From 24e42f7d28e98152484cf9bbf8ee4080f5082da0 Mon Sep 17 00:00:00 2001 From: Roman Lebedev Date: Tue, 28 Sep 2021 19:15:07 +0300 Subject: [PATCH] [X86][Costmodel] Load/store i16 Stride=6 VF=8 interleaving costs 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/3Tc5s897j - for intels `Block RThroughput: =39.0`; for ryzens, `Block RThroughput: <=13.5` So pick cost of `39`. For store we have: https://godbolt.org/z/fo1h9E67e - for intels `Block RThroughput: =21.0`; for ryzens, `Block RThroughput: <=12.0` So pick cost of `21`. 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/D110592 --- llvm/lib/Target/X86/X86TargetTransformInfo.cpp | 2 ++ llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll | 2 +- llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp index 7a133a8..dc8cc21 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -5093,6 +5093,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2( {6, MVT::v2i16, 13}, // (load 12i16 and) deinterleave into 6 x 2i16 {6, MVT::v4i16, 9}, // (load 24i16 and) deinterleave into 6 x 4i16 + {6, MVT::v8i16, 39}, // (load 48i16 and) deinterleave into 6 x 8i16 {8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32 }; @@ -5126,6 +5127,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2( {6, MVT::v2i16, 10}, // interleave 6 x 2i16 into 12i16 (and store) {6, MVT::v4i16, 15}, // interleave 6 x 4i16 into 24i16 (and store) + {6, MVT::v8i16, 21}, // interleave 6 x 8i16 into 48i16 (and store) }; if (Opcode == Instruction::Load) { diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll index eef8a13..2d13e26 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll @@ -11,7 +11,7 @@ target triple = "x86_64-unknown-linux-gnu" ; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK: LV: Found an estimated cost of 16 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2 -; CHECK: LV: Found an estimated cost of 123 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2 +; CHECK: LV: Found an estimated cost of 42 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK: LV: Found an estimated cost of 342 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll index aff7d13..78d4f4d 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll @@ -11,7 +11,7 @@ target triple = "x86_64-unknown-linux-gnu" ; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v5, i16* %out5, align 2 ; CHECK: LV: Found an estimated cost of 13 for VF 2 For instruction: store i16 %v5, i16* %out5, align 2 ; CHECK: LV: Found an estimated cost of 17 for VF 4 For instruction: store i16 %v5, i16* %out5, align 2 -; CHECK: LV: Found an estimated cost of 147 for VF 8 For instruction: store i16 %v5, i16* %out5, align 2 +; CHECK: LV: Found an estimated cost of 24 for VF 8 For instruction: store i16 %v5, i16* %out5, align 2 ; CHECK: LV: Found an estimated cost of 342 for VF 16 For instruction: store i16 %v5, i16* %out5, align 2 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i16 %v5, i16* %out5, align 2 -- 2.7.4