[llvm] X86: Return canonicalized result from LowerFMINIMUM_FMAXIMUM (PR #123868)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 21 18:01:27 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: YunQiang Su (wzssyqa)
<details>
<summary>Changes</summary>
Fixes: #<!-- -->123263.
fminimum/fmaximum and fminimumnum/fmaximumnum shouldn't return
sNaN, instead we should quiet it if a NaN will be returned.
---
Patch is 46.90 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/123868.diff
2 Files Affected:
- (modified) llvm/lib/Target/X86/X86ISelLowering.cpp (+3-2)
- (modified) llvm/test/CodeGen/X86/fminimumnum-fmaximumnum.ll (+189-90)
``````````diff
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index a956074e50d86f..c777bc84461b50 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -334,10 +334,10 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
setOperationAction(ISD::FP_TO_SINT_SAT, VT, Custom);
}
setOperationAction(ISD::FCANONICALIZE, MVT::f32, Custom);
+ setOperationAction(ISD::FCANONICALIZE, MVT::f64, Custom);
if (Subtarget.is64Bit()) {
setOperationAction(ISD::FP_TO_UINT_SAT, MVT::i64, Custom);
setOperationAction(ISD::FP_TO_SINT_SAT, MVT::i64, Custom);
- setOperationAction(ISD::FCANONICALIZE, MVT::f64, Custom);
}
}
if (Subtarget.hasAVX10_2()) {
@@ -29058,7 +29058,8 @@ static SDValue LowerFMINIMUM_FMAXIMUM(SDValue Op, const X86Subtarget &Subtarget,
SDValue IsNaN =
DAG.getSetCC(DL, SetCCType, NewX, NewX, IsNum ? ISD::SETO : ISD::SETUO);
- return DAG.getSelect(DL, VT, IsNaN, NewX, MinMax);
+ MinMax = DAG.getSelect(DL, VT, IsNaN, NewX, MinMax);
+ return DAG.getNode(ISD::FCANONICALIZE, DL, VT, MinMax);
}
static SDValue LowerABD(SDValue Op, const X86Subtarget &Subtarget,
diff --git a/llvm/test/CodeGen/X86/fminimumnum-fmaximumnum.ll b/llvm/test/CodeGen/X86/fminimumnum-fmaximumnum.ll
index bfff6ef41dbe00..d916cb55764721 100644
--- a/llvm/test/CodeGen/X86/fminimumnum-fmaximumnum.ll
+++ b/llvm/test/CodeGen/X86/fminimumnum-fmaximumnum.ll
@@ -41,6 +41,7 @@ define float @test_fmaximumnum(float %x, float %y) nounwind {
; SSE2-NEXT: maxss %xmm1, %xmm3
; SSE2-NEXT: andnps %xmm3, %xmm0
; SSE2-NEXT: orps %xmm4, %xmm0
+; SSE2-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX1-LABEL: test_fmaximumnum:
@@ -58,6 +59,7 @@ define float @test_fmaximumnum(float %x, float %y) nounwind {
; AVX1-NEXT: vmaxss %xmm2, %xmm1, %xmm0
; AVX1-NEXT: vcmpordss %xmm1, %xmm1, %xmm2
; AVX1-NEXT: vblendvps %xmm2, %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fmaximumnum:
@@ -72,6 +74,7 @@ define float @test_fmaximumnum(float %x, float %y) nounwind {
; AVX512-NEXT: vmaxss %xmm2, %xmm1, %xmm0
; AVX512-NEXT: vcmpordss %xmm1, %xmm1, %k1
; AVX512-NEXT: vmovss %xmm1, %xmm0, %xmm0 {%k1}
+; AVX512-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fmaximumnum:
@@ -97,6 +100,7 @@ define float @test_fmaximumnum(float %x, float %y) nounwind {
; X86-NEXT: vmaxss %xmm1, %xmm0, %xmm1
; X86-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; X86-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
; X86-NEXT: popl %eax
@@ -279,6 +283,7 @@ define double @test_fmaximumnum_zero0(double %x, double %y) nounwind {
; SSE2-NEXT: maxsd %xmm3, %xmm1
; SSE2-NEXT: andnpd %xmm1, %xmm0
; SSE2-NEXT: orpd %xmm2, %xmm0
+; SSE2-NEXT: mulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX1-LABEL: test_fmaximumnum_zero0:
@@ -287,6 +292,7 @@ define double @test_fmaximumnum_zero0(double %x, double %y) nounwind {
; AVX1-NEXT: vmaxsd %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vcmpordsd %xmm1, %xmm1, %xmm2
; AVX1-NEXT: vblendvpd %xmm2, %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fmaximumnum_zero0:
@@ -295,6 +301,7 @@ define double @test_fmaximumnum_zero0(double %x, double %y) nounwind {
; AVX512-NEXT: vmaxsd %xmm0, %xmm1, %xmm0
; AVX512-NEXT: vcmpordsd %xmm1, %xmm1, %k1
; AVX512-NEXT: vmovsd %xmm1, %xmm0, %xmm0 {%k1}
+; AVX512-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fmaximumnum_zero0:
@@ -314,7 +321,8 @@ define double @test_fmaximumnum_zero0(double %x, double %y) nounwind {
; X86-NEXT: vmaxsd %xmm1, %xmm0, %xmm1
; X86-NEXT: vcmpordsd %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
-; X86-NEXT: vmovlpd %xmm0, (%esp)
+; X86-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
+; X86-NEXT: vmovsd %xmm0, (%esp)
; X86-NEXT: fldl (%esp)
; X86-NEXT: movl %ebp, %esp
; X86-NEXT: popl %ebp
@@ -334,6 +342,7 @@ define double @test_fmaximumnum_zero1(double %x, double %y) nounwind {
; SSE2-NEXT: maxsd %xmm3, %xmm0
; SSE2-NEXT: andnpd %xmm0, %xmm1
; SSE2-NEXT: orpd %xmm2, %xmm1
+; SSE2-NEXT: mulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; SSE2-NEXT: movapd %xmm1, %xmm0
; SSE2-NEXT: retq
;
@@ -343,6 +352,7 @@ define double @test_fmaximumnum_zero1(double %x, double %y) nounwind {
; AVX1-NEXT: vmaxsd %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vcmpordsd %xmm0, %xmm0, %xmm2
; AVX1-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
+; AVX1-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fmaximumnum_zero1:
@@ -351,7 +361,7 @@ define double @test_fmaximumnum_zero1(double %x, double %y) nounwind {
; AVX512-NEXT: vmaxsd %xmm1, %xmm0, %xmm1
; AVX512-NEXT: vcmpordsd %xmm0, %xmm0, %k1
; AVX512-NEXT: vmovsd %xmm0, %xmm1, %xmm1 {%k1}
-; AVX512-NEXT: vmovapd %xmm1, %xmm0
+; AVX512-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fmaximumnum_zero1:
@@ -371,7 +381,8 @@ define double @test_fmaximumnum_zero1(double %x, double %y) nounwind {
; X86-NEXT: vmaxsd %xmm1, %xmm0, %xmm1
; X86-NEXT: vcmpordsd %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
-; X86-NEXT: vmovlpd %xmm0, (%esp)
+; X86-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
+; X86-NEXT: vmovsd %xmm0, (%esp)
; X86-NEXT: fldl (%esp)
; X86-NEXT: movl %ebp, %esp
; X86-NEXT: popl %ebp
@@ -414,6 +425,7 @@ define float @test_fmaximumnum_nsz(float %x, float %y) "no-signed-zeros-fp-math"
; SSE2-NEXT: maxss %xmm1, %xmm0
; SSE2-NEXT: andnps %xmm0, %xmm2
; SSE2-NEXT: orps %xmm3, %xmm2
+; SSE2-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
; SSE2-NEXT: movaps %xmm2, %xmm0
; SSE2-NEXT: retq
;
@@ -422,6 +434,7 @@ define float @test_fmaximumnum_nsz(float %x, float %y) "no-signed-zeros-fp-math"
; AVX1-NEXT: vmaxss %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; AVX1-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; AVX1-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fmaximumnum_nsz:
@@ -429,7 +442,7 @@ define float @test_fmaximumnum_nsz(float %x, float %y) "no-signed-zeros-fp-math"
; AVX512-NEXT: vmaxss %xmm1, %xmm0, %xmm1
; AVX512-NEXT: vcmpordss %xmm0, %xmm0, %k1
; AVX512-NEXT: vmovss %xmm0, %xmm1, %xmm1 {%k1}
-; AVX512-NEXT: vmovaps %xmm1, %xmm0
+; AVX512-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fmaximumnum_nsz:
@@ -444,6 +457,7 @@ define float @test_fmaximumnum_nsz(float %x, float %y) "no-signed-zeros-fp-math"
; X86-NEXT: vcmpordss %xmm0, %xmm0, %xmm1
; X86-NEXT: vmaxss {{[0-9]+}}(%esp), %xmm0, %xmm2
; X86-NEXT: vblendvps %xmm1, %xmm0, %xmm2, %xmm0
+; X86-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
; X86-NEXT: popl %eax
@@ -455,6 +469,7 @@ define float @test_fmaximumnum_nsz(float %x, float %y) "no-signed-zeros-fp-math"
define float @test_fmaximumnum_combine_cmps(float %x, float %y) nounwind {
; SSE2-LABEL: test_fmaximumnum_combine_cmps:
; SSE2: # %bb.0:
+; SSE2-NEXT: movaps %xmm0, %xmm2
; SSE2-NEXT: divss %xmm0, %xmm1
; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: testl %eax, %eax
@@ -463,18 +478,18 @@ define float @test_fmaximumnum_combine_cmps(float %x, float %y) nounwind {
; SSE2-NEXT: # %bb.1:
; SSE2-NEXT: movaps %xmm1, %xmm3
; SSE2-NEXT: .LBB9_2:
-; SSE2-NEXT: movaps %xmm3, %xmm2
-; SSE2-NEXT: cmpordss %xmm3, %xmm2
-; SSE2-NEXT: movaps %xmm2, %xmm4
+; SSE2-NEXT: movaps %xmm3, %xmm0
+; SSE2-NEXT: cmpordss %xmm3, %xmm0
+; SSE2-NEXT: movaps %xmm0, %xmm4
; SSE2-NEXT: andps %xmm3, %xmm4
; SSE2-NEXT: js .LBB9_4
; SSE2-NEXT: # %bb.3:
-; SSE2-NEXT: movaps %xmm0, %xmm1
+; SSE2-NEXT: movaps %xmm2, %xmm1
; SSE2-NEXT: .LBB9_4:
; SSE2-NEXT: maxss %xmm1, %xmm3
-; SSE2-NEXT: andnps %xmm3, %xmm2
-; SSE2-NEXT: orps %xmm4, %xmm2
-; SSE2-NEXT: movaps %xmm2, %xmm0
+; SSE2-NEXT: andnps %xmm3, %xmm0
+; SSE2-NEXT: orps %xmm4, %xmm0
+; SSE2-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX1-LABEL: test_fmaximumnum_combine_cmps:
@@ -493,6 +508,7 @@ define float @test_fmaximumnum_combine_cmps(float %x, float %y) nounwind {
; AVX1-NEXT: vmaxss %xmm2, %xmm1, %xmm0
; AVX1-NEXT: vcmpordss %xmm1, %xmm1, %xmm2
; AVX1-NEXT: vblendvps %xmm2, %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512F-LABEL: test_fmaximumnum_combine_cmps:
@@ -508,6 +524,7 @@ define float @test_fmaximumnum_combine_cmps(float %x, float %y) nounwind {
; AVX512F-NEXT: vmaxss %xmm2, %xmm1, %xmm0
; AVX512F-NEXT: vcmpordss %xmm1, %xmm1, %k1
; AVX512F-NEXT: vmovss %xmm1, %xmm0, %xmm0 {%k1}
+; AVX512F-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX512F-NEXT: retq
;
; AVX512DQ-LABEL: test_fmaximumnum_combine_cmps:
@@ -546,6 +563,7 @@ define float @test_fmaximumnum_combine_cmps(float %x, float %y) nounwind {
; X86-NEXT: vmaxss %xmm2, %xmm0, %xmm1
; X86-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; X86-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
; X86-NEXT: popl %eax
@@ -562,25 +580,26 @@ define float @test_fmaximumnum_combine_cmps(float %x, float %y) nounwind {
define float @test_fminimumnum(float %x, float %y) nounwind {
; SSE2-LABEL: test_fminimumnum:
; SSE2: # %bb.0:
+; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: testl %eax, %eax
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: js .LBB10_2
; SSE2-NEXT: # %bb.1:
-; SSE2-NEXT: movdqa %xmm0, %xmm3
+; SSE2-NEXT: movdqa %xmm2, %xmm3
; SSE2-NEXT: .LBB10_2:
-; SSE2-NEXT: movdqa %xmm3, %xmm2
-; SSE2-NEXT: cmpordss %xmm3, %xmm2
-; SSE2-NEXT: movaps %xmm2, %xmm4
+; SSE2-NEXT: movdqa %xmm3, %xmm0
+; SSE2-NEXT: cmpordss %xmm3, %xmm0
+; SSE2-NEXT: movaps %xmm0, %xmm4
; SSE2-NEXT: andps %xmm3, %xmm4
; SSE2-NEXT: js .LBB10_4
; SSE2-NEXT: # %bb.3:
-; SSE2-NEXT: movdqa %xmm1, %xmm0
+; SSE2-NEXT: movdqa %xmm1, %xmm2
; SSE2-NEXT: .LBB10_4:
-; SSE2-NEXT: minss %xmm0, %xmm3
-; SSE2-NEXT: andnps %xmm3, %xmm2
-; SSE2-NEXT: orps %xmm4, %xmm2
-; SSE2-NEXT: movaps %xmm2, %xmm0
+; SSE2-NEXT: minss %xmm2, %xmm3
+; SSE2-NEXT: andnps %xmm3, %xmm0
+; SSE2-NEXT: orps %xmm4, %xmm0
+; SSE2-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX1-LABEL: test_fminimumnum:
@@ -598,6 +617,7 @@ define float @test_fminimumnum(float %x, float %y) nounwind {
; AVX1-NEXT: vminss %xmm2, %xmm0, %xmm1
; AVX1-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; AVX1-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; AVX1-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fminimumnum:
@@ -612,7 +632,7 @@ define float @test_fminimumnum(float %x, float %y) nounwind {
; AVX512-NEXT: vminss %xmm2, %xmm0, %xmm1
; AVX512-NEXT: vcmpordss %xmm0, %xmm0, %k1
; AVX512-NEXT: vmovss %xmm0, %xmm1, %xmm1 {%k1}
-; AVX512-NEXT: vmovaps %xmm1, %xmm0
+; AVX512-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fminimumnum:
@@ -638,6 +658,7 @@ define float @test_fminimumnum(float %x, float %y) nounwind {
; X86-NEXT: vminss %xmm2, %xmm0, %xmm1
; X86-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; X86-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
; X86-NEXT: popl %eax
@@ -808,6 +829,7 @@ define double @test_fminimumnum_zero0(double %x, double %y) nounwind {
; SSE2-NEXT: minsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; SSE2-NEXT: andnpd %xmm1, %xmm0
; SSE2-NEXT: orpd %xmm2, %xmm0
+; SSE2-NEXT: mulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX1-LABEL: test_fminimumnum_zero0:
@@ -815,6 +837,7 @@ define double @test_fminimumnum_zero0(double %x, double %y) nounwind {
; AVX1-NEXT: vcmpordsd %xmm1, %xmm1, %xmm0
; AVX1-NEXT: vminsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm2
; AVX1-NEXT: vblendvpd %xmm0, %xmm1, %xmm2, %xmm0
+; AVX1-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fminimumnum_zero0:
@@ -822,6 +845,7 @@ define double @test_fminimumnum_zero0(double %x, double %y) nounwind {
; AVX512-NEXT: vcmpordsd %xmm1, %xmm1, %k1
; AVX512-NEXT: vminsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512-NEXT: vmovsd %xmm1, %xmm0, %xmm0 {%k1}
+; AVX512-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fminimumnum_zero0:
@@ -839,7 +863,8 @@ define double @test_fminimumnum_zero0(double %x, double %y) nounwind {
; X86-NEXT: vcmpordsd %xmm0, %xmm0, %xmm1
; X86-NEXT: vminsd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm2
; X86-NEXT: vblendvpd %xmm1, %xmm0, %xmm2, %xmm0
-; X86-NEXT: vmovlpd %xmm0, (%esp)
+; X86-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
+; X86-NEXT: vmovsd %xmm0, (%esp)
; X86-NEXT: fldl (%esp)
; X86-NEXT: movl %ebp, %esp
; X86-NEXT: popl %ebp
@@ -858,6 +883,7 @@ define double @test_fminimumnum_zero1(double %x, double %y) nounwind {
; SSE2-NEXT: minsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: andnpd %xmm0, %xmm1
; SSE2-NEXT: orpd %xmm2, %xmm1
+; SSE2-NEXT: mulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; SSE2-NEXT: movapd %xmm1, %xmm0
; SSE2-NEXT: retq
;
@@ -866,6 +892,7 @@ define double @test_fminimumnum_zero1(double %x, double %y) nounwind {
; AVX1-NEXT: vcmpordsd %xmm0, %xmm0, %xmm1
; AVX1-NEXT: vminsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm2
; AVX1-NEXT: vblendvpd %xmm1, %xmm0, %xmm2, %xmm0
+; AVX1-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fminimumnum_zero1:
@@ -873,7 +900,7 @@ define double @test_fminimumnum_zero1(double %x, double %y) nounwind {
; AVX512-NEXT: vcmpordsd %xmm0, %xmm0, %k1
; AVX512-NEXT: vminsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; AVX512-NEXT: vmovsd %xmm0, %xmm1, %xmm1 {%k1}
-; AVX512-NEXT: vmovapd %xmm1, %xmm0
+; AVX512-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fminimumnum_zero1:
@@ -891,7 +918,8 @@ define double @test_fminimumnum_zero1(double %x, double %y) nounwind {
; X86-NEXT: vcmpordsd %xmm0, %xmm0, %xmm1
; X86-NEXT: vminsd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm2
; X86-NEXT: vblendvpd %xmm1, %xmm0, %xmm2, %xmm0
-; X86-NEXT: vmovlpd %xmm0, (%esp)
+; X86-NEXT: vmulsd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
+; X86-NEXT: vmovsd %xmm0, (%esp)
; X86-NEXT: fldl (%esp)
; X86-NEXT: movl %ebp, %esp
; X86-NEXT: popl %ebp
@@ -935,6 +963,7 @@ define float @test_fminimumnum_nsz(float %x, float %y) nounwind {
; SSE2-NEXT: minss %xmm1, %xmm0
; SSE2-NEXT: andnps %xmm0, %xmm2
; SSE2-NEXT: orps %xmm3, %xmm2
+; SSE2-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
; SSE2-NEXT: movaps %xmm2, %xmm0
; SSE2-NEXT: retq
;
@@ -943,6 +972,7 @@ define float @test_fminimumnum_nsz(float %x, float %y) nounwind {
; AVX1-NEXT: vminss %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; AVX1-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; AVX1-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: test_fminimumnum_nsz:
@@ -950,7 +980,7 @@ define float @test_fminimumnum_nsz(float %x, float %y) nounwind {
; AVX512-NEXT: vminss %xmm1, %xmm0, %xmm1
; AVX512-NEXT: vcmpordss %xmm0, %xmm0, %k1
; AVX512-NEXT: vmovss %xmm0, %xmm1, %xmm1 {%k1}
-; AVX512-NEXT: vmovaps %xmm1, %xmm0
+; AVX512-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512-NEXT: retq
;
; AVX10_2-LABEL: test_fminimumnum_nsz:
@@ -965,6 +995,7 @@ define float @test_fminimumnum_nsz(float %x, float %y) nounwind {
; X86-NEXT: vcmpordss %xmm0, %xmm0, %xmm1
; X86-NEXT: vminss {{[0-9]+}}(%esp), %xmm0, %xmm2
; X86-NEXT: vblendvps %xmm1, %xmm0, %xmm2, %xmm0
+; X86-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
; X86-NEXT: popl %eax
@@ -995,6 +1026,7 @@ define float @test_fminimumnum_combine_cmps(float %x, float %y) nounwind {
; SSE2-NEXT: minss %xmm0, %xmm3
; SSE2-NEXT: andnps %xmm3, %xmm2
; SSE2-NEXT: orps %xmm4, %xmm2
+; SSE2-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
; SSE2-NEXT: movaps %xmm2, %xmm0
; SSE2-NEXT: retq
;
@@ -1014,6 +1046,7 @@ define float @test_fminimumnum_combine_cmps(float %x, float %y) nounwind {
; AVX1-NEXT: vminss %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; AVX1-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; AVX1-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512F-LABEL: test_fminimumnum_combine_cmps:
@@ -1029,7 +1062,7 @@ define float @test_fminimumnum_combine_cmps(float %x, float %y) nounwind {
; AVX512F-NEXT: vminss %xmm2, %xmm0, %xmm1
; AVX512F-NEXT: vcmpordss %xmm0, %xmm0, %k1
; AVX512F-NEXT: vmovss %xmm0, %xmm1, %xmm1 {%k1}
-; AVX512F-NEXT: vmovaps %xmm1, %xmm0
+; AVX512F-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX512F-NEXT: retq
;
; AVX512DQ-LABEL: test_fminimumnum_combine_cmps:
@@ -1068,6 +1101,7 @@ define float @test_fminimumnum_combine_cmps(float %x, float %y) nounwind {
; X86-NEXT: vminss %xmm1, %xmm0, %xmm1
; X86-NEXT: vcmpordss %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; X86-NEXT: vmulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
; X86-NEXT: popl %eax
@@ -1099,6 +1133,7 @@ define <2 x double> @test_fminimumnum_vector(<2 x double> %x, <2 x double> %y) {
; SSE2-NEXT: andpd %xmm0, %xmm3
; SSE2-NEXT: andnpd %xmm1, %xmm0
; SSE2-NEXT: orpd %xmm3, %xmm0
+; SSE2-NEXT: mulpd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test_fminimumnum_vector:
@@ -1108,6 +1143,7 @@ define <2 x double> @test_fminimumnum_vector(<2 x double> %x, <2 x double> %y) {
; AVX-NEXT: vminpd %xmm2, %xmm0, %xmm1
; AVX-NEXT: vcmpordpd %xmm0, %xmm0, %xmm2
; AVX-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
+; AVX-NEXT: vmulpd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX10_2-LABEL: test_fminimumnum_vector:
@@ -1122,6 +1158,7 @@ define <2 x double> @test_fminimumnum_vector(<2 x double> %x, <2 x double> %y) {
; X86-NEXT: vminpd %xmm2, %xmm0, %xmm1
; X86-NEXT: vcmpordpd %xmm0, %xmm0, %xmm2
; X86-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
+; X86-NEXT: vmulpd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0, %xmm0
; X86-NEXT: retl
%r = call <2 x double> @llvm.minimumnum.v2f64(<2 x double> %x, <2 x double> %y)
ret <2 x double> %r
@@ -1265,6 +1302,7 @@ define <2 x double> @test_fminimumnum_vector_different_zeros(<2 x double> %x) {
; SSE2-NEXT: andpd %xmm0, %xmm3
; SSE2-NEXT: andnpd %xmm1, %xmm0
; SSE2-NEXT: orpd %xmm3, %xmm0
+; SSE2-NEXT: mulpd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test_fminimumnum_vector_different_zeros:
@@ -1276,6 +1314,7 @@ define <2 x double> @test_fminimumnum_vector_different_zeros(<2 x double> %x) {
; AVX-NEXT: vminpd %xmm2, %xmm0, %xmm1
; AVX-NEXT: vcmpordpd %xmm0, %xmm0, %xmm2
; AVX-NEXT: vblendvpd %x...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/123868
More information about the llvm-commits
mailing list