[llvm] [AArch64] Fix cost of vector shifts with non-uniform constant amounts (PR #214206)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Aug 5 05:07:07 PDT 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Hassnaa Hamdi (hassnaaHamdi)
<details>
<summary>Changes</summary>
Non-uniform constants use variable shifts and require materializing the
shift vector. Account for a shift and materialization per legalized
vector.
---
Patch is 59.75 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/214206.diff
8 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (+15-3)
- (modified) llvm/test/Analysis/CostModel/AArch64/arith.ll (+31)
- (modified) llvm/test/Analysis/CostModel/AArch64/div.ll (+54-54)
- (modified) llvm/test/Analysis/CostModel/AArch64/fshl.ll (+8-8)
- (modified) llvm/test/Analysis/CostModel/AArch64/fshr.ll (+8-8)
- (modified) llvm/test/Analysis/CostModel/AArch64/rem.ll (+36-36)
- (modified) llvm/test/Transforms/SLPVectorizer/AArch64/fma-reduce-regression.ll (+8-5)
- (modified) llvm/test/Transforms/SLPVectorizer/AArch64/unique_values.ll (+10-6)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 9e1a0960617a5..b8ffb9e51ce01 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -4869,12 +4869,24 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
case ISD::XOR:
case ISD::OR:
case ISD::AND:
+ // These nodes are marked as 'custom' for combining purposes only.
+ // We know that they are legal. See related functions in ISelLowering.
+ return LT.first;
case ISD::SRL:
case ISD::SRA:
- case ISD::SHL:
- // These nodes are marked as 'custom' for combining purposes only.
- // We know that they are legal. See LowerAdd in ISelLowering.
+ case ISD::SHL: {
+ // Immediate vector shifts require uniform shift amounts. Non-uniform
+ // constants therefore use variable shifts and require materializing the
+ // shift vector. Account for a shift and materialization per legalized
+ // vector, together with shared setup.
+ if (Op2Info.isConstant() && !Op2Info.isUniform() &&
+ LT.second.isFixedLengthVector())
+ return 2 * LT.first + 1;
+
+ // Marked 'custom' for combining purposes; a uniform shift amount still
+ // lowers to a single legal instruction.
return LT.first;
+ }
case ISD::FNEG:
// Scalar fmul(fneg) or fneg(fmul) can be converted to fnmul
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith.ll b/llvm/test/Analysis/CostModel/AArch64/arith.ll
index f390fa8c163b9..7a42c3f2af862 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith.ll
@@ -519,3 +519,34 @@ define void @vi128() {
%k2 = xor <2 x i128> undef, undef
ret void
}
+
+define void @nonuniform_constant_shift_costs(<2 x i64> %x, i64 %scalar,
+; CHECK-LABEL: 'nonuniform_constant_shift_costs'
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %insert = insertelement <2 x i64> poison, i64 %scalar, i64 0
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %splat = shufflevector <2 x i64> %insert, <2 x i64> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %ashr.arbitrary = ashr <2 x i64> %x, <i64 1, i64 2>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %lshr.arbitrary = lshr <2 x i64> %x, <i64 1, i64 2>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %shl.arbitrary = shl <2 x i64> %x, <i64 1, i64 2>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %ashr.splat = ashr <2 x i64> %splat, <i64 1, i64 2>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %lshr.splat = lshr <2 x i64> %splat, <i64 1, i64 2>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %shl.splat = shl <2 x i64> %splat, <i64 1, i64 2>
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %lshr.uniform = lshr <2 x i64> %x, splat (i64 1)
+; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:1 Lat:1 SizeLat:1 for: %lshr.wide = lshr <4 x i64> %wide, <i64 1, i64 2, i64 3, i64 4>
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ <4 x i64> %wide) {
+ %insert = insertelement <2 x i64> poison, i64 %scalar, i64 0
+ %splat = shufflevector <2 x i64> %insert, <2 x i64> poison, <2 x i32> zeroinitializer
+
+ %ashr.arbitrary = ashr <2 x i64> %x, <i64 1, i64 2>
+ %lshr.arbitrary = lshr <2 x i64> %x, <i64 1, i64 2>
+ %shl.arbitrary = shl <2 x i64> %x, <i64 1, i64 2>
+
+ %ashr.splat = ashr <2 x i64> %splat, <i64 1, i64 2>
+ %lshr.splat = lshr <2 x i64> %splat, <i64 1, i64 2>
+ %shl.splat = shl <2 x i64> %splat, <i64 1, i64 2>
+
+ %lshr.uniform = lshr <2 x i64> %x, splat (i64 1)
+ %lshr.wide = lshr <4 x i64> %wide, <i64 1, i64 2, i64 3, i64 4>
+ ret void
+}
diff --git a/llvm/test/Analysis/CostModel/AArch64/div.ll b/llvm/test/Analysis/CostModel/AArch64/div.ll
index 2c5be1acbbd7b..b595a3b1c63af 100644
--- a/llvm/test/Analysis/CostModel/AArch64/div.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div.ll
@@ -347,27 +347,27 @@ define void @udiv_const() {
; CHECK-LABEL: 'udiv_const'
; CHECK-NEXT: Cost Model: Found costs of RThru:12 CodeSize:4 Lat:4 SizeLat:4 for: %I128 = udiv i128 undef, 7
; CHECK-NEXT: Cost Model: Found costs of 4 for: %I64 = udiv i64 undef, 7
-; CHECK-NEXT: Cost Model: Found costs of RThru:32 CodeSize:4 Lat:4 SizeLat:4 for: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
-; CHECK-NEXT: Cost Model: Found costs of RThru:64 CodeSize:4 Lat:4 SizeLat:4 for: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT: Cost Model: Found costs of RThru:128 CodeSize:4 Lat:4 SizeLat:4 for: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; CHECK-NEXT: Cost Model: Found costs of RThru:36 CodeSize:4 Lat:4 SizeLat:4 for: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+; CHECK-NEXT: Cost Model: Found costs of RThru:70 CodeSize:4 Lat:4 SizeLat:4 for: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; CHECK-NEXT: Cost Model: Found costs of RThru:138 CodeSize:4 Lat:4 SizeLat:4 for: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %I32 = udiv i32 undef, 7
-; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V2i32 = udiv <2 x i32> undef, <i32 4, i32 5>
-; CHECK-NEXT: Cost Model: Found costs of RThru:6 CodeSize:4 Lat:4 SizeLat:4 for: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT: Cost Model: Found costs of RThru:12 CodeSize:4 Lat:4 SizeLat:4 for: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V2i32 = udiv <2 x i32> undef, <i32 4, i32 5>
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: Cost Model: Found costs of RThru:18 CodeSize:4 Lat:4 SizeLat:4 for: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT: Cost Model: Found costs of RThru:34 CodeSize:4 Lat:4 SizeLat:4 for: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %I16 = udiv i16 undef, 7
-; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V2i16 = udiv <2 x i16> undef, <i16 4, i16 5>
-; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V4i16 = udiv <4 x i16> undef, <i16 4, i16 5, i16 6, i16 7>
-; CHECK-NEXT: Cost Model: Found costs of RThru:6 CodeSize:4 Lat:4 SizeLat:4 for: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
-; CHECK-NEXT: Cost Model: Found costs of RThru:12 CodeSize:4 Lat:4 SizeLat:4 for: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V2i16 = udiv <2 x i16> undef, <i16 4, i16 5>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V4i16 = udiv <4 x i16> undef, <i16 4, i16 5, i16 6, i16 7>
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; CHECK-NEXT: Cost Model: Found costs of RThru:18 CodeSize:4 Lat:4 SizeLat:4 for: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT: Cost Model: Found costs of RThru:34 CodeSize:4 Lat:4 SizeLat:4 for: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %I8 = udiv i8 undef, 7
-; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V2i8 = udiv <2 x i8> undef, <i8 4, i8 5>
-; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V4i8 = udiv <4 x i8> undef, <i8 4, i8 5, i8 6, i8 7>
-; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V8i8 = udiv <8 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11>
-; CHECK-NEXT: Cost Model: Found costs of RThru:6 CodeSize:4 Lat:4 SizeLat:4 for: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT: Cost Model: Found costs of RThru:12 CodeSize:4 Lat:4 SizeLat:4 for: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V2i8 = udiv <2 x i8> undef, <i8 4, i8 5>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V4i8 = udiv <4 x i8> undef, <i8 4, i8 5, i8 6, i8 7>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V8i8 = udiv <8 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11>
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found costs of RThru:18 CodeSize:4 Lat:4 SizeLat:4 for: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found costs of RThru:34 CodeSize:4 Lat:4 SizeLat:4 for: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
@@ -580,27 +580,27 @@ define void @udiv_constpow2() {
; CHECK-LABEL: 'udiv_constpow2'
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %I128 = udiv i128 undef, 16
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %I64 = udiv i64 undef, 16
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %I32 = udiv i32 undef, 16
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V2i32 = udiv <2 x i32> undef, <i32 2, i32 4>
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V2i32 = udiv <2 x i32> undef, <i32 2, i32 4>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %I16 = udiv i16 undef, 16
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V2i16 = udiv <2 x i16> undef, <i16 2, i16 4>
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V4i16 = udiv <4 x i16> undef, <i16 2, i16 4, i16 8, i16 16>
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V2i16 = udiv <2 x i16> undef, <i16 2, i16 4>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V4i16 = udiv <4 x i16> undef, <i16 2, i16 4, i16 8, i16 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %I8 = udiv i8 undef, 16
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V2i8 = udiv <2 x i8> undef, <i8 2, i8 4>
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V4i8 = udiv <4 x i8> undef, <i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V8i8 = udiv <8 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:4 Lat:4 SizeLat:4 for: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V2i8 = udiv <2 x i8> undef, <i8 2, i8 4>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V4i8 = udiv <4 x i8> undef, <i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V8i8 = udiv <8 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:3 CodeSize:4 Lat:4 SizeLat:4 for: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:5 CodeSize:4 Lat:4 SizeLat:4 for: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found costs of RThru:9 CodeSize:4 Lat:4 SizeLat:4 for: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%I128 = udiv i128 undef, 16
@@ -812,27 +812,27 @@ define void @udiv_constnegpow2() {
; CHECK-LABEL: 'udiv_constnegpow2'
; CHECK-NEXT: Cost Model: Found costs of R...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/214206
More information about the llvm-commits
mailing list