[llvm] [CostModel][X86] Update AVX1/AVX2 uitofp v2i64 -> v2f32 costs based off worst case llvm-mca numbers (PR #230098)
Tim Besard via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 8 05:50:08 PDT 2026
https://github.com/maleadt updated https://github.com/llvm/llvm-project/pull/230098
>From c2462a0fc8960c63983071adf9befc2849203316 Mon Sep 17 00:00:00 2001
From: Tim Besard <tim.besard at gmail.com>
Date: Thu, 8 Oct 2026 13:21:41 +0200
Subject: [PATCH 1/2] [SLP][X86] Add fdiv-seeded uitofp v2i64 -> v2f32 test
(NFC)
---
.../Transforms/SLPVectorizer/X86/uitofp.ll | 25 +++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll b/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll
index 9b4123c0218d8..ddfc0345007cc 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll
@@ -515,6 +515,31 @@ define void @uitofp_2i64_2f32() #0 {
ret void
}
+define [2 x float] @uitofp_2i64_2f32_fdiv(ptr %p, float %y) #0 {
+; CHECK-LABEL: @uitofp_2i64_2f32_fdiv(
+; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i64>, ptr [[P:%.*]], align 8
+; CHECK-NEXT: [[TMP2:%.*]] = uitofp <2 x i64> [[TMP1]] to <2 x float>
+; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[Y:%.*]], i64 0
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP2]], [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[TMP5]], i64 0
+; CHECK-NEXT: [[R0:%.*]] = insertvalue [2 x float] poison, float [[TMP6]], 0
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x float> [[TMP5]], i64 1
+; CHECK-NEXT: [[R1:%.*]] = insertvalue [2 x float] [[R0]], float [[TMP7]], 1
+; CHECK-NEXT: ret [2 x float] [[R1]]
+;
+ %ld0 = load i64, ptr %p, align 8
+ %p1 = getelementptr inbounds i8, ptr %p, i64 8
+ %ld1 = load i64, ptr %p1, align 8
+ %cvt0 = uitofp i64 %ld0 to float
+ %cvt1 = uitofp i64 %ld1 to float
+ %div0 = fdiv float %cvt0, %y
+ %div1 = fdiv float %cvt1, %y
+ %r0 = insertvalue [2 x float] poison, float %div0, 0
+ %r1 = insertvalue [2 x float] %r0, float %div1, 1
+ ret [2 x float] %r1
+}
+
define void @uitofp_4i64_4f32() #0 {
; CHECK-LABEL: @uitofp_4i64_4f32(
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i64>, ptr @src64, align 64
>From f682896d28555fd4bb060e5bf99b0ab9cc1a03bf Mon Sep 17 00:00:00 2001
From: Tim Besard <tim.besard at gmail.com>
Date: Thu, 8 Oct 2026 13:26:13 +0200
Subject: [PATCH 2/2] [CostModel][X86] Update AVX1/AVX2 uitofp v2i64 -> v2f32
costs based off worst case llvm-mca numbers
Since #206518, SLP uses fdiv as a vectorization seed. A pair of
uitofp i64 -> float feeding fdivs by a common divisor (e.g. a complex
number with unsigned 64-bit parts divided by a float, as in Julia's
`Complex{UInt64} / Float32`) is now fully vectorized on AVX1/AVX2
targets. Without AVX512DQ, uitofp v2i64 -> v2f32 has no native
instruction: it halves large elements, converts each lane through a GPR
with cvtsi2ss and fixes the result up with blends (14 instructions).
This made the code slower than before #206518.
SLP picked that sequence because the AVX table costs it at 10, below
what it measures. Use the worst case llvm-mca throughput from
check_cost_tables.py across btver2, sandybridge, haswell, broadwell,
skylake, alderlake and znver1-3, which is 11 (haswell/broadwell). With
that, SLP keeps the conversions scalar and only vectorizes the fdiv, as
it already does on SSE4.1 targets.
Assisted-by: Claude Code, Codex
---
.../lib/Target/X86/X86TargetTransformInfo.cpp | 2 +-
llvm/test/Analysis/CostModel/X86/uitofp.ll | 2 +-
.../Transforms/SLPVectorizer/X86/uitofp.ll | 63 +++++++++++++++----
3 files changed, 54 insertions(+), 13 deletions(-)
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 0001c93fb42b6..b1bac7fe4b25a 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -3416,7 +3416,7 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
{ ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i32, { 6, 1, 1, 1 } },
{ ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i32, { 8, 1, 1, 1 } },
{ ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i32, {10, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v2f32, MVT::v2i64, {10, 1, 1, 1 } },
+ { ISD::UINT_TO_FP, MVT::v2f32, MVT::v2i64, {11, 1, 1, 1 } },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v4i64, {18, 1, 1, 1 } },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, { 5, 1, 1, 1 } },
{ ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i64, {10, 1, 1, 1 } },
diff --git a/llvm/test/Analysis/CostModel/X86/uitofp.ll b/llvm/test/Analysis/CostModel/X86/uitofp.ll
index 1b2a1a46fb299..28478e7fee3ce 100644
--- a/llvm/test/Analysis/CostModel/X86/uitofp.ll
+++ b/llvm/test/Analysis/CostModel/X86/uitofp.ll
@@ -348,7 +348,7 @@ define i32 @uitofp_i64_float() {
;
; AVX-LABEL: 'uitofp_i64_float'
; AVX-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cvt_i64_f32 = uitofp i64 undef to float
-; AVX-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:1 SizeLat:1 for: %cvt_v2i64_v2f32 = uitofp <2 x i64> undef to <2 x float>
+; AVX-NEXT: Cost Model: Found costs of RThru:11 CodeSize:1 Lat:1 SizeLat:1 for: %cvt_v2i64_v2f32 = uitofp <2 x i64> undef to <2 x float>
; AVX-NEXT: Cost Model: Found costs of RThru:18 CodeSize:1 Lat:1 SizeLat:1 for: %cvt_v4i64_v4f32 = uitofp <4 x i64> undef to <4 x float>
; AVX-NEXT: Cost Model: Found costs of RThru:37 CodeSize:1 Lat:1 SizeLat:1 for: %cvt_v8i64_v8f32 = uitofp <8 x i64> undef to <8 x float>
; AVX-NEXT: Cost Model: Found costs of RThru:74 CodeSize:1 Lat:1 SizeLat:1 for: %cvt_v16i64_v16f32 = uitofp <16 x i64> undef to <16 x float>
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll b/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll
index ddfc0345007cc..3cc9f6b08b20f 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll
@@ -516,17 +516,58 @@ define void @uitofp_2i64_2f32() #0 {
}
define [2 x float] @uitofp_2i64_2f32_fdiv(ptr %p, float %y) #0 {
-; CHECK-LABEL: @uitofp_2i64_2f32_fdiv(
-; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i64>, ptr [[P:%.*]], align 8
-; CHECK-NEXT: [[TMP2:%.*]] = uitofp <2 x i64> [[TMP1]] to <2 x float>
-; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[Y:%.*]], i64 0
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP2]], [[TMP4]]
-; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[TMP5]], i64 0
-; CHECK-NEXT: [[R0:%.*]] = insertvalue [2 x float] poison, float [[TMP6]], 0
-; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x float> [[TMP5]], i64 1
-; CHECK-NEXT: [[R1:%.*]] = insertvalue [2 x float] [[R0]], float [[TMP7]], 1
-; CHECK-NEXT: ret [2 x float] [[R1]]
+; SSE-LABEL: @uitofp_2i64_2f32_fdiv(
+; SSE-NEXT: [[TMP1:%.*]] = load <2 x i64>, ptr [[P:%.*]], align 8
+; SSE-NEXT: [[TMP2:%.*]] = uitofp <2 x i64> [[TMP1]] to <2 x float>
+; SSE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[Y:%.*]], i64 0
+; SSE-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <2 x i32> zeroinitializer
+; SSE-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP2]], [[TMP4]]
+; SSE-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[TMP5]], i64 0
+; SSE-NEXT: [[R0:%.*]] = insertvalue [2 x float] poison, float [[TMP6]], 0
+; SSE-NEXT: [[TMP7:%.*]] = extractelement <2 x float> [[TMP5]], i64 1
+; SSE-NEXT: [[R1:%.*]] = insertvalue [2 x float] [[R0]], float [[TMP7]], 1
+; SSE-NEXT: ret [2 x float] [[R1]]
+;
+; AVX256NODQ-LABEL: @uitofp_2i64_2f32_fdiv(
+; AVX256NODQ-NEXT: [[P1:%.*]] = getelementptr inbounds i8, ptr [[P:%.*]], i64 8
+; AVX256NODQ-NEXT: [[LD0:%.*]] = load i64, ptr [[P]], align 8
+; AVX256NODQ-NEXT: [[LD1:%.*]] = load i64, ptr [[P1]], align 8
+; AVX256NODQ-NEXT: [[CVT0:%.*]] = uitofp i64 [[LD0]] to float
+; AVX256NODQ-NEXT: [[CVT1:%.*]] = uitofp i64 [[LD1]] to float
+; AVX256NODQ-NEXT: [[TMP1:%.*]] = insertelement <2 x float> poison, float [[CVT0]], i64 0
+; AVX256NODQ-NEXT: [[TMP2:%.*]] = insertelement <2 x float> [[TMP1]], float [[CVT1]], i64 1
+; AVX256NODQ-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[Y:%.*]], i64 0
+; AVX256NODQ-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <2 x i32> zeroinitializer
+; AVX256NODQ-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP2]], [[TMP4]]
+; AVX256NODQ-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[TMP5]], i64 0
+; AVX256NODQ-NEXT: [[R0:%.*]] = insertvalue [2 x float] poison, float [[TMP6]], 0
+; AVX256NODQ-NEXT: [[TMP7:%.*]] = extractelement <2 x float> [[TMP5]], i64 1
+; AVX256NODQ-NEXT: [[R1:%.*]] = insertvalue [2 x float] [[R0]], float [[TMP7]], 1
+; AVX256NODQ-NEXT: ret [2 x float] [[R1]]
+;
+; AVX256DQ-LABEL: @uitofp_2i64_2f32_fdiv(
+; AVX256DQ-NEXT: [[TMP1:%.*]] = load <2 x i64>, ptr [[P:%.*]], align 8
+; AVX256DQ-NEXT: [[TMP2:%.*]] = uitofp <2 x i64> [[TMP1]] to <2 x float>
+; AVX256DQ-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[Y:%.*]], i64 0
+; AVX256DQ-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <2 x i32> zeroinitializer
+; AVX256DQ-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP2]], [[TMP4]]
+; AVX256DQ-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[TMP5]], i64 0
+; AVX256DQ-NEXT: [[R0:%.*]] = insertvalue [2 x float] poison, float [[TMP6]], 0
+; AVX256DQ-NEXT: [[TMP7:%.*]] = extractelement <2 x float> [[TMP5]], i64 1
+; AVX256DQ-NEXT: [[R1:%.*]] = insertvalue [2 x float] [[R0]], float [[TMP7]], 1
+; AVX256DQ-NEXT: ret [2 x float] [[R1]]
+;
+; AVX512-LABEL: @uitofp_2i64_2f32_fdiv(
+; AVX512-NEXT: [[TMP1:%.*]] = load <2 x i64>, ptr [[P:%.*]], align 8
+; AVX512-NEXT: [[TMP2:%.*]] = uitofp <2 x i64> [[TMP1]] to <2 x float>
+; AVX512-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[Y:%.*]], i64 0
+; AVX512-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <2 x i32> zeroinitializer
+; AVX512-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP2]], [[TMP4]]
+; AVX512-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[TMP5]], i64 0
+; AVX512-NEXT: [[R0:%.*]] = insertvalue [2 x float] poison, float [[TMP6]], 0
+; AVX512-NEXT: [[TMP7:%.*]] = extractelement <2 x float> [[TMP5]], i64 1
+; AVX512-NEXT: [[R1:%.*]] = insertvalue [2 x float] [[R0]], float [[TMP7]], 1
+; AVX512-NEXT: ret [2 x float] [[R1]]
;
%ld0 = load i64, ptr %p, align 8
%p1 = getelementptr inbounds i8, ptr %p, i64 8
More information about the llvm-commits
mailing list