[llvm] [InstCombine] Remove the canonicalization of `trunc` to `i1` (PR #84628)
via llvm-commits
llvm-commits at lists.llvm.org
Sat Mar 9 05:40:20 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Monad (YanWQ-monad)
<details>
<summary>Changes</summary>
Remove the canonicalization of `trunc` to `i1` according to the suggestion of https://github.com/llvm/llvm-project/pull/83829#issuecomment-1986801166
https://github.com/llvm/llvm-project/blob/a84e66a92d7b97f68aa3ae7d2c5839f3fb0d291d/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp#L737-L745
---
Patch is 66.44 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/84628.diff
16 Files Affected:
- (modified) llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp (-9)
- (modified) llvm/test/Transforms/InstCombine/X86/x86-avx512-inseltpoison.ll (+56-84)
- (modified) llvm/test/Transforms/InstCombine/X86/x86-avx512.ll (+56-84)
- (modified) llvm/test/Transforms/InstCombine/apint-shl-trunc.ll (+4-6)
- (modified) llvm/test/Transforms/InstCombine/cast.ll (+2-4)
- (modified) llvm/test/Transforms/InstCombine/catchswitch-phi.ll (+9-10)
- (modified) llvm/test/Transforms/InstCombine/icmp-mul-and.ll (+2-2)
- (modified) llvm/test/Transforms/InstCombine/icmp-mul-zext.ll (+3-3)
- (modified) llvm/test/Transforms/InstCombine/mul-masked-bits.ll (+4-6)
- (modified) llvm/test/Transforms/InstCombine/mul.ll (+2-3)
- (modified) llvm/test/Transforms/InstCombine/phi.ll (+4-5)
- (modified) llvm/test/Transforms/InstCombine/ptr-int-cast.ll (+1-2)
- (modified) llvm/test/Transforms/InstCombine/reduction-add-sext-zext-i1.ll (+1-2)
- (modified) llvm/test/Transforms/InstCombine/reduction-xor-sext-zext-i1.ll (+7-11)
- (modified) llvm/test/Transforms/InstCombine/select-ctlz-to-cttz.ll (+12-6)
- (modified) llvm/test/Transforms/PhaseOrdering/X86/merge-functions.ll (+1-2)
``````````diff
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
index 45afa6363ae01f..2f34d825ceed58 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -734,15 +734,6 @@ Instruction *InstCombinerImpl::visitTrunc(TruncInst &Trunc) {
if (DestWidth == 1) {
Value *Zero = Constant::getNullValue(SrcTy);
- if (DestTy->isIntegerTy()) {
- // Canonicalize trunc x to i1 -> icmp ne (and x, 1), 0 (scalar only).
- // TODO: We canonicalize to more instructions here because we are probably
- // lacking equivalent analysis for trunc relative to icmp. There may also
- // be codegen concerns. If those trunc limitations were removed, we could
- // remove this transform.
- Value *And = Builder.CreateAnd(Src, ConstantInt::get(SrcTy, 1));
- return new ICmpInst(ICmpInst::ICMP_NE, And, Zero);
- }
// For vectors, we do not canonicalize all truncs to icmp, so optimize
// patterns that would be covered within visitICmpInst.
diff --git a/llvm/test/Transforms/InstCombine/X86/x86-avx512-inseltpoison.ll b/llvm/test/Transforms/InstCombine/X86/x86-avx512-inseltpoison.ll
index 9b990480709c97..80d8e1b16ed28b 100644
--- a/llvm/test/Transforms/InstCombine/X86/x86-avx512-inseltpoison.ll
+++ b/llvm/test/Transforms/InstCombine/X86/x86-avx512-inseltpoison.ll
@@ -39,10 +39,9 @@ define <4 x float> @test_add_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fadd float [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP5]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], float [[TMP3]], float [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[A]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -117,10 +116,9 @@ define <2 x double> @test_add_sd_mask(<2 x double> %a, <2 x double> %b, <2 x dou
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fadd double [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP5]], double [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], double [[TMP3]], double [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[A]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -191,10 +189,9 @@ define <4 x float> @test_sub_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fsub float [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP5]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], float [[TMP3]], float [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[A]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -269,10 +266,9 @@ define <2 x double> @test_sub_sd_mask(<2 x double> %a, <2 x double> %b, <2 x dou
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fsub double [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP5]], double [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], double [[TMP3]], double [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[A]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -343,10 +339,9 @@ define <4 x float> @test_mul_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fmul float [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP5]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], float [[TMP3]], float [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[A]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -421,10 +416,9 @@ define <2 x double> @test_mul_sd_mask(<2 x double> %a, <2 x double> %b, <2 x dou
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fmul double [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP5]], double [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], double [[TMP3]], double [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[A]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -495,10 +489,9 @@ define <4 x float> @test_div_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fdiv float [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP5]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], float [[TMP3]], float [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[A]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -573,10 +566,9 @@ define <2 x double> @test_div_sd_mask(<2 x double> %a, <2 x double> %b, <2 x dou
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = fdiv double [[TMP1]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP4]], 0
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[MASK:%.*]] to i1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP5]], double [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP4]], double [[TMP3]], double [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[A]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -981,9 +973,8 @@ define <4 x float> @test_mask_vfmadd_ss(<4 x float> %a, <4 x float> %b, <4 x flo
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP1]], float [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float [[TMP1]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[A]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -1011,9 +1002,8 @@ define float @test_mask_vfmadd_ss_0(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP1]], float [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float [[TMP1]]
; CHECK-NEXT: ret float [[TMP6]]
;
%1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
@@ -1060,9 +1050,8 @@ define <2 x double> @test_mask_vfmadd_sd(<2 x double> %a, <2 x double> %b, <2 x
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP1]], double [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], double [[TMP4]], double [[TMP1]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[A]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -1086,9 +1075,8 @@ define double @test_mask_vfmadd_sd_0(<2 x double> %a, <2 x double> %b, <2 x doub
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP1]], double [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], double [[TMP4]], double [[TMP1]]
; CHECK-NEXT: ret double [[TMP6]]
;
%1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
@@ -1129,9 +1117,8 @@ define <4 x float> @test_maskz_vfmadd_ss(<4 x float> %a, <4 x float> %b, <4 x fl
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float 0.000000e+00, float [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float 0.000000e+00
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[A]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -1159,9 +1146,8 @@ define float @test_maskz_vfmadd_ss_0(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float 0.000000e+00, float [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float 0.000000e+00
; CHECK-NEXT: ret float [[TMP6]]
;
%1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
@@ -1206,9 +1192,8 @@ define <2 x double> @test_maskz_vfmadd_sd(<2 x double> %a, <2 x double> %b, <2 x
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double 0.000000e+00, double [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], double [[TMP4]], double 0.000000e+00
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[A]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -1232,9 +1217,8 @@ define double @test_maskz_vfmadd_sd_0(<2 x double> %a, <2 x double> %b, <2 x dou
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double 0.000000e+00, double [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], double [[TMP4]], double 0.000000e+00
; CHECK-NEXT: ret double [[TMP6]]
;
%1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
@@ -1275,9 +1259,8 @@ define <4 x float> @test_mask3_vfmadd_ss(<4 x float> %a, <4 x float> %b, <4 x fl
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP3]], float [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float [[TMP3]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[C]], float [[TMP6]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP7]]
;
@@ -1305,9 +1288,8 @@ define float @test_mask3_vfmadd_ss_0(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], float [[TMP3]], float [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float [[TMP3]]
; CHECK-NEXT: ret float [[TMP6]]
;
%1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
@@ -1352,9 +1334,8 @@ define <2 x double> @test_mask3_vfmadd_sd(<2 x double> %a, <2 x double> %b, <2 x
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP3]], double [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], double [[TMP4]], double [[TMP3]]
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[C]], double [[TMP6]], i64 0
; CHECK-NEXT: ret <2 x double> [[TMP7]]
;
@@ -1378,9 +1359,8 @@ define double @test_mask3_vfmadd_sd_0(<2 x double> %a, <2 x double> %b, <2 x dou
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
-; CHECK-NEXT: [[TMP5:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP5]], 0
-; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[DOTNOT]], double [[TMP3]], double [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], double [[TMP4]], double [[TMP3]]
; CHECK-NEXT: ret double [[TMP6]]
;
%1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
@@ -1423,9 +1403,8 @@ define <4 x float> @test_mask3_vfmsub_ss(<4 x float> %a, <4 x float> %b, <4 x fl
; CHECK-NEXT: [[TMP4:%.*]] = fneg float [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[C]], i64 0
-; CHECK-NEXT: [[TMP7:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP7]], 0
-; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[DOTNOT]], float [[TMP6]], float [[TMP5]]
+; CHECK-NEXT: [[TMP7:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x float> [[C]], float [[TMP8]], i64 0
; CHECK-NEXT: ret <4 x float> [[TMP9]]
;
@@ -1457,9 +1436,8 @@ define float @test_mask3_vfmsub_ss_0(<4 x float> %a, <4 x float> %b, <4 x float>
; CHECK-NEXT: [[TMP4:%.*]] = fneg float [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[C]], i64 0
-; CHECK-NEXT: [[TMP7:%.*]] = and i8 [[MASK:%.*]], 1
-; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i8 [[TMP7]], 0
-; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[DOTNOT]], float [[TMP6]], float [[TMP5]]
+; CHECK-NEXT: [[TMP7:%.*]] = trunc i8 [[MASK:%.*]] to i1
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
; CHECK-NEXT: ret float [[TMP8]]
;
%1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
@@ -1532,9 +1510,8 @@ define <2 x double> @test_mask3_vfmsub_sd(<2 x double> %a, <2 x double> %b, <2 x
; CHECK-NEXT: [[TMP4:%.*]] = fneg double [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[C]], i64 0
-; CHECK-NEXT: [[TMP7:%.*]] = an...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/84628
More information about the llvm-commits
mailing list