maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][AVX] Truncate vectors with PACKSS/PACKUS on AVX2 targets 

Until AVX512 we don't have any vector truncation instructions, and always lower using shuffles instead.

combineVectorTruncation performs this earlier than lowering as it makes it easier to use any sign/zero-extended bits in the truncated bits with PACKSS/PACKUS to perform the shuffle.

We currently don't attempt to use combineVectorTruncation on AVX2 targets as in the past 256-bit PACKSS/PACKUS tended to cause 128-bit lane shuffle regressions - but these should now be all resolved with combineHorizOpWithShuffle and in all cases we now reduce the amount of cross-lane shuffling and variable shuffle mask usage.

Differential Revision: https://reviews.llvm.org/D96609
This commit is contained in:
Simon Pilgrim 2021-03-25 10:34:34 +00:00
parent 9fde88c3e2
commit 36e3c6c841
8 changed files with 552 additions and 1080 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -46145,10 +46145,8 @@ static SDValue combineVectorTruncation(SDNode *N, SelectionDAG &DAG,
EVT InVT = In.getValueType();
unsigned NumElems = OutVT.getVectorNumElements();
// TODO: On AVX2, the behavior of X86ISD::PACKUS is different from that on
// SSE2, and we need to take care of it specially.
// AVX512 provides vpmovdb.
if (!Subtarget.hasSSE2() || Subtarget.hasAVX2())
// AVX512 provides fast truncate ops.
if (!Subtarget.hasSSE2() || Subtarget.hasAVX512())
return SDValue();
EVT OutSVT = OutVT.getVectorElementType();

56
llvm/test/CodeGen/X86/masked_store_trunc.ll
View File

@ -453,11 +453,12 @@ define void @truncstore_v8i64_v8i16(<8 x i64> %x, <8 x i16>* %p, <8 x i32> %mask
; AVX2-LABEL: truncstore_v8i64_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm0[2,3],ymm1[2,3]
; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm4[0,2],ymm0[4,6],ymm4[4,6]
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,u,u,u,u,16,17,20,21,24,25,28,29,u,u,u,u,u,u,u,u]
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm3[1,2,3],ymm1[4],ymm3[5,6,7],ymm1[8],ymm3[9,10,11],ymm1[12],ymm3[13,14,15]
; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm3[1,2,3],ymm0[4],ymm3[5,6,7],ymm0[8],ymm3[9,10,11],ymm0[12],ymm3[13,14,15]
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm1
; AVX2-NEXT: vmovmskps %ymm1, %eax
; AVX2-NEXT: notl %eax
@ -841,17 +842,14 @@ define void @truncstore_v8i64_v8i8(<8 x i64> %x, <8 x i8>* %p, <8 x i32> %mask)
; AVX2-LABEL: truncstore_v8i64_v8i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm4
; AVX2-NEXT: vmovdqa {{.*#+}} xmm5 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm5, %xmm4, %xmm4
; AVX2-NEXT: vpshufb %xmm5, %xmm1, %xmm1
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm4
; AVX2-NEXT: vmovdqa {{.*#+}} xmm5 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm5, %xmm4, %xmm4
; AVX2-NEXT: vpshufb %xmm5, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm4 = [255,255,255,255]
; AVX2-NEXT: vpand %ymm4, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm4, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm1
; AVX2-NEXT: vmovmskps %ymm1, %eax
; AVX2-NEXT: notl %eax
@ -2365,12 +2363,10 @@ define void @truncstore_v16i32_v16i16(<16 x i32> %x, <16 x i16>* %p, <16 x i32>
; AVX2-LABEL: truncstore_v16i32_v16i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
; AVX2-NEXT: vmovdqa {{.*#+}} ymm5 = [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: vpshufb %ymm5, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb %ymm5, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm4[1],ymm1[2],ymm4[3],ymm1[4],ymm4[5],ymm1[6],ymm4[7],ymm1[8],ymm4[9],ymm1[10],ymm4[11],ymm1[12],ymm4[13],ymm1[14],ymm4[15]
; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm4[1],ymm0[2],ymm4[3],ymm0[4],ymm4[5],ymm0[6],ymm4[7],ymm0[8],ymm4[9],ymm0[10],ymm4[11],ymm0[12],ymm4[13],ymm0[14],ymm4[15]
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpcmpeqd %ymm4, %ymm3, %ymm1
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm3, %ymm3
; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm1
@ -3043,15 +3039,13 @@ define void @truncstore_v16i32_v16i8(<16 x i32> %x, <16 x i8>* %p, <16 x i32> %m
; AVX2-LABEL: truncstore_v16i32_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
; AVX2-NEXT: vmovdqa {{.*#+}} ymm5 = [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: vpshufb %ymm5, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm6 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm6, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm5, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm6, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm5 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm5, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm5, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vpcmpeqd %ymm4, %ymm3, %ymm1
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm3, %ymm3
; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm1
@ -5135,7 +5129,7 @@ define void @truncstore_v32i16_v32i8(<32 x i16> %x, <32 x i8>* %p, <32 x i8> %ma
; AVX2-LABEL: truncstore_v32i16_v32i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT: vmovdqa {{.*#+}} ymm4 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpbroadcastw {{.*#+}} ymm4 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm4, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm4, %ymm0, %ymm0
; AVX2-NEXT: vpackuswb %ymm1, %ymm0, %ymm0

14
llvm/test/CodeGen/X86/psubus.ll
View File

@ -702,15 +702,13 @@ define <16 x i8> @test14(<16 x i8> %x, <16 x i32> %y) nounwind {
; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm5
; AVX2-NEXT: vpackssdw %xmm5, %xmm3, %xmm3
; AVX2-NEXT: vpacksswb %xmm3, %xmm4, %xmm3
; AVX2-NEXT: vmovdqa {{.*#+}} ymm4 = [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: vpshufb %ymm4, %ymm2, %ymm2
; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %ymm4, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vpand %xmm5, %xmm1, %xmm1
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm4 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm4, %ymm2, %ymm2
; AVX2-NEXT: vpand %ymm4, %ymm1, %ymm1
; AVX2-NEXT: vpackusdw %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,1,3]
; AVX2-NEXT: vpsubb %xmm0, %xmm1, %xmm0
; AVX2-NEXT: vpandn %xmm0, %xmm3, %xmm0
; AVX2-NEXT: vzeroupper

16
llvm/test/CodeGen/X86/vector-reduce-and-bool.ll
View File

@ -650,15 +650,13 @@ define i1 @trunc_v16i32_v16i1(<16 x i32>) {
;
; AVX2-LABEL: trunc_v16i32_v16i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpw $-1, %ax
@ -711,7 +709,7 @@ define i1 @trunc_v32i16_v32i1(<32 x i16>) {
;
; AVX2-LABEL: trunc_v32i16_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpbroadcastw {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackuswb %ymm1, %ymm0, %ymm0

16
llvm/test/CodeGen/X86/vector-reduce-or-bool.ll
View File

@ -637,15 +637,13 @@ define i1 @trunc_v16i32_v16i1(<16 x i32>) {
;
; AVX2-LABEL: trunc_v16i32_v16i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: testw %ax, %ax
@ -698,7 +696,7 @@ define i1 @trunc_v32i16_v32i1(<32 x i16>) {
;
; AVX2-LABEL: trunc_v32i16_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpbroadcastw {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackuswb %ymm1, %ymm0, %ymm0

16
llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll
View File

@ -662,15 +662,13 @@ define i1 @trunc_v16i32_v16i1(<16 x i32>) {
;
; AVX2-LABEL: trunc_v16i32_v16i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: xorb %ah, %al
@ -750,7 +748,7 @@ define i1 @trunc_v32i16_v32i1(<32 x i16>) {
;
; AVX2-LABEL: trunc_v32i16_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpbroadcastw {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackuswb %ymm1, %ymm0, %ymm0

1427
llvm/test/CodeGen/X86/vector-trunc-math.ll
View File

File diff suppressed because it is too large Load Diff

81
llvm/test/CodeGen/X86/vector-trunc.ll
View File

@ -187,28 +187,17 @@ define <8 x i16> @trunc8i64_8i16(<8 x i64> %a) {
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc8i64_8i16:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,u,u,u,u,16,17,20,21,24,25,28,29,u,u,u,u,u,u,u,u]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i16:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,u,u,u,u,16,17,20,21,24,25,28,29,u,u,u,u,u,u,u,u]
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
; AVX2-LABEL: trunc8i64_8i16:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3],ymm1[4],ymm2[5,6,7],ymm1[8],ymm2[9,10,11],ymm1[12],ymm2[13,14,15]
; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5,6,7],ymm0[8],ymm2[9,10,11],ymm0[12],ymm2[13,14,15]
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i16:
; AVX512: # %bb.0: # %entry
@ -280,17 +269,14 @@ define void @trunc8i64_8i8(<8 x i64> %a) {
;
; AVX2-LABEL: trunc8i64_8i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vmovq %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
@ -676,13 +662,12 @@ define void @trunc16i32_16i16(<16 x i32> %a) {
;
; AVX2-LABEL: trunc16i32_16i16:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqu %xmm1, (%rax)
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm2[1],ymm1[2],ymm2[3],ymm1[4],ymm2[5],ymm1[6],ymm2[7],ymm1[8],ymm2[9],ymm1[10],ymm2[11],ymm1[12],ymm2[13],ymm1[14],ymm2[15]
; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm2[1],ymm0[2],ymm2[3],ymm0[4],ymm2[5],ymm0[6],ymm2[7],ymm0[8],ymm2[9],ymm0[10],ymm2[11],ymm0[12],ymm2[13],ymm0[14],ymm2[15]
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
@ -903,15 +888,13 @@ define void @trunc16i32_16i8(<16 x i32> %a) {
;
; AVX2-LABEL: trunc16i32_16i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
@ -1303,7 +1286,7 @@ define void @trunc32i16_32i8(<32 x i16> %a) {
;
; AVX2-LABEL: trunc32i16_32i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpbroadcastw {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackuswb %ymm1, %ymm0, %ymm0