forked from OSchip/llvm-project
71 lines
3.7 KiB
LLVM
71 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=skx --show-mc-encoding | FileCheck %s
|
|
|
|
define i32 @f256(<8 x float> %A, <8 x float> %AA, i8* %B, <4 x double> %C, <4 x double> %CC, i32 %D, <4 x i64> %E, <4 x i64> %EE, i32* %loadptr) {
|
|
; CHECK-LABEL: f256:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: movl (%rdx), %eax ## encoding: [0x8b,0x02]
|
|
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfc,0x58,0xc1]
|
|
; CHECK-NEXT: vmovntps %ymm0, (%rdi) ## EVEX TO VEX Compression encoding: [0xc5,0xfc,0x2b,0x07]
|
|
; CHECK-NEXT: vpaddq %ymm5, %ymm4, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xdd,0xd4,0xc5]
|
|
; CHECK-NEXT: addl (%rdx), %eax ## encoding: [0x03,0x02]
|
|
; CHECK-NEXT: vmovntdq %ymm0, (%rdi) ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe7,0x07]
|
|
; CHECK-NEXT: vaddpd %ymm3, %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xed,0x58,0xc3]
|
|
; CHECK-NEXT: addl (%rdx), %eax ## encoding: [0x03,0x02]
|
|
; CHECK-NEXT: vmovntpd %ymm0, (%rdi) ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x2b,0x07]
|
|
; CHECK-NEXT: addl (%rdx), %eax ## encoding: [0x03,0x02]
|
|
; CHECK-NEXT: vzeroupper ## encoding: [0xc5,0xf8,0x77]
|
|
; CHECK-NEXT: retq ## encoding: [0xc3]
|
|
%v0 = load i32, i32* %loadptr, align 1
|
|
%cast = bitcast i8* %B to <8 x float>*
|
|
%A2 = fadd <8 x float> %A, %AA
|
|
store <8 x float> %A2, <8 x float>* %cast, align 64, !nontemporal !0
|
|
%v1 = load i32, i32* %loadptr, align 1
|
|
%cast1 = bitcast i8* %B to <4 x i64>*
|
|
%E2 = add <4 x i64> %E, %EE
|
|
store <4 x i64> %E2, <4 x i64>* %cast1, align 64, !nontemporal !0
|
|
%v2 = load i32, i32* %loadptr, align 1
|
|
%cast2 = bitcast i8* %B to <4 x double>*
|
|
%C2 = fadd <4 x double> %C, %CC
|
|
store <4 x double> %C2, <4 x double>* %cast2, align 64, !nontemporal !0
|
|
%v3 = load i32, i32* %loadptr, align 1
|
|
%sum1 = add i32 %v0, %v1
|
|
%sum2 = add i32 %sum1, %v2
|
|
%sum3 = add i32 %sum2, %v3
|
|
ret i32 %sum3
|
|
}
|
|
|
|
define i32 @f128(<4 x float> %A, <4 x float> %AA, i8* %B, <2 x double> %C, <2 x double> %CC, i32 %D, <2 x i64> %E, <2 x i64> %EE, i32* %loadptr) {
|
|
; CHECK-LABEL: f128:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: movl (%rdx), %eax ## encoding: [0x8b,0x02]
|
|
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf8,0x58,0xc1]
|
|
; CHECK-NEXT: vmovntps %xmm0, (%rdi) ## EVEX TO VEX Compression encoding: [0xc5,0xf8,0x2b,0x07]
|
|
; CHECK-NEXT: vpaddq %xmm5, %xmm4, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xd9,0xd4,0xc5]
|
|
; CHECK-NEXT: addl (%rdx), %eax ## encoding: [0x03,0x02]
|
|
; CHECK-NEXT: vmovntdq %xmm0, (%rdi) ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0xe7,0x07]
|
|
; CHECK-NEXT: vaddpd %xmm3, %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xe9,0x58,0xc3]
|
|
; CHECK-NEXT: addl (%rdx), %eax ## encoding: [0x03,0x02]
|
|
; CHECK-NEXT: vmovntpd %xmm0, (%rdi) ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x2b,0x07]
|
|
; CHECK-NEXT: addl (%rdx), %eax ## encoding: [0x03,0x02]
|
|
; CHECK-NEXT: retq ## encoding: [0xc3]
|
|
%v0 = load i32, i32* %loadptr, align 1
|
|
%cast = bitcast i8* %B to <4 x float>*
|
|
%A2 = fadd <4 x float> %A, %AA
|
|
store <4 x float> %A2, <4 x float>* %cast, align 64, !nontemporal !0
|
|
%v1 = load i32, i32* %loadptr, align 1
|
|
%cast1 = bitcast i8* %B to <2 x i64>*
|
|
%E2 = add <2 x i64> %E, %EE
|
|
store <2 x i64> %E2, <2 x i64>* %cast1, align 64, !nontemporal !0
|
|
%v2 = load i32, i32* %loadptr, align 1
|
|
%cast2 = bitcast i8* %B to <2 x double>*
|
|
%C2 = fadd <2 x double> %C, %CC
|
|
store <2 x double> %C2, <2 x double>* %cast2, align 64, !nontemporal !0
|
|
%v3 = load i32, i32* %loadptr, align 1
|
|
%sum1 = add i32 %v0, %v1
|
|
%sum2 = add i32 %sum1, %v2
|
|
%sum3 = add i32 %sum2, %v3
|
|
ret i32 %sum3
|
|
}
|
|
!0 = !{i32 1}
|