From 2a7a768dad3a77571fae8506d84078fe4ce3d105 Mon Sep 17 00:00:00 2001
From: Roman Lebedev <lebedev.ri@gmail.com>
Date: Mon, 27 Sep 2021 22:18:41 +0300
Subject: [PATCH] [X86][Costmodel] Load/store i16 Stride=4 VF=32 interleaving
 costs

The only sched models that for cpu's that support avx2
but not avx512 are: haswell, broadwell, skylake, zen1-3

For this tuple, measuring becomes problematic since there's a lot of spilling going on,
but apparently all these memory ops do not affect worst-case estimate at all here.

For load we have:
https://godbolt.org/z/zP4hd8MT6 - for intels `Block RThroughput: =150.0`; for ryzens, `Block RThroughput: <=59`
So pick cost of `150`.

For store we have:
https://godbolt.org/z/vKb8zTK8E - for intels `Block RThroughput: =32.0`; for ryzens, `Block RThroughput: <=24.0`
So pick cost of `64`.

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/D110548
---
 llvm/lib/Target/X86/X86TargetTransformInfo.cpp                  | 2 ++
 .../Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll     | 2 +-
 .../Analysis/CostModel/X86/interleaved-store-i16-stride-4.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 fa8e979a1ac4..fa4c648e94c3 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -5089,6 +5089,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2(
       {4, MVT::v4i16, 17}, // (load 16i16 and) deinterleave into 4 x 4i16
       {4, MVT::v8i16, 33}, // (load 32i16 and) deinterleave into 4 x 8i16
       {4, MVT::v16i16, 75}, // (load 64i16 and) deinterleave into 4 x 16i16
+      {4, MVT::v32i16, 150}, // (load 128i16 and) deinterleave into 4 x 32i16
 
       {8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32
   };
@@ -5118,6 +5119,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2(
       {4, MVT::v4i16, 6},  // interleave 4 x 4i16 into 16i16 (and store)
       {4, MVT::v8i16, 10},  // interleave 4 x 8i16 into 32i16 (and store)
       {4, MVT::v16i16, 32},  // interleave 4 x 16i16 into 64i16 (and store)
+      {4, MVT::v32i16, 64},  // interleave 4 x 32i16 into 128i16 (and store)
   };
 
   if (Opcode == Instruction::Load) {
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll
index d2870ce92214..8998a3c1d134 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll
@@ -13,7 +13,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; CHECK: LV: Found an estimated cost of 18 for VF 4 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; CHECK: LV: Found an estimated cost of 35 for VF 8 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; CHECK: LV: Found an estimated cost of 79 for VF 16 For instruction:   %v0 = load i16, i16* %in0, align 2
-; CHECK: LV: Found an estimated cost of 456 for VF 32 For instruction:   %v0 = load i16, i16* %in0, align 2
+; CHECK: LV: Found an estimated cost of 158 for VF 32 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
 
 define void @test() {
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll
index c614be256d06..7d9c1f1a0f4d 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll
@@ -13,7 +13,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; CHECK: LV: Found an estimated cost of 7 for VF 4 For instruction:   store i16 %v3, i16* %out3, align 2
 ; CHECK: LV: Found an estimated cost of 12 for VF 8 For instruction:   store i16 %v3, i16* %out3, align 2
 ; CHECK: LV: Found an estimated cost of 36 for VF 16 For instruction:   store i16 %v3, i16* %out3, align 2
-; CHECK: LV: Found an estimated cost of 456 for VF 32 For instruction:   store i16 %v3, i16* %out3, align 2
+; CHECK: LV: Found an estimated cost of 72 for VF 32 For instruction:   store i16 %v3, i16* %out3, align 2
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   store i16 %v3, i16* %out3, align 2
 
 define void @test() {