llvm-project/llvm/test/CodeGen/X86/pr38738.ll

255 lines
8.8 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -o - -mattr=-x87,+sse,-sse2 %s | FileCheck --check-prefixes=X64SSE %s
; RUN: llc -mtriple=i686-unknown-linux-gnu -o - -mattr=-x87,+sse,-sse2 %s | FileCheck --check-prefixes=X86SSE %s
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -o - -mattr=-x87,+sse2,-sse3 %s | FileCheck --check-prefixes=X64SSE2 %s
; RUN: llc -mtriple=i686-unknown-linux-gnu -o - -mattr=-x87,+sse2,-sse3 %s | FileCheck --check-prefixes=X86SSE2 %s
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -o - -mattr=-x87,+avx,-avx2 %s | FileCheck --check-prefixes=X64AVX %s
; RUN: llc -mtriple=i686-unknown-linux-gnu -o - -mattr=-x87,+avx,-avx2 %s | FileCheck --check-prefixes=X86AVX %s
%struct.params = type { double, double }
define i32 @pr38738() {
; X64SSE-LABEL: pr38738:
; X64SSE: # %bb.0: # %entry
; X64SSE-NEXT: xorps %xmm0, %xmm0
; X64SSE-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; X64SSE-NEXT: movl $0, -{{[0-9]+}}(%rsp)
; X64SSE-NEXT: movl -{{[0-9]+}}(%rsp), %eax
; X64SSE-NEXT: retq
;
; X86SSE-LABEL: pr38738:
; X86SSE: # %bb.0: # %entry
; X86SSE-NEXT: subl $28, %esp
; X86SSE-NEXT: .cfi_def_cfa_offset 32
; X86SSE-NEXT: movl $0, {{[0-9]+}}(%esp)
; X86SSE-NEXT: movl $0, {{[0-9]+}}(%esp)
; X86SSE-NEXT: movl $0, {{[0-9]+}}(%esp)
; X86SSE-NEXT: movl $0, (%esp)
; X86SSE-NEXT: movl $0, {{[0-9]+}}(%esp)
; X86SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86SSE-NEXT: addl $28, %esp
; X86SSE-NEXT: .cfi_def_cfa_offset 4
; X86SSE-NEXT: retl
;
; X64SSE2-LABEL: pr38738:
; X64SSE2: # %bb.0: # %entry
; X64SSE2-NEXT: xorps %xmm0, %xmm0
; X64SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; X64SSE2-NEXT: movl $0, -{{[0-9]+}}(%rsp)
; X64SSE2-NEXT: movl -{{[0-9]+}}(%rsp), %eax
; X64SSE2-NEXT: retq
;
; X86SSE2-LABEL: pr38738:
; X86SSE2: # %bb.0: # %entry
; X86SSE2-NEXT: subl $44, %esp
; X86SSE2-NEXT: .cfi_def_cfa_offset 48
; X86SSE2-NEXT: xorps %xmm0, %xmm0
; X86SSE2-NEXT: movaps %xmm0, {{[0-9]+}}(%esp)
; X86SSE2-NEXT: movl $0, {{[0-9]+}}(%esp)
; X86SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86SSE2-NEXT: addl $44, %esp
; X86SSE2-NEXT: .cfi_def_cfa_offset 4
; X86SSE2-NEXT: retl
;
; X64AVX-LABEL: pr38738:
; X64AVX: # %bb.0: # %entry
; X64AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; X64AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; X64AVX-NEXT: movl $0, -{{[0-9]+}}(%rsp)
; X64AVX-NEXT: movl -{{[0-9]+}}(%rsp), %eax
; X64AVX-NEXT: retq
;
; X86AVX-LABEL: pr38738:
; X86AVX: # %bb.0: # %entry
; X86AVX-NEXT: subl $44, %esp
; X86AVX-NEXT: .cfi_def_cfa_offset 48
; X86AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; X86AVX-NEXT: vmovaps %xmm0, {{[0-9]+}}(%esp)
; X86AVX-NEXT: movl $0, {{[0-9]+}}(%esp)
; X86AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86AVX-NEXT: addl $44, %esp
; X86AVX-NEXT: .cfi_def_cfa_offset 4
; X86AVX-NEXT: retl
entry:
%retval = alloca i32, align 4
%dlg_sys_param = alloca %struct.params, align 8
%total_active_bw = alloca float, align 4
%0 = bitcast %struct.params* %dlg_sys_param to i8*
call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 16, i1 false)
store float 0.000000e+00, float* %total_active_bw, align 4
%1 = load i32, i32* %retval, align 4
ret i32 %1
}
define void @tryset(i8* nocapture %x) {
; X64SSE-LABEL: tryset:
; X64SSE: # %bb.0:
; X64SSE-NEXT: movq $0, 56(%rdi)
; X64SSE-NEXT: movq $0, 48(%rdi)
; X64SSE-NEXT: movq $0, 40(%rdi)
; X64SSE-NEXT: movq $0, 32(%rdi)
; X64SSE-NEXT: movq $0, 24(%rdi)
; X64SSE-NEXT: movq $0, 16(%rdi)
; X64SSE-NEXT: movq $0, 8(%rdi)
; X64SSE-NEXT: movq $0, (%rdi)
; X64SSE-NEXT: retq
;
; X86SSE-LABEL: tryset:
; X86SSE: # %bb.0:
; X86SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86SSE-NEXT: movl $0, 60(%eax)
; X86SSE-NEXT: movl $0, 56(%eax)
; X86SSE-NEXT: movl $0, 52(%eax)
; X86SSE-NEXT: movl $0, 48(%eax)
; X86SSE-NEXT: movl $0, 44(%eax)
; X86SSE-NEXT: movl $0, 40(%eax)
; X86SSE-NEXT: movl $0, 36(%eax)
; X86SSE-NEXT: movl $0, 32(%eax)
; X86SSE-NEXT: movl $0, 28(%eax)
; X86SSE-NEXT: movl $0, 24(%eax)
; X86SSE-NEXT: movl $0, 20(%eax)
; X86SSE-NEXT: movl $0, 16(%eax)
; X86SSE-NEXT: movl $0, 12(%eax)
; X86SSE-NEXT: movl $0, 8(%eax)
; X86SSE-NEXT: movl $0, 4(%eax)
; X86SSE-NEXT: movl $0, (%eax)
; X86SSE-NEXT: retl
;
; X64SSE2-LABEL: tryset:
; X64SSE2: # %bb.0:
; X64SSE2-NEXT: movq $0, 56(%rdi)
; X64SSE2-NEXT: movq $0, 48(%rdi)
; X64SSE2-NEXT: movq $0, 40(%rdi)
; X64SSE2-NEXT: movq $0, 32(%rdi)
; X64SSE2-NEXT: movq $0, 24(%rdi)
; X64SSE2-NEXT: movq $0, 16(%rdi)
; X64SSE2-NEXT: movq $0, 8(%rdi)
; X64SSE2-NEXT: movq $0, (%rdi)
; X64SSE2-NEXT: retq
;
; X86SSE2-LABEL: tryset:
; X86SSE2: # %bb.0:
; X86SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86SSE2-NEXT: movl $0, 4(%eax)
; X86SSE2-NEXT: movl $0, (%eax)
; X86SSE2-NEXT: movl $0, 12(%eax)
; X86SSE2-NEXT: movl $0, 8(%eax)
; X86SSE2-NEXT: movl $0, 20(%eax)
; X86SSE2-NEXT: movl $0, 16(%eax)
; X86SSE2-NEXT: movl $0, 28(%eax)
; X86SSE2-NEXT: movl $0, 24(%eax)
; X86SSE2-NEXT: movl $0, 36(%eax)
; X86SSE2-NEXT: movl $0, 32(%eax)
; X86SSE2-NEXT: movl $0, 44(%eax)
; X86SSE2-NEXT: movl $0, 40(%eax)
; X86SSE2-NEXT: movl $0, 52(%eax)
; X86SSE2-NEXT: movl $0, 48(%eax)
; X86SSE2-NEXT: movl $0, 60(%eax)
; X86SSE2-NEXT: movl $0, 56(%eax)
; X86SSE2-NEXT: retl
;
; X64AVX-LABEL: tryset:
; X64AVX: # %bb.0:
; X64AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; X64AVX-NEXT: vmovups %ymm0, 32(%rdi)
; X64AVX-NEXT: vmovups %ymm0, (%rdi)
; X64AVX-NEXT: vzeroupper
; X64AVX-NEXT: retq
;
; X86AVX-LABEL: tryset:
; X86AVX: # %bb.0:
; X86AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; X86AVX-NEXT: vmovups %ymm0, 32(%eax)
; X86AVX-NEXT: vmovups %ymm0, (%eax)
; X86AVX-NEXT: vzeroupper
; X86AVX-NEXT: retl
tail call void @llvm.memset.p0i8.i64(i8* align 1 %x, i8 0, i64 64, i1 false)
ret void
}
define void @trycpy(i8* nocapture %x, i8* nocapture readonly %y) {
; X64SSE-LABEL: trycpy:
; X64SSE: # %bb.0:
; X64SSE-NEXT: movq 24(%rsi), %rax
; X64SSE-NEXT: movq %rax, 24(%rdi)
; X64SSE-NEXT: movq 16(%rsi), %rax
; X64SSE-NEXT: movq %rax, 16(%rdi)
; X64SSE-NEXT: movq (%rsi), %rax
; X64SSE-NEXT: movq 8(%rsi), %rcx
; X64SSE-NEXT: movq %rcx, 8(%rdi)
; X64SSE-NEXT: movq %rax, (%rdi)
; X64SSE-NEXT: retq
;
; X86SSE-LABEL: trycpy:
; X86SSE: # %bb.0:
; X86SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86SSE-NEXT: movl 28(%ecx), %edx
; X86SSE-NEXT: movl %edx, 28(%eax)
; X86SSE-NEXT: movl 24(%ecx), %edx
; X86SSE-NEXT: movl %edx, 24(%eax)
; X86SSE-NEXT: movl 20(%ecx), %edx
; X86SSE-NEXT: movl %edx, 20(%eax)
; X86SSE-NEXT: movl 16(%ecx), %edx
; X86SSE-NEXT: movl %edx, 16(%eax)
; X86SSE-NEXT: movl 12(%ecx), %edx
; X86SSE-NEXT: movl %edx, 12(%eax)
; X86SSE-NEXT: movl 8(%ecx), %edx
; X86SSE-NEXT: movl %edx, 8(%eax)
; X86SSE-NEXT: movl (%ecx), %edx
; X86SSE-NEXT: movl 4(%ecx), %ecx
; X86SSE-NEXT: movl %ecx, 4(%eax)
; X86SSE-NEXT: movl %edx, (%eax)
; X86SSE-NEXT: retl
;
; X64SSE2-LABEL: trycpy:
; X64SSE2: # %bb.0:
; X64SSE2-NEXT: movq 24(%rsi), %rax
; X64SSE2-NEXT: movq %rax, 24(%rdi)
; X64SSE2-NEXT: movq 16(%rsi), %rax
; X64SSE2-NEXT: movq %rax, 16(%rdi)
; X64SSE2-NEXT: movq (%rsi), %rax
; X64SSE2-NEXT: movq 8(%rsi), %rcx
; X64SSE2-NEXT: movq %rcx, 8(%rdi)
; X64SSE2-NEXT: movq %rax, (%rdi)
; X64SSE2-NEXT: retq
;
; X86SSE2-LABEL: trycpy:
; X86SSE2: # %bb.0:
; X86SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86SSE2-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86SSE2-NEXT: movsd %xmm0, 24(%eax)
; X86SSE2-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86SSE2-NEXT: movsd %xmm0, 16(%eax)
; X86SSE2-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86SSE2-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; X86SSE2-NEXT: movsd %xmm1, 8(%eax)
; X86SSE2-NEXT: movsd %xmm0, (%eax)
; X86SSE2-NEXT: retl
;
; X64AVX-LABEL: trycpy:
; X64AVX: # %bb.0:
; X64AVX-NEXT: vmovups (%rsi), %ymm0
; X64AVX-NEXT: vmovups %ymm0, (%rdi)
; X64AVX-NEXT: vzeroupper
; X64AVX-NEXT: retq
;
; X86AVX-LABEL: trycpy:
; X86AVX: # %bb.0:
; X86AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86AVX-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86AVX-NEXT: vmovups (%ecx), %ymm0
; X86AVX-NEXT: vmovups %ymm0, (%eax)
; X86AVX-NEXT: vzeroupper
; X86AVX-NEXT: retl
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %x, i8* align 1 %y, i64 32, i1 false)
ret void
}
declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) argmemonly nounwind
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #2