[llvm] [AArch64] Add cost model for REV shuffles. (PR #128498)

[David Green via llvm-commits]

https://github.com/davemgreen created https://github.com/llvm/llvm-project/pull/128498

These patterns represent rev instructions, which reverse inside a portion of the full vector. See llvm/test/CodeGen/AArch64/arm64-rev.ll for codegen tests.

>From 541394d610cbc9fc06f608d0d318cf7bd006e690 Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Mon, 24 Feb 2025 11:05:10 +0000
Subject: [PATCH] [AArch64] Add cost model for REV shuffles.

These patterns represent rev instructions.
---
 .../AArch64/AArch64TargetTransformInfo.cpp    |  6 ++++
 .../CostModel/AArch64/shuffle-reverse.ll      | 36 +++++++++----------
 2 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index d45cd8ed64787..32edfad5a5d97 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -4956,6 +4956,12 @@ InstructionCost AArch64TTIImpl::getShuffleCost(
       (Kind == TTI::SK_PermuteTwoSrc || Kind == TTI::SK_PermuteSingleSrc) &&
       (isZIPMask(Mask, LT.second.getVectorNumElements(), Unused) ||
        isUZPMask(Mask, LT.second.getVectorNumElements(), Unused) ||
+       isREVMask(Mask, LT.second.getScalarSizeInBits(),
+                 LT.second.getVectorNumElements(), 16) ||
+       isREVMask(Mask, LT.second.getScalarSizeInBits(),
+                 LT.second.getVectorNumElements(), 32) ||
+       isREVMask(Mask, LT.second.getScalarSizeInBits(),
+                 LT.second.getVectorNumElements(), 64) ||
        // Check for non-zero lane splats
        all_of(drop_begin(Mask),
               [&Mask](int M) { return M < 0 || M == Mask[0]; })))
diff --git a/llvm/test/Analysis/CostModel/AArch64/shuffle-reverse.ll b/llvm/test/Analysis/CostModel/AArch64/shuffle-reverse.ll
index 807685ccba5f9..7a11d6ff0cffd 100644
--- a/llvm/test/Analysis/CostModel/AArch64/shuffle-reverse.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/shuffle-reverse.ll
@@ -77,11 +77,11 @@ define void @reverse() {
 
 define void @vrev64() {
 ; CHECK-LABEL: 'vrev64'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
@@ -90,10 +90,10 @@ define void @vrev64() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = shufflevector <4 x half> undef, <4 x half> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4bf16 = shufflevector <4 x bfloat> undef, <4 x bfloat> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = shufflevector <8 x bfloat> undef, <8 x bfloat> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8bf16 = shufflevector <8 x bfloat> undef, <8 x bfloat> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16bf16 = shufflevector <16 x bfloat> undef, <16 x bfloat> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
@@ -140,18 +140,18 @@ define void @vrev64() {
 
 define void @vrev32() {
 ; CHECK-LABEL: 'vrev32'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8bf16 = shufflevector <8 x bfloat> undef, <8 x bfloat> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = shufflevector <16 x bfloat> undef, <16 x bfloat> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = shufflevector <8 x half> undef, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8bf16 = shufflevector <8 x bfloat> undef, <8 x bfloat> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16bf16 = shufflevector <16 x bfloat> undef, <16 x bfloat> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = shufflevector <8 x float> undef, <8 x float> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16f32 = shufflevector <16 x float> undef, <16 x float> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = shufflevector <8 x double> undef, <8 x double> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
@@ -187,12 +187,12 @@ define void @vrev32() {
 
 define void @vrev16() {
 ; CHECK-LABEL: 'vrev16'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16bf16 = shufflevector <16 x bfloat> undef, <16 x bfloat> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = shufflevector <16 x half> undef, <16 x half> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16bf16 = shufflevector <16 x bfloat> undef, <16 x bfloat> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = shufflevector <16 x float> undef, <16 x float> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16f64 = shufflevector <16 x double> undef, <16 x double> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void