimated cost of 152 for VF 16 For instruction: store float %v3, float* %out3, align 4 +; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: store float %v3, float* %out3, align 4 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v3, float* %out3, align 4 ; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store float %v3, float* %out3, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll index daf22a7..c9ad8a1 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll @@ -27,7 +27,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %v3, i32* %out3, align 4 ; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %v3, i32* %out3, align 4 ; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: store i32 %v3, i32* %out3, align 4 -; AVX2: LV: Found an estimated cost of 184 for VF 16 For instruction: store i32 %v3, i32* %out3, align 4 +; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: store i32 %v3, i32* %out3, align 4 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v3, i32* %out3, align 4 ; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i32 %v3, i32* %out3, align 4 -- 2.7.4