diff options
author | Roman Lebedev <lebedev.ri@gmail.com> | 2021-10-17 17:27:40 +0300 |
---|---|---|
committer | Roman Lebedev <lebedev.ri@gmail.com> | 2021-10-17 17:28:10 +0300 |
commit | 3274ce3a287dcd4d02b4d2c7a2bf60e942836e06 (patch) | |
tree | 9006f310c8169ede165e414f0ee1d9098232a72b | |
parent | 3a6a9f74d3a59beb359a9968ac27dcf97d072b3a (diff) | |
download | llvm-3274ce3a287dcd4d02b4d2c7a2bf60e942836e06.tar.gz |
[X86][Costmodel] Load/store i64 Stride=2 VF=32 interleaving costs
A few more tuples are being queried after D111546. Might be good to model them,
They all require a lot of manual assembly surgery.
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/MTaKboejM - for intels `Block RThroughput: =32.0`; for ryzens, `Block RThroughput: <=16.0`
So could pick cost of `32`
For store we have:
https://godbolt.org/z/v7xPj3Wd4 - for intels `Block RThroughput: =32.0`; for ryzens, `Block RThroughput: <=32.0`
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/D111944
5 files changed, 6 insertions, 4 deletions
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp index 7c1a8b522a3a..0f2d3b26c21f 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -5231,6 +5231,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost( {2, MVT::v4i64, 4}, // (load 8i64 and) deinterleave into 2 x 4i64 {2, MVT::v8i64, 8}, // (load 16i64 and) deinterleave into 2 x 8i64 {2, MVT::v16i64, 16}, // (load 32i64 and) deinterleave into 2 x 16i64 + {2, MVT::v32i64, 32}, // (load 64i64 and) deinterleave into 2 x 32i64 {3, MVT::v2i8, 3}, // (load 6i8 and) deinterleave into 3 x 2i8 {3, MVT::v4i8, 3}, // (load 12i8 and) deinterleave into 3 x 4i8 @@ -5338,6 +5339,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost( {2, MVT::v4i64, 4}, // interleave 2 x 4i64 into 8i64 (and store) {2, MVT::v8i64, 8}, // interleave 2 x 8i64 into 16i64 (and store) {2, MVT::v16i64, 16}, // interleave 2 x 16i64 into 32i64 (and store) + {2, MVT::v32i64, 32}, // interleave 2 x 32i64 into 64i64 (and store) {3, MVT::v2i8, 4}, // interleave 3 x 2i8 into 6i8 (and store) {3, MVT::v4i8, 4}, // interleave 3 x 4i8 into 12i8 (and store) diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll index 67629c58d42c..160ada094daa 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll @@ -30,7 +30,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load double, double* %in0, align 8 ; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load double, double* %in0, align 8 ; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: %v0 = load double, double* %in0, align 8 -; AVX2: LV: Found an estimated cost of 128 for VF 32 For instruction: %v0 = load double, double* %in0, align 8 +; AVX2: LV: Found an estimated cost of 48 for VF 32 For instruction: %v0 = load double, double* %in0, align 8 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8 ; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load double, double* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll index 84e208971455..6d24cd248677 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll @@ -30,7 +30,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i64, i64* %in0, align 8 ; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load i64, i64* %in0, align 8 ; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: %v0 = load i64, i64* %in0, align 8 -; AVX2: LV: Found an estimated cost of 208 for VF 32 For instruction: %v0 = load i64, i64* %in0, align 8 +; AVX2: LV: Found an estimated cost of 48 for VF 32 For instruction: %v0 = load i64, i64* %in0, align 8 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8 ; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll index 186cd4a5186e..de6bfc43c3d7 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll @@ -30,7 +30,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: store double %v1, double* %out1, align 8 ; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: store double %v1, double* %out1, align 8 ; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: store double %v1, double* %out1, align 8 -; AVX2: LV: Found an estimated cost of 128 for VF 32 For instruction: store double %v1, double* %out1, align 8 +; AVX2: LV: Found an estimated cost of 48 for VF 32 For instruction: store double %v1, double* %out1, align 8 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, double* %out1, align 8 ; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: store double %v1, double* %out1, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll index 06d1c6e0c862..0f58fe6c9692 100644 --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll @@ -30,7 +30,7 @@ target triple = "x86_64-unknown-linux-gnu" ; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: store i64 %v1, i64* %out1, align 8 ; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: store i64 %v1, i64* %out1, align 8 ; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: store i64 %v1, i64* %out1, align 8 -; AVX2: LV: Found an estimated cost of 208 for VF 32 For instruction: store i64 %v1, i64* %out1, align 8 +; AVX2: LV: Found an estimated cost of 48 for VF 32 For instruction: store i64 %v1, i64* %out1, align 8 ; ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, i64* %out1, align 8 ; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %v1, i64* %out1, align 8 |