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/vector-shuffle-combining-ss...

170 lines
8.6 KiB
LLVM
Raw Normal View History

[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx512f | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512F
;
; Combine tests involving SSE3/SSSE3 target shuffles (MOVDDUP, MOVSHDUP, MOVSLDUP, PSHUFB)
declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>)
[X86][SSE] Demonstrate issue with decoding shuffle masks that have been lowered as rematerialized constants on scalar unit Found whilst investigating PR27472 llvm-svn: 267339
2016-04-24 21:45:30 +08:00
define <16 x i8> @combine_vpshufb_zero(<16 x i8> %a0) {
; SSE-LABEL: combine_vpshufb_zero:
; SSE: # BB#0:
[X86][SSE] Improved support for decoding target shuffle masks through bitcasts Reused the ability to split constants of a type wider than the shuffle mask to work with masks generated from scalar constants transfered to xmm. This fixes an issue preventing PSHUFB target shuffle masks decoding rematerialized scalar constants and also exposes the XOP VPPERM bug described in PR27472. llvm-svn: 267343
2016-04-24 22:53:54 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
[X86][SSE] Demonstrate issue with decoding shuffle masks that have been lowered as rematerialized constants on scalar unit Found whilst investigating PR27472 llvm-svn: 267339
2016-04-24 21:45:30 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vpshufb_zero:
; AVX: # BB#0:
[X86][SSE] Improved support for decoding target shuffle masks through bitcasts Reused the ability to split constants of a type wider than the shuffle mask to work with masks generated from scalar constants transfered to xmm. This fixes an issue preventing PSHUFB target shuffle masks decoding rematerialized scalar constants and also exposes the XOP VPPERM bug described in PR27472. llvm-svn: 267343
2016-04-24 22:53:54 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
[X86][SSE] Demonstrate issue with decoding shuffle masks that have been lowered as rematerialized constants on scalar unit Found whilst investigating PR27472 llvm-svn: 267339
2016-04-24 21:45:30 +08:00
; AVX-NEXT: retq
%res0 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> <i8 128, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>)
%res1 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %res0, <16 x i8> <i8 0, i8 128, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>)
%res2 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %res1, <16 x i8> <i8 0, i8 1, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128>)
ret <16 x i8> %res2
}
[X86][SSSE3] Missing combine opportunity to simplify to a MOVQ shuffle llvm-svn: 268378
2016-05-03 21:12:44 +08:00
define <16 x i8> @combine_vpshufb_movq(<16 x i8> %a0) {
; SSE-LABEL: combine_vpshufb_movq:
; SSE: # BB#0:
[X86][SSE] Added target shuffle combine to MOVQ llvm-svn: 268391
2016-05-03 23:05:13 +08:00
; SSE-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
[X86][SSSE3] Missing combine opportunity to simplify to a MOVQ shuffle llvm-svn: 268378
2016-05-03 21:12:44 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vpshufb_movq:
; AVX: # BB#0:
[X86][SSE] Added target shuffle combine to MOVQ llvm-svn: 268391
2016-05-03 23:05:13 +08:00
; AVX-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
[X86][SSSE3] Missing combine opportunity to simplify to a MOVQ shuffle llvm-svn: 268378
2016-05-03 21:12:44 +08:00
; AVX-NEXT: retq
%res0 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> <i8 0, i8 128, i8 1, i8 128, i8 2, i8 128, i8 3, i8 128, i8 4, i8 128, i8 5, i8 128, i8 6, i8 128, i8 7, i8 128>)
%res1 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %res0, <16 x i8> <i8 0, i8 2, i8 4, i8 6, i8 8, i8 10, i8 12, i8 14, i8 1, i8 3, i8 5, i8 7, i8 9, i8 11, i8 13, i8 15>)
ret <16 x i8> %res1
}
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
define <4 x float> @combine_pshufb_movddup(<4 x float> %a0) {
; SSE-LABEL: combine_pshufb_movddup:
; SSE: # BB#0:
[X86][SSE3] Added combine support for MOVDDUP/MOVSHDUP/MOVSLDUP target shuffles Now that PerformShuffleCombine can handle unary shuffles. llvm-svn: 261843
2016-02-25 17:12:12 +08:00
; SSE-NEXT: pshufb {{.*#+}} xmm0 = xmm0[5,5,5,5,7,7,7,7,5,5,5,5,7,7,7,7]
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_pshufb_movddup:
; AVX: # BB#0:
[X86][SSE3] Added combine support for MOVDDUP/MOVSHDUP/MOVSLDUP target shuffles Now that PerformShuffleCombine can handle unary shuffles. llvm-svn: 261843
2016-02-25 17:12:12 +08:00
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[5,5,5,5,7,7,7,7,5,5,5,5,7,7,7,7]
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; AVX-NEXT: retq
%1 = bitcast <4 x float> %a0 to <16 x i8>
%2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 5, i8 5, i8 5, i8 5, i8 7, i8 7, i8 7, i8 7, i8 1, i8 1, i8 1, i8 1, i8 3, i8 3, i8 3, i8 3>)
%3 = bitcast <16 x i8> %2 to <4 x float>
%4 = shufflevector <4 x float> %3, <4 x float> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
ret <4 x float> %4
}
define <4 x float> @combine_pshufb_movshdup(<4 x float> %a0) {
; SSE-LABEL: combine_pshufb_movshdup:
; SSE: # BB#0:
[X86][SSE3] Added combine support for MOVDDUP/MOVSHDUP/MOVSLDUP target shuffles Now that PerformShuffleCombine can handle unary shuffles. llvm-svn: 261843
2016-02-25 17:12:12 +08:00
; SSE-NEXT: pshufb {{.*#+}} xmm0 = xmm0[7,7,7,7,7,7,7,7,3,3,3,3,3,3,3,3]
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_pshufb_movshdup:
; AVX: # BB#0:
[X86][SSE3] Added combine support for MOVDDUP/MOVSHDUP/MOVSLDUP target shuffles Now that PerformShuffleCombine can handle unary shuffles. llvm-svn: 261843
2016-02-25 17:12:12 +08:00
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[7,7,7,7,7,7,7,7,3,3,3,3,3,3,3,3]
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; AVX-NEXT: retq
%1 = bitcast <4 x float> %a0 to <16 x i8>
%2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 5, i8 5, i8 5, i8 5, i8 7, i8 7, i8 7, i8 7, i8 1, i8 1, i8 1, i8 1, i8 3, i8 3, i8 3, i8 3>)
%3 = bitcast <16 x i8> %2 to <4 x float>
%4 = shufflevector <4 x float> %3, <4 x float> undef, <4 x i32> <i32 1, i32 1, i32 3, i32 3>
ret <4 x float> %4
}
define <4 x float> @combine_pshufb_movsldup(<4 x float> %a0) {
; SSE-LABEL: combine_pshufb_movsldup:
; SSE: # BB#0:
[X86][SSE3] Added combine support for MOVDDUP/MOVSHDUP/MOVSLDUP target shuffles Now that PerformShuffleCombine can handle unary shuffles. llvm-svn: 261843
2016-02-25 17:12:12 +08:00
; SSE-NEXT: pshufb {{.*#+}} xmm0 = xmm0[5,5,5,5,5,5,5,5,1,1,1,1,1,1,1,1]
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_pshufb_movsldup:
; AVX: # BB#0:
[X86][SSE3] Added combine support for MOVDDUP/MOVSHDUP/MOVSLDUP target shuffles Now that PerformShuffleCombine can handle unary shuffles. llvm-svn: 261843
2016-02-25 17:12:12 +08:00
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[5,5,5,5,5,5,5,5,1,1,1,1,1,1,1,1]
[X86][SSSE3] Added target shuffle combine tests for SSE3/SSSE3 specific shuffles. Allows us to test SSSE3 PSHUFB intrinsic. llvm-svn: 261753
2016-02-25 01:08:59 +08:00
; AVX-NEXT: retq
%1 = bitcast <4 x float> %a0 to <16 x i8>
%2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 5, i8 5, i8 5, i8 5, i8 7, i8 7, i8 7, i8 7, i8 1, i8 1, i8 1, i8 1, i8 3, i8 3, i8 3, i8 3>)
%3 = bitcast <16 x i8> %2 to <4 x float>
%4 = shufflevector <4 x float> %3, <4 x float> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
ret <4 x float> %4
}
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from one of the inputs of a binary shuffle (punpcklbw) llvm-svn: 262486
2016-03-02 22:16:50 +08:00
[X86][SSE] Added target shuffle combine tests for byte shift/rotates (PSLLDQ/PSRLDQ/PALIGNR) llvm-svn: 272392
2016-06-10 21:03:22 +08:00
define <16 x i8> @combine_pshufb_palignr(<16 x i8> %a0, <16 x i8> %a1) {
; SSE-LABEL: combine_pshufb_palignr:
; SSE: # BB#0:
; SSE-NEXT: pshufb {{.*#+}} xmm1 = xmm1[8,9,10,11,12,13,14,15,8,9,10,11,12,13,14,15]
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_pshufb_palignr:
; AVX: # BB#0:
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm1[8,9,10,11,12,13,14,15,8,9,10,11,12,13,14,15]
; AVX-NEXT: retq
%1 = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <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>
%2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>)
ret <16 x i8> %2
}
define <16 x i8> @combine_pshufb_pslldq(<16 x i8> %a0) {
; SSE-LABEL: combine_pshufb_pslldq:
; SSE: # BB#0:
[X86][SSE] Added PSLLDQ/PSRLDQ as a target shuffle type Ensure that PALIGNR/PSLLDQ/PSRLDQ are byte vectors so that they can be correctly decoded for target shuffle combining llvm-svn: 272471
2016-06-11 21:38:28 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
[X86][SSE] Added target shuffle combine tests for byte shift/rotates (PSLLDQ/PSRLDQ/PALIGNR) llvm-svn: 272392
2016-06-10 21:03:22 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_pshufb_pslldq:
; AVX: # BB#0:
[X86][SSE] Added PSLLDQ/PSRLDQ as a target shuffle type Ensure that PALIGNR/PSLLDQ/PSRLDQ are byte vectors so that they can be correctly decoded for target shuffle combining llvm-svn: 272471
2016-06-11 21:38:28 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
[X86][SSE] Added target shuffle combine tests for byte shift/rotates (PSLLDQ/PSRLDQ/PALIGNR) llvm-svn: 272392
2016-06-10 21:03:22 +08:00
; AVX-NEXT: retq
%1 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> <i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>)
%2 = shufflevector <16 x i8> %1, <16 x i8> zeroinitializer, <16 x i32> <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <16 x i8> %2
}
define <16 x i8> @combine_pshufb_psrldq(<16 x i8> %a0) {
; SSE-LABEL: combine_pshufb_psrldq:
; SSE: # BB#0:
[X86][SSE] Added PSLLDQ/PSRLDQ as a target shuffle type Ensure that PALIGNR/PSLLDQ/PSRLDQ are byte vectors so that they can be correctly decoded for target shuffle combining llvm-svn: 272471
2016-06-11 21:38:28 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
[X86][SSE] Added target shuffle combine tests for byte shift/rotates (PSLLDQ/PSRLDQ/PALIGNR) llvm-svn: 272392
2016-06-10 21:03:22 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_pshufb_psrldq:
; AVX: # BB#0:
[X86][SSE] Added PSLLDQ/PSRLDQ as a target shuffle type Ensure that PALIGNR/PSLLDQ/PSRLDQ are byte vectors so that they can be correctly decoded for target shuffle combining llvm-svn: 272471
2016-06-11 21:38:28 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
[X86][SSE] Added target shuffle combine tests for byte shift/rotates (PSLLDQ/PSRLDQ/PALIGNR) llvm-svn: 272392
2016-06-10 21:03:22 +08:00
; AVX-NEXT: retq
%1 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> <i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128, i8 128>)
%2 = shufflevector <16 x i8> %1, <16 x i8> zeroinitializer, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
ret <16 x i8> %2
}
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from the second input of a binary shuffle (punpcklbw) llvm-svn: 262710
2016-03-04 19:15:23 +08:00
define <16 x i8> @combine_unpckl_arg0_pshufb(<16 x i8> %a0, <16 x i8> %a1) {
; SSE-LABEL: combine_unpckl_arg0_pshufb:
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from one of the inputs of a binary shuffle (punpcklbw) llvm-svn: 262486
2016-03-02 22:16:50 +08:00
; SSE: # BB#0:
; SSE-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero
; SSE-NEXT: retq
;
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from the second input of a binary shuffle (punpcklbw) llvm-svn: 262710
2016-03-04 19:15:23 +08:00
; AVX-LABEL: combine_unpckl_arg0_pshufb:
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from one of the inputs of a binary shuffle (punpcklbw) llvm-svn: 262486
2016-03-02 22:16:50 +08:00
; AVX: # BB#0:
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero
; AVX-NEXT: retq
%1 = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
%2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1>)
ret <16 x i8> %2
}
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from the second input of a binary shuffle (punpcklbw) llvm-svn: 262710
2016-03-04 19:15:23 +08:00
define <16 x i8> @combine_unpckl_arg1_pshufb(<16 x i8> %a0, <16 x i8> %a1) {
; SSE-LABEL: combine_unpckl_arg1_pshufb:
; SSE: # BB#0:
[X86][SSE] Basic combining of unary target shuffles of binary target shuffles. This patch reorders the combining of target shuffle masks so that when a unary shuffle takes a binary shuffle as its input but only references one of its inputs it can correctly combine into a unary shuffle mask. This is starting to encroach on the purpose of resolveTargetShuffleInputs, but I don't want to remove it until we definitely know we won't need it for full binary shuffle combining. There is a lot more work before we can properly support binary target shuffle masks but this was an easy case to add support for. Differential Revision: http://reviews.llvm.org/D17858 llvm-svn: 263102
2016-03-10 19:23:51 +08:00
; SSE-NEXT: pshufb {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[0],zero,zero,zero,xmm1[0],zero,zero,zero,xmm1[0],zero,zero,zero
; SSE-NEXT: movdqa %xmm1, %xmm0
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from the second input of a binary shuffle (punpcklbw) llvm-svn: 262710
2016-03-04 19:15:23 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_unpckl_arg1_pshufb:
; AVX: # BB#0:
[X86][SSE] Basic combining of unary target shuffles of binary target shuffles. This patch reorders the combining of target shuffle masks so that when a unary shuffle takes a binary shuffle as its input but only references one of its inputs it can correctly combine into a unary shuffle mask. This is starting to encroach on the purpose of resolveTargetShuffleInputs, but I don't want to remove it until we definitely know we won't need it for full binary shuffle combining. There is a lot more work before we can properly support binary target shuffle masks but this was an easy case to add support for. Differential Revision: http://reviews.llvm.org/D17858 llvm-svn: 263102
2016-03-10 19:23:51 +08:00
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm1[0],zero,zero,zero,xmm1[0],zero,zero,zero,xmm1[0],zero,zero,zero,xmm1[0],zero,zero,zero
[X86][SSSE3] Added combine test for unary shuffle (pshufb) only referencing elements from the second input of a binary shuffle (punpcklbw) llvm-svn: 262710
2016-03-04 19:15:23 +08:00
; AVX-NEXT: retq
%1 = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
%2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1>)
ret <16 x i8> %2
}