maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/avx512vbmivl-intrinsics-fas...

189 lines
7.3 KiB
LLVM
Raw Normal View History

[X86] Add unmasked vermi2var intrinsics so we can use explicit select instructions for masking in clang. This will allow us to remove the 3 different flavors of masked intrinsics. I'm leaving the actual intrinsic removal for another patch. llvm-svn: 333386
2018-05-29 11:26:30 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -fast-isel -mtriple=i386-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=X32
; RUN: llc < %s -fast-isel -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=X64
[X86] Add fast-isel tests for avx512vbmi2 instructions. llvm-svn: 333794
2018-06-02 05:59:22 +08:00
; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/avx512vlvbmi-builtins.c
[X86] Add unmasked vermi2var intrinsics so we can use explicit select instructions for masking in clang. This will allow us to remove the 3 different flavors of masked intrinsics. I'm leaving the actual intrinsic removal for another patch. llvm-svn: 333386
2018-05-29 11:26:30 +08:00
define <2 x i64> @test_mm_mask2_permutex2var_epi8(<2 x i64> %__A, <2 x i64> %__I, i16 zeroext %__U, <2 x i64> %__B) {
; X32-LABEL: test_mm_mask2_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X32-NEXT: vpermi2b %xmm2, %xmm0, %xmm1 {%k1}
; X32-NEXT: vmovdqa %xmm1, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: test_mm_mask2_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: kmovd %edi, %k1
; X64-NEXT: vpermi2b %xmm2, %xmm0, %xmm1 {%k1}
; X64-NEXT: vmovdqa %xmm1, %xmm0
; X64-NEXT: retq
entry:
%0 = bitcast <2 x i64> %__A to <16 x i8>
%1 = bitcast <2 x i64> %__I to <16 x i8>
%2 = bitcast <2 x i64> %__B to <16 x i8>
%3 = tail call <16 x i8> @llvm.x86.avx512.vpermi2var.qi.128(<16 x i8> %0, <16 x i8> %1, <16 x i8> %2)
%4 = bitcast i16 %__U to <16 x i1>
%5 = select <16 x i1> %4, <16 x i8> %3, <16 x i8> %1
%6 = bitcast <16 x i8> %5 to <2 x i64>
ret <2 x i64> %6
}
define <4 x i64> @test_mm256_mask2_permutex2var_epi8(<4 x i64> %__A, <4 x i64> %__I, i32 %__U, <4 x i64> %__B) {
; X32-LABEL: test_mm256_mask2_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; X32-NEXT: vpermi2b %ymm2, %ymm0, %ymm1 {%k1}
; X32-NEXT: vmovdqa %ymm1, %ymm0
; X32-NEXT: retl
;
; X64-LABEL: test_mm256_mask2_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: kmovd %edi, %k1
; X64-NEXT: vpermi2b %ymm2, %ymm0, %ymm1 {%k1}
; X64-NEXT: vmovdqa %ymm1, %ymm0
; X64-NEXT: retq
entry:
%0 = bitcast <4 x i64> %__A to <32 x i8>
%1 = bitcast <4 x i64> %__I to <32 x i8>
%2 = bitcast <4 x i64> %__B to <32 x i8>
%3 = tail call <32 x i8> @llvm.x86.avx512.vpermi2var.qi.256(<32 x i8> %0, <32 x i8> %1, <32 x i8> %2)
%4 = bitcast i32 %__U to <32 x i1>
%5 = select <32 x i1> %4, <32 x i8> %3, <32 x i8> %1
%6 = bitcast <32 x i8> %5 to <4 x i64>
ret <4 x i64> %6
}
define <2 x i64> @test_mm_permutex2var_epi8(<2 x i64> %__A, <2 x i64> %__I, <2 x i64> %__B) {
; X32-LABEL: test_mm_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: vpermt2b %xmm2, %xmm1, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: test_mm_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: vpermt2b %xmm2, %xmm1, %xmm0
; X64-NEXT: retq
entry:
%0 = bitcast <2 x i64> %__A to <16 x i8>
%1 = bitcast <2 x i64> %__I to <16 x i8>
%2 = bitcast <2 x i64> %__B to <16 x i8>
%3 = tail call <16 x i8> @llvm.x86.avx512.vpermi2var.qi.128(<16 x i8> %0, <16 x i8> %1, <16 x i8> %2)
%4 = bitcast <16 x i8> %3 to <2 x i64>
ret <2 x i64> %4
}
define <2 x i64> @test_mm_mask_permutex2var_epi8(<2 x i64> %__A, i16 zeroext %__U, <2 x i64> %__I, <2 x i64> %__B) {
; X32-LABEL: test_mm_mask_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X32-NEXT: vpermt2b %xmm2, %xmm1, %xmm0 {%k1}
; X32-NEXT: retl
;
; X64-LABEL: test_mm_mask_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: kmovd %edi, %k1
; X64-NEXT: vpermt2b %xmm2, %xmm1, %xmm0 {%k1}
; X64-NEXT: retq
entry:
%0 = bitcast <2 x i64> %__A to <16 x i8>
%1 = bitcast <2 x i64> %__I to <16 x i8>
%2 = bitcast <2 x i64> %__B to <16 x i8>
%3 = tail call <16 x i8> @llvm.x86.avx512.vpermi2var.qi.128(<16 x i8> %0, <16 x i8> %1, <16 x i8> %2)
%4 = bitcast i16 %__U to <16 x i1>
%5 = select <16 x i1> %4, <16 x i8> %3, <16 x i8> %0
%6 = bitcast <16 x i8> %5 to <2 x i64>
ret <2 x i64> %6
}
define <2 x i64> @test_mm_maskz_permutex2var_epi8(i16 zeroext %__U, <2 x i64> %__A, <2 x i64> %__I, <2 x i64> %__B) {
; X32-LABEL: test_mm_maskz_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X32-NEXT: vpermt2b %xmm2, %xmm1, %xmm0 {%k1} {z}
; X32-NEXT: retl
;
; X64-LABEL: test_mm_maskz_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: kmovd %edi, %k1
; X64-NEXT: vpermt2b %xmm2, %xmm1, %xmm0 {%k1} {z}
; X64-NEXT: retq
entry:
%0 = bitcast <2 x i64> %__A to <16 x i8>
%1 = bitcast <2 x i64> %__I to <16 x i8>
%2 = bitcast <2 x i64> %__B to <16 x i8>
%3 = tail call <16 x i8> @llvm.x86.avx512.vpermi2var.qi.128(<16 x i8> %0, <16 x i8> %1, <16 x i8> %2)
%4 = bitcast i16 %__U to <16 x i1>
%5 = select <16 x i1> %4, <16 x i8> %3, <16 x i8> zeroinitializer
%6 = bitcast <16 x i8> %5 to <2 x i64>
ret <2 x i64> %6
}
define <4 x i64> @test_mm256_permutex2var_epi8(<4 x i64> %__A, <4 x i64> %__I, <4 x i64> %__B) {
; X32-LABEL: test_mm256_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: vpermt2b %ymm2, %ymm1, %ymm0
; X32-NEXT: retl
;
; X64-LABEL: test_mm256_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: vpermt2b %ymm2, %ymm1, %ymm0
; X64-NEXT: retq
entry:
%0 = bitcast <4 x i64> %__A to <32 x i8>
%1 = bitcast <4 x i64> %__I to <32 x i8>
%2 = bitcast <4 x i64> %__B to <32 x i8>
%3 = tail call <32 x i8> @llvm.x86.avx512.vpermi2var.qi.256(<32 x i8> %0, <32 x i8> %1, <32 x i8> %2)
%4 = bitcast <32 x i8> %3 to <4 x i64>
ret <4 x i64> %4
}
define <4 x i64> @test_mm256_mask_permutex2var_epi8(<4 x i64> %__A, i32 %__U, <4 x i64> %__I, <4 x i64> %__B) {
; X32-LABEL: test_mm256_mask_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; X32-NEXT: vpermt2b %ymm2, %ymm1, %ymm0 {%k1}
; X32-NEXT: retl
;
; X64-LABEL: test_mm256_mask_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: kmovd %edi, %k1
; X64-NEXT: vpermt2b %ymm2, %ymm1, %ymm0 {%k1}
; X64-NEXT: retq
entry:
%0 = bitcast <4 x i64> %__A to <32 x i8>
%1 = bitcast <4 x i64> %__I to <32 x i8>
%2 = bitcast <4 x i64> %__B to <32 x i8>
%3 = tail call <32 x i8> @llvm.x86.avx512.vpermi2var.qi.256(<32 x i8> %0, <32 x i8> %1, <32 x i8> %2)
%4 = bitcast i32 %__U to <32 x i1>
%5 = select <32 x i1> %4, <32 x i8> %3, <32 x i8> %0
%6 = bitcast <32 x i8> %5 to <4 x i64>
ret <4 x i64> %6
}
define <4 x i64> @test_mm256_maskz_permutex2var_epi8(i32 %__U, <4 x i64> %__A, <4 x i64> %__I, <4 x i64> %__B) {
; X32-LABEL: test_mm256_maskz_permutex2var_epi8:
; X32: # %bb.0: # %entry
; X32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; X32-NEXT: vpermt2b %ymm2, %ymm1, %ymm0 {%k1} {z}
; X32-NEXT: retl
;
; X64-LABEL: test_mm256_maskz_permutex2var_epi8:
; X64: # %bb.0: # %entry
; X64-NEXT: kmovd %edi, %k1
; X64-NEXT: vpermt2b %ymm2, %ymm1, %ymm0 {%k1} {z}
; X64-NEXT: retq
entry:
%0 = bitcast <4 x i64> %__A to <32 x i8>
%1 = bitcast <4 x i64> %__I to <32 x i8>
%2 = bitcast <4 x i64> %__B to <32 x i8>
%3 = tail call <32 x i8> @llvm.x86.avx512.vpermi2var.qi.256(<32 x i8> %0, <32 x i8> %1, <32 x i8> %2)
%4 = bitcast i32 %__U to <32 x i1>
%5 = select <32 x i1> %4, <32 x i8> %3, <32 x i8> zeroinitializer
%6 = bitcast <32 x i8> %5 to <4 x i64>
ret <4 x i64> %6
}
declare <16 x i8> @llvm.x86.avx512.vpermi2var.qi.128(<16 x i8>, <16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.x86.avx512.vpermi2var.qi.256(<32 x i8>, <32 x i8>, <32 x i8>)