[llvm] [X86][NFC] Added/Updated SINCOS function testcases (PR #141283)
via llvm-commits
llvm-commits at lists.llvm.org
Mon May 26 08:10:23 PDT 2025
https://github.com/JaydeepChauhan14 updated https://github.com/llvm/llvm-project/pull/141283
>From 52519aeaebfaa42ca634c1659b43e69c3b7a99fc Mon Sep 17 00:00:00 2001
From: Chauhan Jaydeep Ashwinbhai <chauhan.jaydeep.ashwinbhai at intel.com>
Date: Fri, 23 May 2025 12:04:37 -0700
Subject: [PATCH 1/2] [X86][NFC] Added/Updated SINCOS function testcases
---
llvm/test/CodeGen/X86/llvm.sincos.ll | 370 ++++++++++++++---------
llvm/test/CodeGen/X86/llvm.sincos.vec.ll | 103 +++++++
2 files changed, 326 insertions(+), 147 deletions(-)
create mode 100644 llvm/test/CodeGen/X86/llvm.sincos.vec.ll
diff --git a/llvm/test/CodeGen/X86/llvm.sincos.ll b/llvm/test/CodeGen/X86/llvm.sincos.ll
index a429314630e56..a8a3e233c072e 100644
--- a/llvm/test/CodeGen/X86/llvm.sincos.ll
+++ b/llvm/test/CodeGen/X86/llvm.sincos.ll
@@ -1,157 +1,233 @@
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp --version 5
-; RUN: llc < %s -mtriple=i386-unknown-linux-gnu | FileCheck %s
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-linux-gnu -fast-isel | FileCheck %s --check-prefixes=X86,FASTISEL-X86
+; RUN: llc < %s -mtriple=x86_64-linux-gnu -fast-isel | FileCheck %s --check-prefixes=X64,FASTISEL-X64
+; RUN: llc < %s -mtriple=i686-linux-gnu -global-isel=0 -fast-isel=0 | FileCheck %s --check-prefixes=X86,SDAG-X86
+; RUN: llc < %s -mtriple=x86_64-linux-gnu -global-isel=0 -fast-isel=0 | FileCheck %s --check-prefixes=X64,SDAG-X64
+; RUN: llc < %s -mtriple=x86_64-linux-gnu -global-isel=1 -global-isel-abort=2 | FileCheck %s --check-prefixes=X64,GISEL-X64
-define void @test_sincos_v4f32(<4 x float> %x, ptr noalias %out_sin, ptr noalias %out_cos) {
-; CHECK-LABEL: test_sincos_v4f32:
-; CHECK: # %bb.0:
-; CHECK-NEXT: pushl %edi
-; CHECK-NEXT: .cfi_def_cfa_offset 8
-; CHECK-NEXT: pushl %esi
-; CHECK-NEXT: .cfi_def_cfa_offset 12
-; CHECK-NEXT: subl $52, %esp
-; CHECK-NEXT: .cfi_def_cfa_offset 64
-; CHECK-NEXT: .cfi_offset %esi, -12
-; CHECK-NEXT: .cfi_offset %edi, -8
-; CHECK-NEXT: movl 84(%esp), %esi
-; CHECK-NEXT: flds 76(%esp)
-; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; CHECK-NEXT: flds 64(%esp)
-; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; CHECK-NEXT: flds 72(%esp)
-; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; CHECK-NEXT: flds 68(%esp)
-; CHECK-NEXT: movl 80(%esp), %edi
-; CHECK-NEXT: leal 40(%esp), %eax
-; CHECK-NEXT: movl %eax, 8(%esp)
-; CHECK-NEXT: leal 4(%edi), %eax
-; CHECK-NEXT: movl %eax, 4(%esp)
-; CHECK-NEXT: fstps (%esp)
-; CHECK-NEXT: calll sincosf
-; CHECK-NEXT: leal 44(%esp), %eax
-; CHECK-NEXT: movl %eax, 8(%esp)
-; CHECK-NEXT: leal 8(%edi), %eax
-; CHECK-NEXT: movl %eax, 4(%esp)
-; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; CHECK-NEXT: fstps (%esp)
-; CHECK-NEXT: calll sincosf
-; CHECK-NEXT: leal 36(%esp), %eax
-; CHECK-NEXT: movl %eax, 8(%esp)
-; CHECK-NEXT: movl %edi, 4(%esp)
-; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; CHECK-NEXT: fstps (%esp)
-; CHECK-NEXT: calll sincosf
-; CHECK-NEXT: leal 48(%esp), %eax
-; CHECK-NEXT: movl %eax, 8(%esp)
-; CHECK-NEXT: addl $12, %edi
-; CHECK-NEXT: movl %edi, 4(%esp)
-; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; CHECK-NEXT: fstps (%esp)
-; CHECK-NEXT: calll sincosf
-; CHECK-NEXT: flds 36(%esp)
-; CHECK-NEXT: flds 40(%esp)
-; CHECK-NEXT: flds 44(%esp)
-; CHECK-NEXT: flds 48(%esp)
-; CHECK-NEXT: fstps 12(%esi)
-; CHECK-NEXT: fstps 8(%esi)
-; CHECK-NEXT: fstps 4(%esi)
-; CHECK-NEXT: fstps (%esi)
-; CHECK-NEXT: addl $52, %esp
-; CHECK-NEXT: .cfi_def_cfa_offset 12
-; CHECK-NEXT: popl %esi
-; CHECK-NEXT: .cfi_def_cfa_offset 8
-; CHECK-NEXT: popl %edi
-; CHECK-NEXT: .cfi_def_cfa_offset 4
-; CHECK-NEXT: retl
- %result = call { <4 x float>, <4 x float> } @llvm.sincos.v4f32(<4 x float> %x)
- %result.0 = extractvalue { <4 x float>, <4 x float> } %result, 0
- %result.1 = extractvalue { <4 x float>, <4 x float> } %result, 1
- store <4 x float> %result.0, ptr %out_sin, align 4
- store <4 x float> %result.1, ptr %out_cos, align 4
- ret void
+define { float, float } @test_sincos_f32(float %Val) nounwind {
+; X86-LABEL: test_sincos_f32:
+; X86: # %bb.0:
+; X86-NEXT: subl $28, %esp
+; X86-NEXT: flds {{[0-9]+}}(%esp)
+; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: fstps (%esp)
+; X86-NEXT: calll sincosf
+; X86-NEXT: flds {{[0-9]+}}(%esp)
+; X86-NEXT: flds {{[0-9]+}}(%esp)
+; X86-NEXT: addl $28, %esp
+; X86-NEXT: retl
+;
+; X64-LABEL: test_sincos_f32:
+; X64: # %bb.0:
+; X64-NEXT: pushq %rax
+; X64-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
+; X64-NEXT: movq %rsp, %rsi
+; X64-NEXT: callq sincosf at PLT
+; X64-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X64-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X64-NEXT: popq %rax
+; X64-NEXT: retq
+ %res = call { float, float } @llvm.sincos.f32(float %Val)
+ ret { float, float } %res
}
-define void @test_sincos_v2f64(<2 x double> %x, ptr noalias %out_sin, ptr noalias %out_cos) {
-; CHECK-LABEL: test_sincos_v2f64:
-; CHECK: # %bb.0:
-; CHECK-NEXT: pushl %edi
-; CHECK-NEXT: .cfi_def_cfa_offset 8
-; CHECK-NEXT: pushl %esi
-; CHECK-NEXT: .cfi_def_cfa_offset 12
-; CHECK-NEXT: subl $52, %esp
-; CHECK-NEXT: .cfi_def_cfa_offset 64
-; CHECK-NEXT: .cfi_offset %esi, -12
-; CHECK-NEXT: .cfi_offset %edi, -8
-; CHECK-NEXT: movl 84(%esp), %esi
-; CHECK-NEXT: fldl 72(%esp)
-; CHECK-NEXT: fstpl {{[-0-9]+}}(%e{{[sb]}}p) # 8-byte Folded Spill
-; CHECK-NEXT: fldl 64(%esp)
-; CHECK-NEXT: movl 80(%esp), %edi
-; CHECK-NEXT: leal 24(%esp), %eax
-; CHECK-NEXT: movl %eax, 12(%esp)
-; CHECK-NEXT: movl %edi, 8(%esp)
-; CHECK-NEXT: fstpl (%esp)
-; CHECK-NEXT: calll sincos
-; CHECK-NEXT: leal 32(%esp), %eax
-; CHECK-NEXT: movl %eax, 12(%esp)
-; CHECK-NEXT: addl $8, %edi
-; CHECK-NEXT: movl %edi, 8(%esp)
-; CHECK-NEXT: fldl {{[-0-9]+}}(%e{{[sb]}}p) # 8-byte Folded Reload
-; CHECK-NEXT: fstpl (%esp)
-; CHECK-NEXT: calll sincos
-; CHECK-NEXT: fldl 24(%esp)
-; CHECK-NEXT: fldl 32(%esp)
-; CHECK-NEXT: fstpl 8(%esi)
-; CHECK-NEXT: fstpl (%esi)
-; CHECK-NEXT: addl $52, %esp
-; CHECK-NEXT: .cfi_def_cfa_offset 12
-; CHECK-NEXT: popl %esi
-; CHECK-NEXT: .cfi_def_cfa_offset 8
-; CHECK-NEXT: popl %edi
-; CHECK-NEXT: .cfi_def_cfa_offset 4
-; CHECK-NEXT: retl
- %result = call { <2 x double>, <2 x double> } @llvm.sincos.v2f64(<2 x double> %x)
- %result.0 = extractvalue { <2 x double>, <2 x double> } %result, 0
- %result.1 = extractvalue { <2 x double>, <2 x double> } %result, 1
- store <2 x double> %result.0, ptr %out_sin, align 8
- store <2 x double> %result.1, ptr %out_cos, align 8
- ret void
+define { double, double } @test_sincos_f64(double %Val) nounwind {
+; X86-LABEL: test_sincos_f64:
+; X86: # %bb.0:
+; X86-NEXT: subl $44, %esp
+; X86-NEXT: fldl {{[0-9]+}}(%esp)
+; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: fstpl (%esp)
+; X86-NEXT: calll sincos
+; X86-NEXT: fldl {{[0-9]+}}(%esp)
+; X86-NEXT: fldl {{[0-9]+}}(%esp)
+; X86-NEXT: addl $44, %esp
+; X86-NEXT: retl
+;
+; X64-LABEL: test_sincos_f64:
+; X64: # %bb.0:
+; X64-NEXT: subq $24, %rsp
+; X64-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
+; X64-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
+; X64-NEXT: callq sincos at PLT
+; X64-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
+; X64-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
+; X64-NEXT: addq $24, %rsp
+; X64-NEXT: retq
+ %res = call { double, double } @llvm.sincos.f64(double %Val)
+ ret { double, double } %res
+}
+
+define { x86_fp80, x86_fp80 } @test_sincos_f80(x86_fp80 %Val) nounwind {
+; X86-LABEL: test_sincos_f80:
+; X86: # %bb.0:
+; X86-NEXT: subl $44, %esp
+; X86-NEXT: fldt {{[0-9]+}}(%esp)
+; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: fstpt (%esp)
+; X86-NEXT: calll sincosl
+; X86-NEXT: fldt {{[0-9]+}}(%esp)
+; X86-NEXT: fldt {{[0-9]+}}(%esp)
+; X86-NEXT: addl $44, %esp
+; X86-NEXT: retl
+;
+; X64-LABEL: test_sincos_f80:
+; X64: # %bb.0:
+; X64-NEXT: subq $56, %rsp
+; X64-NEXT: fldt {{[0-9]+}}(%rsp)
+; X64-NEXT: fstpt (%rsp)
+; X64-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
+; X64-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
+; X64-NEXT: callq sincosl at PLT
+; X64-NEXT: fldt {{[0-9]+}}(%rsp)
+; X64-NEXT: fldt {{[0-9]+}}(%rsp)
+; X64-NEXT: addq $56, %rsp
+; X64-NEXT: retq
+ %res = call { x86_fp80, x86_fp80 } @llvm.sincos.f80(x86_fp80 %Val)
+ ret { x86_fp80, x86_fp80 } %res
}
declare void @foo(ptr, ptr)
-define void @can_fold_with_call_in_chain(float %x, ptr noalias %a, ptr noalias %b) {
-; CHECK-LABEL: can_fold_with_call_in_chain:
-; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: pushl %edi
-; CHECK-NEXT: .cfi_def_cfa_offset 8
-; CHECK-NEXT: pushl %esi
-; CHECK-NEXT: .cfi_def_cfa_offset 12
-; CHECK-NEXT: subl $20, %esp
-; CHECK-NEXT: .cfi_def_cfa_offset 32
-; CHECK-NEXT: .cfi_offset %esi, -12
-; CHECK-NEXT: .cfi_offset %edi, -8
-; CHECK-NEXT: flds 32(%esp)
-; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; CHECK-NEXT: movl 36(%esp), %edi
-; CHECK-NEXT: movl 40(%esp), %esi
-; CHECK-NEXT: movl %esi, 4(%esp)
-; CHECK-NEXT: movl %edi, (%esp)
-; CHECK-NEXT: calll foo at PLT
-; CHECK-NEXT: leal 16(%esp), %eax
-; CHECK-NEXT: movl %eax, 8(%esp)
-; CHECK-NEXT: movl %edi, 4(%esp)
-; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; CHECK-NEXT: fstps (%esp)
-; CHECK-NEXT: calll sincosf
-; CHECK-NEXT: flds 16(%esp)
-; CHECK-NEXT: fstps (%esi)
-; CHECK-NEXT: addl $20, %esp
-; CHECK-NEXT: .cfi_def_cfa_offset 12
-; CHECK-NEXT: popl %esi
-; CHECK-NEXT: .cfi_def_cfa_offset 8
-; CHECK-NEXT: popl %edi
-; CHECK-NEXT: .cfi_def_cfa_offset 4
-; CHECK-NEXT: retl
+define void @can_fold_with_call_in_chain(float %x, ptr noalias %a, ptr noalias %b) nounwind {
+; FASTISEL-X86-LABEL: can_fold_with_call_in_chain:
+; FASTISEL-X86: # %bb.0: # %entry
+; FASTISEL-X86-NEXT: pushl %edi
+; FASTISEL-X86-NEXT: pushl %esi
+; FASTISEL-X86-NEXT: subl $20, %esp
+; FASTISEL-X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; FASTISEL-X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; FASTISEL-X86-NEXT: flds {{[0-9]+}}(%esp)
+; FASTISEL-X86-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; FASTISEL-X86-NEXT: movl %esi, {{[0-9]+}}(%esp)
+; FASTISEL-X86-NEXT: movl %edi, (%esp)
+; FASTISEL-X86-NEXT: calll foo at PLT
+; FASTISEL-X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; FASTISEL-X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; FASTISEL-X86-NEXT: movl %edi, {{[0-9]+}}(%esp)
+; FASTISEL-X86-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; FASTISEL-X86-NEXT: fstps (%esp)
+; FASTISEL-X86-NEXT: calll sincosf
+; FASTISEL-X86-NEXT: flds {{[0-9]+}}(%esp)
+; FASTISEL-X86-NEXT: fstps (%esi)
+; FASTISEL-X86-NEXT: addl $20, %esp
+; FASTISEL-X86-NEXT: popl %esi
+; FASTISEL-X86-NEXT: popl %edi
+; FASTISEL-X86-NEXT: retl
+;
+; FASTISEL-X64-LABEL: can_fold_with_call_in_chain:
+; FASTISEL-X64: # %bb.0: # %entry
+; FASTISEL-X64-NEXT: pushq %r14
+; FASTISEL-X64-NEXT: pushq %rbx
+; FASTISEL-X64-NEXT: pushq %rax
+; FASTISEL-X64-NEXT: movq %rsi, %rbx
+; FASTISEL-X64-NEXT: movq %rdi, %r14
+; FASTISEL-X64-NEXT: movss %xmm0, (%rsp) # 4-byte Spill
+; FASTISEL-X64-NEXT: callq sinf at PLT
+; FASTISEL-X64-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
+; FASTISEL-X64-NEXT: movss (%rsp), %xmm0 # 4-byte Reload
+; FASTISEL-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; FASTISEL-X64-NEXT: callq cosf at PLT
+; FASTISEL-X64-NEXT: movss %xmm0, (%rsp) # 4-byte Spill
+; FASTISEL-X64-NEXT: movq %r14, %rdi
+; FASTISEL-X64-NEXT: movq %rbx, %rsi
+; FASTISEL-X64-NEXT: callq foo at PLT
+; FASTISEL-X64-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
+; FASTISEL-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; FASTISEL-X64-NEXT: movss %xmm0, (%r14)
+; FASTISEL-X64-NEXT: movss (%rsp), %xmm0 # 4-byte Reload
+; FASTISEL-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; FASTISEL-X64-NEXT: movss %xmm0, (%rbx)
+; FASTISEL-X64-NEXT: addq $8, %rsp
+; FASTISEL-X64-NEXT: popq %rbx
+; FASTISEL-X64-NEXT: popq %r14
+; FASTISEL-X64-NEXT: retq
+;
+; SDAG-X86-LABEL: can_fold_with_call_in_chain:
+; SDAG-X86: # %bb.0: # %entry
+; SDAG-X86-NEXT: pushl %edi
+; SDAG-X86-NEXT: pushl %esi
+; SDAG-X86-NEXT: subl $20, %esp
+; SDAG-X86-NEXT: flds {{[0-9]+}}(%esp)
+; SDAG-X86-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; SDAG-X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; SDAG-X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; SDAG-X86-NEXT: movl %esi, {{[0-9]+}}(%esp)
+; SDAG-X86-NEXT: movl %edi, (%esp)
+; SDAG-X86-NEXT: calll foo at PLT
+; SDAG-X86-NEXT: leal {{[0-9]+}}(%esp), %eax
+; SDAG-X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; SDAG-X86-NEXT: movl %edi, {{[0-9]+}}(%esp)
+; SDAG-X86-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; SDAG-X86-NEXT: fstps (%esp)
+; SDAG-X86-NEXT: calll sincosf
+; SDAG-X86-NEXT: flds {{[0-9]+}}(%esp)
+; SDAG-X86-NEXT: fstps (%esi)
+; SDAG-X86-NEXT: addl $20, %esp
+; SDAG-X86-NEXT: popl %esi
+; SDAG-X86-NEXT: popl %edi
+; SDAG-X86-NEXT: retl
+;
+; SDAG-X64-LABEL: can_fold_with_call_in_chain:
+; SDAG-X64: # %bb.0: # %entry
+; SDAG-X64-NEXT: pushq %r14
+; SDAG-X64-NEXT: pushq %rbx
+; SDAG-X64-NEXT: pushq %rax
+; SDAG-X64-NEXT: movq %rsi, %rbx
+; SDAG-X64-NEXT: movq %rdi, %r14
+; SDAG-X64-NEXT: movss %xmm0, (%rsp) # 4-byte Spill
+; SDAG-X64-NEXT: callq foo at PLT
+; SDAG-X64-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
+; SDAG-X64-NEXT: movss (%rsp), %xmm0 # 4-byte Reload
+; SDAG-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; SDAG-X64-NEXT: movq %r14, %rdi
+; SDAG-X64-NEXT: callq sincosf at PLT
+; SDAG-X64-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; SDAG-X64-NEXT: movss %xmm0, (%rbx)
+; SDAG-X64-NEXT: addq $8, %rsp
+; SDAG-X64-NEXT: popq %rbx
+; SDAG-X64-NEXT: popq %r14
+; SDAG-X64-NEXT: retq
+;
+; GISEL-X64-LABEL: can_fold_with_call_in_chain:
+; GISEL-X64: # %bb.0: # %entry
+; GISEL-X64-NEXT: pushq %r14
+; GISEL-X64-NEXT: pushq %rbx
+; GISEL-X64-NEXT: pushq %rax
+; GISEL-X64-NEXT: movss %xmm0, (%rsp) # 4-byte Spill
+; GISEL-X64-NEXT: movq %rdi, %rbx
+; GISEL-X64-NEXT: movq %rsi, %r14
+; GISEL-X64-NEXT: callq sinf
+; GISEL-X64-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
+; GISEL-X64-NEXT: movss (%rsp), %xmm0 # 4-byte Reload
+; GISEL-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; GISEL-X64-NEXT: callq cosf
+; GISEL-X64-NEXT: movss %xmm0, (%rsp) # 4-byte Spill
+; GISEL-X64-NEXT: movq %rbx, %rdi
+; GISEL-X64-NEXT: movq %r14, %rsi
+; GISEL-X64-NEXT: callq foo
+; GISEL-X64-NEXT: movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Folded Reload
+; GISEL-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; GISEL-X64-NEXT: movd %xmm0, %eax
+; GISEL-X64-NEXT: movl %eax, (%rbx)
+; GISEL-X64-NEXT: movd (%rsp), %xmm0 # 4-byte Folded Reload
+; GISEL-X64-NEXT: # xmm0 = mem[0],zero,zero,zero
+; GISEL-X64-NEXT: movd %xmm0, %eax
+; GISEL-X64-NEXT: movl %eax, (%r14)
+; GISEL-X64-NEXT: addq $8, %rsp
+; GISEL-X64-NEXT: popq %rbx
+; GISEL-X64-NEXT: popq %r14
+; GISEL-X64-NEXT: retq
entry:
%sin = tail call float @llvm.sin.f32(float %x)
%cos = tail call float @llvm.cos.f32(float %x)
diff --git a/llvm/test/CodeGen/X86/llvm.sincos.vec.ll b/llvm/test/CodeGen/X86/llvm.sincos.vec.ll
new file mode 100644
index 0000000000000..834dd788ff7fb
--- /dev/null
+++ b/llvm/test/CodeGen/X86/llvm.sincos.vec.ll
@@ -0,0 +1,103 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp --version 5
+; RUN: llc < %s -mtriple=i386-unknown-linux-gnu | FileCheck %s
+
+define void @test_sincos_v4f32(<4 x float> %x, ptr noalias %out_sin, ptr noalias %out_cos) nounwind {
+; CHECK-LABEL: test_sincos_v4f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: pushl %edi
+; CHECK-NEXT: pushl %esi
+; CHECK-NEXT: subl $52, %esp
+; CHECK-NEXT: movl 84(%esp), %esi
+; CHECK-NEXT: flds 76(%esp)
+; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; CHECK-NEXT: flds 64(%esp)
+; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; CHECK-NEXT: flds 72(%esp)
+; CHECK-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; CHECK-NEXT: flds 68(%esp)
+; CHECK-NEXT: movl 80(%esp), %edi
+; CHECK-NEXT: leal 40(%esp), %eax
+; CHECK-NEXT: movl %eax, 8(%esp)
+; CHECK-NEXT: leal 4(%edi), %eax
+; CHECK-NEXT: movl %eax, 4(%esp)
+; CHECK-NEXT: fstps (%esp)
+; CHECK-NEXT: calll sincosf
+; CHECK-NEXT: leal 44(%esp), %eax
+; CHECK-NEXT: movl %eax, 8(%esp)
+; CHECK-NEXT: leal 8(%edi), %eax
+; CHECK-NEXT: movl %eax, 4(%esp)
+; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; CHECK-NEXT: fstps (%esp)
+; CHECK-NEXT: calll sincosf
+; CHECK-NEXT: leal 36(%esp), %eax
+; CHECK-NEXT: movl %eax, 8(%esp)
+; CHECK-NEXT: movl %edi, 4(%esp)
+; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; CHECK-NEXT: fstps (%esp)
+; CHECK-NEXT: calll sincosf
+; CHECK-NEXT: leal 48(%esp), %eax
+; CHECK-NEXT: movl %eax, 8(%esp)
+; CHECK-NEXT: addl $12, %edi
+; CHECK-NEXT: movl %edi, 4(%esp)
+; CHECK-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; CHECK-NEXT: fstps (%esp)
+; CHECK-NEXT: calll sincosf
+; CHECK-NEXT: flds 36(%esp)
+; CHECK-NEXT: flds 40(%esp)
+; CHECK-NEXT: flds 44(%esp)
+; CHECK-NEXT: flds 48(%esp)
+; CHECK-NEXT: fstps 12(%esi)
+; CHECK-NEXT: fstps 8(%esi)
+; CHECK-NEXT: fstps 4(%esi)
+; CHECK-NEXT: fstps (%esi)
+; CHECK-NEXT: addl $52, %esp
+; CHECK-NEXT: popl %esi
+; CHECK-NEXT: popl %edi
+; CHECK-NEXT: retl
+ %result = call { <4 x float>, <4 x float> } @llvm.sincos.v4f32(<4 x float> %x)
+ %result.0 = extractvalue { <4 x float>, <4 x float> } %result, 0
+ %result.1 = extractvalue { <4 x float>, <4 x float> } %result, 1
+ store <4 x float> %result.0, ptr %out_sin, align 4
+ store <4 x float> %result.1, ptr %out_cos, align 4
+ ret void
+}
+
+define void @test_sincos_v2f64(<2 x double> %x, ptr noalias %out_sin, ptr noalias %out_cos) nounwind {
+; CHECK-LABEL: test_sincos_v2f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: pushl %edi
+; CHECK-NEXT: pushl %esi
+; CHECK-NEXT: subl $52, %esp
+; CHECK-NEXT: movl 84(%esp), %esi
+; CHECK-NEXT: fldl 72(%esp)
+; CHECK-NEXT: fstpl {{[-0-9]+}}(%e{{[sb]}}p) # 8-byte Folded Spill
+; CHECK-NEXT: fldl 64(%esp)
+; CHECK-NEXT: movl 80(%esp), %edi
+; CHECK-NEXT: leal 24(%esp), %eax
+; CHECK-NEXT: movl %eax, 12(%esp)
+; CHECK-NEXT: movl %edi, 8(%esp)
+; CHECK-NEXT: fstpl (%esp)
+; CHECK-NEXT: calll sincos
+; CHECK-NEXT: leal 32(%esp), %eax
+; CHECK-NEXT: movl %eax, 12(%esp)
+; CHECK-NEXT: addl $8, %edi
+; CHECK-NEXT: movl %edi, 8(%esp)
+; CHECK-NEXT: fldl {{[-0-9]+}}(%e{{[sb]}}p) # 8-byte Folded Reload
+; CHECK-NEXT: fstpl (%esp)
+; CHECK-NEXT: calll sincos
+; CHECK-NEXT: fldl 24(%esp)
+; CHECK-NEXT: fldl 32(%esp)
+; CHECK-NEXT: fstpl 8(%esi)
+; CHECK-NEXT: fstpl (%esi)
+; CHECK-NEXT: addl $52, %esp
+; CHECK-NEXT: popl %esi
+; CHECK-NEXT: popl %edi
+; CHECK-NEXT: retl
+ %result = call { <2 x double>, <2 x double> } @llvm.sincos.v2f64(<2 x double> %x)
+ %result.0 = extractvalue { <2 x double>, <2 x double> } %result, 0
+ %result.1 = extractvalue { <2 x double>, <2 x double> } %result, 1
+ store <2 x double> %result.0, ptr %out_sin, align 8
+ store <2 x double> %result.1, ptr %out_cos, align 8
+ ret void
+}
+
>From c14ad562586f74912cb1fb42c7af1eac4147df6f Mon Sep 17 00:00:00 2001
From: Chauhan Jaydeep Ashwinbhai <chauhan.jaydeep.ashwinbhai at intel.com>
Date: Mon, 26 May 2025 08:10:11 -0700
Subject: [PATCH 2/2] Added i686 RUN case
---
llvm/test/CodeGen/X86/llvm.sincos.ll | 29 ++++++++++++++++++++++++++++
1 file changed, 29 insertions(+)
diff --git a/llvm/test/CodeGen/X86/llvm.sincos.ll b/llvm/test/CodeGen/X86/llvm.sincos.ll
index a8a3e233c072e..5734729a2c507 100644
--- a/llvm/test/CodeGen/X86/llvm.sincos.ll
+++ b/llvm/test/CodeGen/X86/llvm.sincos.ll
@@ -3,6 +3,7 @@
; RUN: llc < %s -mtriple=x86_64-linux-gnu -fast-isel | FileCheck %s --check-prefixes=X64,FASTISEL-X64
; RUN: llc < %s -mtriple=i686-linux-gnu -global-isel=0 -fast-isel=0 | FileCheck %s --check-prefixes=X86,SDAG-X86
; RUN: llc < %s -mtriple=x86_64-linux-gnu -global-isel=0 -fast-isel=0 | FileCheck %s --check-prefixes=X64,SDAG-X64
+; RUN: llc < %s -mtriple=i686-linux-gnu -global-isel=1 -global-isel-abort=2 | FileCheck %s --check-prefixes=X86,GISEL-X86
; RUN: llc < %s -mtriple=x86_64-linux-gnu -global-isel=1 -global-isel-abort=2 | FileCheck %s --check-prefixes=X64,GISEL-X64
define { float, float } @test_sincos_f32(float %Val) nounwind {
@@ -199,6 +200,34 @@ define void @can_fold_with_call_in_chain(float %x, ptr noalias %a, ptr noalias %
; SDAG-X64-NEXT: popq %r14
; SDAG-X64-NEXT: retq
;
+; GISEL-X86-LABEL: can_fold_with_call_in_chain:
+; GISEL-X86: # %bb.0: # %entry
+; GISEL-X86-NEXT: pushl %ebx
+; GISEL-X86-NEXT: pushl %edi
+; GISEL-X86-NEXT: pushl %esi
+; GISEL-X86-NEXT: subl $16, %esp
+; GISEL-X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; GISEL-X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; GISEL-X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; GISEL-X86-NEXT: movl %ebx, (%esp)
+; GISEL-X86-NEXT: calll sinf
+; GISEL-X86-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; GISEL-X86-NEXT: movl %ebx, (%esp)
+; GISEL-X86-NEXT: calll cosf
+; GISEL-X86-NEXT: fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; GISEL-X86-NEXT: movl %esi, (%esp)
+; GISEL-X86-NEXT: movl %edi, {{[0-9]+}}(%esp)
+; GISEL-X86-NEXT: calll foo
+; GISEL-X86-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; GISEL-X86-NEXT: fstps (%esi)
+; GISEL-X86-NEXT: flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; GISEL-X86-NEXT: fstps (%edi)
+; GISEL-X86-NEXT: addl $16, %esp
+; GISEL-X86-NEXT: popl %esi
+; GISEL-X86-NEXT: popl %edi
+; GISEL-X86-NEXT: popl %ebx
+; GISEL-X86-NEXT: retl
+;
; GISEL-X64-LABEL: can_fold_with_call_in_chain:
; GISEL-X64: # %bb.0: # %entry
; GISEL-X64-NEXT: pushq %r14
More information about the llvm-commits
mailing list