forked from OSchip/llvm-project
43 lines
2.8 KiB
LLVM
43 lines
2.8 KiB
LLVM
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512vl -mattr=+avx512vbmi --show-mc-encoding| FileCheck %s
|
||
|
|
|
||
|
|
declare <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8>, <16 x i8>, <16 x i8>, i16)
|
||
|
|
|
||
|
|
define <16 x i8>@test_int_x86_avx512_mask_permvar_qi_128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8> %x2, i16 %x3) {
|
||
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_permvar_qi_128:
|
||
|
|
; CHECK: ## %bb.0:
|
||
|
|
; CHECK-NEXT: vpermb %xmm0, %xmm1, %xmm3 ## encoding: [0x62,0xf2,0x75,0x08,0x8d,0xd8]
|
||
|
|
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
|
||
|
|
; CHECK-NEXT: vpermb %xmm0, %xmm1, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x75,0x09,0x8d,0xd0]
|
||
|
|
; CHECK-NEXT: vpermb %xmm0, %xmm1, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x75,0x89,0x8d,0xc0]
|
||
|
|
; CHECK-NEXT: vpaddb %xmm3, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc3]
|
||
|
|
; CHECK-NEXT: vpaddb %xmm0, %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfc,0xc0]
|
||
|
|
; CHECK-NEXT: retq ## encoding: [0xc3]
|
||
|
|
%res = call <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8> %x2, i16 %x3)
|
||
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8> zeroinitializer, i16 %x3)
|
||
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8> %x2, i16 -1)
|
||
|
|
%res3 = add <16 x i8> %res, %res1
|
||
|
|
%res4 = add <16 x i8> %res3, %res2
|
||
|
|
ret <16 x i8> %res4
|
||
|
|
}
|
||
|
|
|
||
|
|
declare <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8>, <32 x i8>, <32 x i8>, i32)
|
||
|
|
|
||
|
|
define <32 x i8>@test_int_x86_avx512_mask_permvar_qi_256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8> %x2, i32 %x3) {
|
||
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_permvar_qi_256:
|
||
|
|
; CHECK: ## %bb.0:
|
||
|
|
; CHECK-NEXT: vpermb %ymm0, %ymm1, %ymm3 ## encoding: [0x62,0xf2,0x75,0x28,0x8d,0xd8]
|
||
|
|
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
|
||
|
|
; CHECK-NEXT: vpermb %ymm0, %ymm1, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x75,0x29,0x8d,0xd0]
|
||
|
|
; CHECK-NEXT: vpermb %ymm0, %ymm1, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x75,0xa9,0x8d,0xc0]
|
||
|
|
; CHECK-NEXT: vpaddb %ymm3, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfc,0xc3]
|
||
|
|
; CHECK-NEXT: vpaddb %ymm0, %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xed,0xfc,0xc0]
|
||
|
|
; CHECK-NEXT: retq ## encoding: [0xc3]
|
||
|
|
%res = call <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8> %x2, i32 %x3)
|
||
|
|
%res1 = call <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8> zeroinitializer, i32 %x3)
|
||
|
|
%res2 = call <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8> %x2, i32 -1)
|
||
|
|
%res3 = add <32 x i8> %res, %res1
|
||
|
|
%res4 = add <32 x i8> %res3, %res2
|
||
|
|
ret <32 x i8> %res4
|
||
|
|
}
|