mirror of
https://github.com/RPCS3/llvm.git
synced 2024-12-13 14:47:00 +00:00
ecb8fc414d
Demonstrate missing 128-bit wide shuffle combine support git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@268290 91177308-0d34-0410-b5e6-96231b3b80d8
42 lines
2.7 KiB
LLVM
42 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s
|
|
|
|
declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>)
|
|
declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>)
|
|
declare <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8>, <32 x i8>)
|
|
|
|
define <32 x i8> @combine_pshufb_vpermd(<8 x i32> %a) {
|
|
; CHECK-LABEL: combine_pshufb_vpermd:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,16,17,18,18]
|
|
; CHECK-NEXT: retq
|
|
%tmp0 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 4>)
|
|
%tmp1 = bitcast <8 x i32> %tmp0 to <32 x i8>
|
|
%tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 30>
|
|
ret <32 x i8> %tmp2
|
|
}
|
|
|
|
define <32 x i8> @combine_pshufb_vpermps(<8 x float> %a) {
|
|
; CHECK-LABEL: combine_pshufb_vpermps:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,16,17,18,18]
|
|
; CHECK-NEXT: retq
|
|
%tmp0 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 4>)
|
|
%tmp1 = bitcast <8 x float> %tmp0 to <32 x i8>
|
|
%tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 30>
|
|
ret <32 x i8> %tmp2
|
|
}
|
|
|
|
define <4 x i64> @combine_permq_pshufb(<4 x i64> %a0) {
|
|
; CHECK-LABEL: combine_permq_pshufb:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0]
|
|
; CHECK-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7,24,25,26,27,28,29,30,31,16,17,18,19,20,21,22,23]
|
|
; CHECK-NEXT: retq
|
|
%1 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
|
|
%2 = bitcast <4 x i64> %1 to <32 x i8>
|
|
%3 = call <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8> %2, <32 x i8> <i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>)
|
|
%4 = bitcast <32 x i8> %3 to <4 x i64>
|
|
ret <4 x i64> %4
|
|
}
|