forked from OSchip/llvm-project
[x86] NFC Add some more shuffle-vs-trunc tests
These are related to: https://reviews.llvm.org/D46957 llvm-svn: 332962
This commit is contained in:
Gabor Buella
parent
f163bdc07e
commit
e96c488aa7
|
|
@ -479,6 +479,592 @@ define void @trunc_v8i32_to_v8i8(<32 x i8>* %L, <8 x i8>* %S) nounwind {
|
|||
ret void
|
||||
}
|
||||
|
||||
define <2 x i64> @trunc_v8i32_to_v8i8_return_v2i64(<8 x i32> %vec) nounwind {
|
||||
; IR generated from:
|
||||
; return (__m128i) {(long long)__builtin_convertvector((__v8si)__A, __v8qi), 0};
|
||||
; AVX1-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated.vec = trunc <8 x i32> %vec to <8 x i8>
|
||||
%bc = bitcast <8 x i8> %truncated.vec to i64
|
||||
%result = insertelement <2 x i64> zeroinitializer, i64 %bc, i32 0
|
||||
ret <2 x i64> %result
|
||||
}
|
||||
|
||||
define <16 x i8> @trunc_v8i32_to_v8i8_with_zext_return_v16i8(<8 x i32> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <8 x i32> %vec to <8 x i8>
|
||||
%truncated.ext = zext <8 x i8> %truncated to <8 x i16>
|
||||
%bc = bitcast <8 x i16> %truncated.ext to <16 x i8>
|
||||
%result = shufflevector <16 x i8> %bc, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
||||
ret <16 x i8> %result
|
||||
}
|
||||
|
||||
define <16 x i8> @trunc_v8i32_to_v8i8_via_v8i16_return_v16i8(<8 x i32> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <8 x i32> %vec to <8 x i16>
|
||||
%bc = bitcast <8 x i16> %truncated to <16 x i8>
|
||||
%result = shufflevector <16 x i8> %bc, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 17, i32 20, i32 24, i32 22, i32 31, i32 28, i32 28, i32 29>
|
||||
ret <16 x i8> %result
|
||||
}
|
||||
|
||||
define <16 x i8> @trunc_v8i32_to_v8i8_return_v16i8(<8 x i32> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <8 x i32> %vec to <8 x i8>
|
||||
%result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 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>
|
||||
ret <16 x i8> %result
|
||||
}
|
||||
|
||||
define <2 x i64> @trunc_v4i64_to_v4i16_return_v2i64(<4 x i64> %vec) nounwind {
|
||||
; IR generated from:
|
||||
; return (__m128i) {(long long)__builtin_convertvector((__v4di)x, __v4hi), 0};
|
||||
; AVX1-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX2-FAST: # %bb.0:
|
||||
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i16>
|
||||
%bc = bitcast <4 x i16> %truncated to i64
|
||||
%result = insertelement <2 x i64> zeroinitializer, i64 %bc, i32 0
|
||||
ret <2 x i64> %result
|
||||
}
|
||||
|
||||
define <8 x i16> @trunc_v4i64_to_v4i16_with_zext_return_v8i16(<4 x i64> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX2-FAST: # %bb.0:
|
||||
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i16>
|
||||
%truncated.ext = zext <4 x i16> %truncated to <4 x i32>
|
||||
%bc = bitcast <4 x i32> %truncated.ext to <8 x i16>
|
||||
%result = shufflevector <8 x i16> %bc, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
|
||||
ret <8 x i16> %result
|
||||
}
|
||||
|
||||
define <8 x i16> @trunc_v4i64_to_v4i16_via_v4i32_return_v8i16(<4 x i64> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX2-FAST: # %bb.0:
|
||||
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i32>
|
||||
%bc = bitcast <4 x i32> %truncated to <8 x i16>
|
||||
%result = shufflevector <8 x i16> %bc, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 8, i32 undef, i32 13>
|
||||
ret <8 x i16> %result
|
||||
}
|
||||
|
||||
define <8 x i16> @trunc_v4i64_to_v4i16_return_v8i16(<4 x i64> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX2-FAST: # %bb.0:
|
||||
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i16>
|
||||
%result = shufflevector <4 x i16> %truncated, <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
ret <8 x i16> %result
|
||||
}
|
||||
|
||||
define <16 x i8> @trunc_v4i64_to_v4i8_return_v16i8(<4 x i64> %vec) nounwind {
|
||||
; AVX1-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX2-FAST: # %bb.0:
|
||||
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i8>
|
||||
%result = shufflevector <4 x i8> %truncated, <4 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7, i32 5, i32 5, i32 undef, i32 7>
|
||||
ret <16 x i8> %result
|
||||
}
|
||||
|
||||
define void @shuffle_v16i16_to_v4i16(<16 x i16>* %L, <4 x i16>* %S) nounwind {
|
||||
; AVX1-LABEL: shuffle_v16i16_to_v4i16:
|
||||
; AVX1: # %bb.0:
|
||||
|
|
|
|||
|
|
@ -941,3 +941,16 @@ define <4 x double> @PR34175(<32 x i16>* %p) {
|
|||
%tofp = uitofp <4 x i16> %shuf to <4 x double>
|
||||
ret <4 x double> %tofp
|
||||
}
|
||||
|
||||
define <16 x i8> @trunc_v8i64_to_v8i8_return_v16i8(<8 x i64> %vec) nounwind {
|
||||
; AVX512-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%truncated = trunc <8 x i64> %vec to <8 x i8>
|
||||
%result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 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>
|
||||
ret <16 x i8> %result
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue