[llvm] 764fd5f - [X86][Costmodel] Load/store i32/f32 Stride=6 VF=2 interleaving costs

Roman Lebedev via llvm-commits llvm-commits at lists.llvm.org
Tue Oct 5 07:00:02 PDT 2021


Author: Roman Lebedev
Date: 2021-10-05T16:58:57+03:00
New Revision: 764fd5f463e4a2d13e77751e0da1c623d2781d4b

URL: https://github.com/llvm/llvm-project/commit/764fd5f463e4a2d13e77751e0da1c623d2781d4b
DIFF: https://github.com/llvm/llvm-project/commit/764fd5f463e4a2d13e77751e0da1c623d2781d4b.diff

LOG: [X86][Costmodel] Load/store i32/f32 Stride=6 VF=2 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/aec96Thee - for intels `Block RThroughput: =6.0`; for ryzens, `Block RThroughput: <=3.3`
So could pick cost of `6`.

For store we have:
https://godbolt.org/z/aec96Thee - for intels `Block RThroughput: =9.0`; for ryzens, `Block RThroughput: <=3.0`
So we could pick cost of `9`.

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/D111083

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll
    llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll
    llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll
    llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 0dc8c27caaaf..6692ab1cb6b1 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -5148,6 +5148,8 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2(
       {6, MVT::v8i16, 39}, // (load 48i16 and) deinterleave into 6 x 8i16
       {6, MVT::v16i16, 106}, // (load 96i16 and) deinterleave into 6 x 16i16
 
+      {6, MVT::v2i32, 6}, // (load 12i32 and) deinterleave into 6 x 2i32
+
       {8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32
   };
 
@@ -5228,6 +5230,8 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2(
       {6, MVT::v4i16, 15},  // interleave 6 x 4i16 into 24i16 (and store)
       {6, MVT::v8i16, 21},  // interleave 6 x 8i16 into 48i16 (and store)
       {6, MVT::v16i16, 58},  // interleave 6 x 16i16 into 96i16 (and store)
+
+      {6, MVT::v2i32, 9},  // interleave 6 x 2i32 into 12i32 (and store)
   };
 
   if (Opcode == Instruction::Load) {

diff  --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll
index a596a40a12a2..964a48aa7045 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll
@@ -24,7 +24,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; AVX1: LV: Found an estimated cost of 228 for VF 16 For instruction:   %v0 = load float, float* %in0, align 4
 ;
 ; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load float, float* %in0, align 4
-; AVX2: LV: Found an estimated cost of 21 for VF 2 For instruction:   %v0 = load float, float* %in0, align 4
+; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction:   %v0 = load float, float* %in0, align 4
 ; AVX2: LV: Found an estimated cost of 51 for VF 4 For instruction:   %v0 = load float, float* %in0, align 4
 ; AVX2: LV: Found an estimated cost of 114 for VF 8 For instruction:   %v0 = load float, float* %in0, align 4
 ; AVX2: LV: Found an estimated cost of 228 for VF 16 For instruction:   %v0 = load float, float* %in0, align 4

diff  --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll
index bcc5a2da2b52..ad3eade1111d 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll
@@ -24,7 +24,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; AVX1: LV: Found an estimated cost of 276 for VF 16 For instruction:   %v0 = load i32, i32* %in0, align 4
 ;
 ; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 30 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX2: LV: Found an estimated cost of 63 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX2: LV: Found an estimated cost of 138 for VF 8 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX2: LV: Found an estimated cost of 276 for VF 16 For instruction:   %v0 = load i32, i32* %in0, align 4

diff  --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll
index 0dc6f301ea1e..89c7b4dd84ca 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll
@@ -24,7 +24,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; AVX1: LV: Found an estimated cost of 228 for VF 16 For instruction:   store float %v5, float* %out5, align 4
 ;
 ; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction:   store float %v5, float* %out5, align 4
-; AVX2: LV: Found an estimated cost of 20 for VF 2 For instruction:   store float %v5, float* %out5, align 4
+; AVX2: LV: Found an estimated cost of 11 for VF 2 For instruction:   store float %v5, float* %out5, align 4
 ; AVX2: LV: Found an estimated cost of 45 for VF 4 For instruction:   store float %v5, float* %out5, align 4
 ; AVX2: LV: Found an estimated cost of 114 for VF 8 For instruction:   store float %v5, float* %out5, align 4
 ; AVX2: LV: Found an estimated cost of 228 for VF 16 For instruction:   store float %v5, float* %out5, align 4

diff  --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll
index 81753a47ad34..a2d7fedfd3da 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll
@@ -24,7 +24,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; AVX1: LV: Found an estimated cost of 276 for VF 16 For instruction:   store i32 %v5, i32* %out5, align 4
 ;
 ; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i32 %v5, i32* %out5, align 4
-; AVX2: LV: Found an estimated cost of 29 for VF 2 For instruction:   store i32 %v5, i32* %out5, align 4
+; AVX2: LV: Found an estimated cost of 11 for VF 2 For instruction:   store i32 %v5, i32* %out5, align 4
 ; AVX2: LV: Found an estimated cost of 57 for VF 4 For instruction:   store i32 %v5, i32* %out5, align 4
 ; AVX2: LV: Found an estimated cost of 138 for VF 8 For instruction:   store i32 %v5, i32* %out5, align 4
 ; AVX2: LV: Found an estimated cost of 276 for VF 16 For instruction:   store i32 %v5, i32* %out5, align 4


        


More information about the llvm-commits mailing list