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-sse4a.ll

362 lines
16 KiB
LLVM
Raw Normal View History

Make utils/update_llc_test_checks.py note that the assertions are autogenerated. Also update existing test cases which appear to be generated by it and weren't modified (other than addition of the header) by rerunning it. llvm-svn: 253917
2015-11-24 05:33:58 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86][SSE4A] Shuffle lowering using SSE4A EXTRQ/INSERTQ instructions This patch adds support for v8i16 and v16i8 shuffle lowering using the immediate versions of the SSE4A EXTRQ and INSERTQ instructions. Although rather limited (they can only act on the lower 64-bits of the source vectors, leave the upper 64-bits of the result vector undefined and don't have VEX encoded variants), the instructions are still useful for the zero extension of any lane (EXTRQ) or inserting a lane into another vector (INSERTQ). Testing demonstrated that it wasn't typically worth it to use these instructions for v2i64 or v4i32 vector shuffles although they are capable of it. As well as adding specific pattern matching for the shuffles, the patch uses EXTRQ for zero extension cases where SSE41 isn't available and its more efficient than the SSE2 'unpack' default approach. It also adds shuffle decode support for the EXTRQ / INSERTQ cases when the instructions are handling full byte-sized extractions / insertions. From this foundation, future patches will be able to make use of the instructions for situations that use their ability to extract/insert at the bit level. Differential Revision: http://reviews.llvm.org/D10146 llvm-svn: 241508
2015-07-07 04:46:41 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3,+sse4a | FileCheck %s --check-prefix=ALL --check-prefix=BTVER1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+sse4a | FileCheck %s --check-prefix=ALL --check-prefix=BTVER2
;
; EXTRQI
;
[X86][SSE4A] Added shuffle decode tests for 'special case' SSE4A EXTRQI/INSERTQI ops. llvm-svn: 249263
2015-10-04 18:12:53 +08:00
; A length of zero is equivalent to a bit length of 64.
define <2 x i64> @extrqi_len0_idx0(<2 x i64> %a) {
; ALL-LABEL: extrqi_len0_idx0:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = tail call <2 x i64> @llvm.x86.sse4a.extrqi(<2 x i64> %a, i8 0, i8 0)
ret <2 x i64> %1
}
define <2 x i64> @extrqi_len8_idx16(<2 x i64> %a) {
; ALL-LABEL: extrqi_len8_idx16:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = tail call <2 x i64> @llvm.x86.sse4a.extrqi(<2 x i64> %a, i8 8, i8 16)
ret <2 x i64> %1
}
; If the length + index exceeds the bottom 64 bits the result is undefined.
define <2 x i64> @extrqi_len32_idx48(<2 x i64> %a) {
; ALL-LABEL: extrqi_len32_idx48:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = tail call <2 x i64> @llvm.x86.sse4a.extrqi(<2 x i64> %a, i8 32, i8 48)
ret <2 x i64> %1
}
[X86][SSE4A] Shuffle lowering using SSE4A EXTRQ/INSERTQ instructions This patch adds support for v8i16 and v16i8 shuffle lowering using the immediate versions of the SSE4A EXTRQ and INSERTQ instructions. Although rather limited (they can only act on the lower 64-bits of the source vectors, leave the upper 64-bits of the result vector undefined and don't have VEX encoded variants), the instructions are still useful for the zero extension of any lane (EXTRQ) or inserting a lane into another vector (INSERTQ). Testing demonstrated that it wasn't typically worth it to use these instructions for v2i64 or v4i32 vector shuffles although they are capable of it. As well as adding specific pattern matching for the shuffles, the patch uses EXTRQ for zero extension cases where SSE41 isn't available and its more efficient than the SSE2 'unpack' default approach. It also adds shuffle decode support for the EXTRQ / INSERTQ cases when the instructions are handling full byte-sized extractions / insertions. From this foundation, future patches will be able to make use of the instructions for situations that use their ability to extract/insert at the bit level. Differential Revision: http://reviews.llvm.org/D10146 llvm-svn: 241508
2015-07-07 04:46:41 +08:00
define <16 x i8> @shuf_0zzzuuuuuuuuuuuu(<16 x i8> %a0) {
; BTVER1-LABEL: shuf_0zzzuuuuuuuuuuuu:
; BTVER1: # BB#0:
; BTVER1-NEXT: extrq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_0zzzuuuuuuuuuuuu:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
; BTVER2-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 16, i32 16, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
}
define <16 x i8> @shuf_0zzzzzzz1zzzzzzz(<16 x i8> %a0) {
; BTVER1-LABEL: shuf_0zzzzzzz1zzzzzzz:
; BTVER1: # BB#0:
; BTVER1-NEXT: movaps %xmm0, %xmm1
; BTVER1-NEXT: extrq {{.*#+}} xmm1 = xmm1[1],zero,zero,zero,zero,zero,zero,zero,xmm1[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: extrq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_0zzzzzzz1zzzzzzz:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
; BTVER2-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 1, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
ret <16 x i8> %s
[X86][SSE] Match zero/any extension shuffles that don't start from the first element This patch generalizes the lowering of shuffles as zero extensions to allow extensions that don't start from the first element. It now recognises extensions starting anywhere in the lower 128-bits or at the start of any higher 128-bit lane. The motivation was to reduce the number of high cost pshufb calls, but it also improves the SSE2 case as well. Differential Revision: http://reviews.llvm.org/D12561 llvm-svn: 248250
2015-09-22 16:16:08 +08:00
}
define <16 x i8> @shuf_2zzzzzzz3zzzzzzz(<16 x i8> %a0) {
; BTVER1-LABEL: shuf_2zzzzzzz3zzzzzzz:
; BTVER1: # BB#0:
; BTVER1-NEXT: movaps %xmm0, %xmm1
; BTVER1-NEXT: extrq {{.*#+}} xmm1 = xmm1[3],zero,zero,zero,zero,zero,zero,zero,xmm1[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: extrq {{.*#+}} xmm0 = xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_2zzzzzzz3zzzzzzz:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpsrld $16, %xmm0, %xmm0
; BTVER2-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
; BTVER2-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> zeroinitializer, <16 x i32> <i32 2, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 3, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
ret <16 x i8> %s
[X86][SSE4A] Shuffle lowering using SSE4A EXTRQ/INSERTQ instructions This patch adds support for v8i16 and v16i8 shuffle lowering using the immediate versions of the SSE4A EXTRQ and INSERTQ instructions. Although rather limited (they can only act on the lower 64-bits of the source vectors, leave the upper 64-bits of the result vector undefined and don't have VEX encoded variants), the instructions are still useful for the zero extension of any lane (EXTRQ) or inserting a lane into another vector (INSERTQ). Testing demonstrated that it wasn't typically worth it to use these instructions for v2i64 or v4i32 vector shuffles although they are capable of it. As well as adding specific pattern matching for the shuffles, the patch uses EXTRQ for zero extension cases where SSE41 isn't available and its more efficient than the SSE2 'unpack' default approach. It also adds shuffle decode support for the EXTRQ / INSERTQ cases when the instructions are handling full byte-sized extractions / insertions. From this foundation, future patches will be able to make use of the instructions for situations that use their ability to extract/insert at the bit level. Differential Revision: http://reviews.llvm.org/D10146 llvm-svn: 241508
2015-07-07 04:46:41 +08:00
}
define <16 x i8> @shuf_01zzuuuuuuuuuuuu(<16 x i8> %a0) {
; BTVER1-LABEL: shuf_01zzuuuuuuuuuuuu:
; BTVER1: # BB#0:
; BTVER1-NEXT: extrq {{.*#+}} xmm0 = xmm0[0,1],zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_01zzuuuuuuuuuuuu:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; BTVER2-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 16, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
}
define <16 x i8> @shuf_01zzzzzz23zzzzzz(<16 x i8> %a0) {
; BTVER1-LABEL: shuf_01zzzzzz23zzzzzz:
; BTVER1: # BB#0:
; BTVER1-NEXT: movaps %xmm0, %xmm1
; BTVER1-NEXT: extrq {{.*#+}} xmm1 = xmm1[2,3],zero,zero,zero,zero,zero,zero,xmm1[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: extrq {{.*#+}} xmm0 = xmm0[0,1],zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_01zzzzzz23zzzzzz:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; BTVER2-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 2, i32 3, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
ret <16 x i8> %s
}
define <16 x i8> @shuf_1zzzuuuuuuuuuuuu(<16 x i8> %a0) {
; ALL-LABEL: shuf_1zzzuuuuuuuuuuuu:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> zeroinitializer, <16 x i32> <i32 1, i32 16, i32 16, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
}
define <8 x i16> @shuf_1zzzuuuu(<8 x i16> %a0) {
; ALL-LABEL: shuf_1zzzuuuu:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[2,3],zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> zeroinitializer, <8 x i32> <i32 1, i32 8, i32 8, i32 8, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_12zzuuuu(<8 x i16> %a0) {
; ALL-LABEL: shuf_12zzuuuu:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[2,3,4,5],zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> zeroinitializer, <8 x i32> <i32 1, i32 2, i32 8, i32 8, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_012zuuuu(<8 x i16> %a0) {
; ALL-LABEL: shuf_012zuuuu:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],zero,zero,xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_0zzz1zzz(<8 x i16> %a0) {
; BTVER1-LABEL: shuf_0zzz1zzz:
; BTVER1: # BB#0:
; BTVER1-NEXT: movaps %xmm0, %xmm1
; BTVER1-NEXT: extrq {{.*#+}} xmm1 = xmm1[2,3],zero,zero,zero,zero,zero,zero,xmm1[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: extrq {{.*#+}} xmm0 = xmm0[0,1],zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; BTVER1-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_0zzz1zzz:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; BTVER2-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 8, i32 8, i32 8, i32 1, i32 8, i32 8, i32 8>
ret <8 x i16> %s
}
define <4 x i32> @shuf_0z1z(<4 x i32> %a0) {
; BTVER1-LABEL: shuf_0z1z:
; BTVER1: # BB#0:
; BTVER1-NEXT: pxor %xmm1, %xmm1
; BTVER1-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuf_0z1z:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; BTVER2-NEXT: retq
%s = shufflevector <4 x i32> %a0, <4 x i32> zeroinitializer, <4 x i32> <i32 0, i32 4, i32 1, i32 4>
ret <4 x i32> %s
}
;
; INSERTQI
;
[X86][SSE4A] Added shuffle decode tests for 'special case' SSE4A EXTRQI/INSERTQI ops. llvm-svn: 249263
2015-10-04 18:12:53 +08:00
; A length of zero is equivalent to a bit length of 64.
define <2 x i64> @insertqi_len0_idx0(<2 x i64> %a, <2 x i64> %b) {
; ALL-LABEL: insertqi_len0_idx0:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm1[0,1,2,3,4,5,6,7],xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = tail call <2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %a, <2 x i64> %b, i8 0, i8 0)
ret <2 x i64> %1
}
define <2 x i64> @insertqi_len8_idx16(<2 x i64> %a, <2 x i64> %b) {
; ALL-LABEL: insertqi_len8_idx16:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3,4,5,6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = tail call <2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %a, <2 x i64> %b, i8 8, i8 16)
ret <2 x i64> %1
}
; If the length + index exceeds the bottom 64 bits the result is undefined
define <2 x i64> @insertqi_len32_idx48(<2 x i64> %a, <2 x i64> %b) {
; ALL-LABEL: insertqi_len32_idx48:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = tail call <2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %a, <2 x i64> %b, i8 32, i8 48)
ret <2 x i64> %1
}
[X86][SSE4A] Shuffle lowering using SSE4A EXTRQ/INSERTQ instructions This patch adds support for v8i16 and v16i8 shuffle lowering using the immediate versions of the SSE4A EXTRQ and INSERTQ instructions. Although rather limited (they can only act on the lower 64-bits of the source vectors, leave the upper 64-bits of the result vector undefined and don't have VEX encoded variants), the instructions are still useful for the zero extension of any lane (EXTRQ) or inserting a lane into another vector (INSERTQ). Testing demonstrated that it wasn't typically worth it to use these instructions for v2i64 or v4i32 vector shuffles although they are capable of it. As well as adding specific pattern matching for the shuffles, the patch uses EXTRQ for zero extension cases where SSE41 isn't available and its more efficient than the SSE2 'unpack' default approach. It also adds shuffle decode support for the EXTRQ / INSERTQ cases when the instructions are handling full byte-sized extractions / insertions. From this foundation, future patches will be able to make use of the instructions for situations that use their ability to extract/insert at the bit level. Differential Revision: http://reviews.llvm.org/D10146 llvm-svn: 241508
2015-07-07 04:46:41 +08:00
define <16 x i8> @shuf_0_0_2_3_uuuu_uuuu_uuuu(<16 x i8> %a0, <16 x i8> %a1) {
; ALL-LABEL: shuf_0_0_2_3_uuuu_uuuu_uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,0,2,3,4,5,6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 0, i32 0, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
}
define <16 x i8> @shuf_0_16_2_3_uuuu_uuuu_uuuu(<16 x i8> %a0, <16 x i8> %a1) {
; ALL-LABEL: shuf_0_16_2_3_uuuu_uuuu_uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3,4,5,6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 0, i32 16, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
}
define <16 x i8> @shuf_16_1_2_3_uuuu_uuuu_uuuu(<16 x i8> %a0, <16 x i8> %a1) {
; ALL-LABEL: shuf_16_1_2_3_uuuu_uuuu_uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3,4,5,6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 16, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
}
define <8 x i16> @shuf_0823uuuu(<8 x i16> %a0, <8 x i16> %a1) {
; ALL-LABEL: shuf_0823uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1],xmm0[4,5,6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> %a1, <8 x i32> <i32 0, i32 8, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_0183uuuu(<8 x i16> %a0, <8 x i16> %a1) {
; ALL-LABEL: shuf_0183uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[0,1],xmm0[6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> %a1, <8 x i32> <i32 0, i32 1, i32 8, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_0128uuuu(<8 x i16> %a0, <8 x i16> %a1) {
; ALL-LABEL: shuf_0128uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[0,1],xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_0893uuuu(<8 x i16> %a0, <8 x i16> %a1) {
; ALL-LABEL: shuf_0893uuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1,2,3],xmm0[6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> %a1, <8 x i32> <i32 0, i32 8, i32 9, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_089Auuuu(<8 x i16> %a0, <8 x i16> %a1) {
; ALL-LABEL: shuf_089Auuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1,2,3,4,5],xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> %a1, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
define <8 x i16> @shuf_089uuuuu(<8 x i16> %a0, <8 x i16> %a1) {
; ALL-LABEL: shuf_089uuuuu:
; ALL: # BB#0:
; ALL-NEXT: insertq {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1,2,3],xmm0[6,7,u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%s = shufflevector <8 x i16> %a0, <8 x i16> %a1, <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i16> %s
}
[X86][SSE4A] Added shuffle decode tests for 'special case' SSE4A EXTRQI/INSERTQI ops. llvm-svn: 249263
2015-10-04 18:12:53 +08:00
[X86][SSE4A] Fix for EXTRQI shuffle lowering. Incorrect range test - found during fuzz testing. llvm-svn: 251245
2015-10-26 01:40:54 +08:00
;
; Special Cases
;
; Out of range.
define <16 x i8> @shuffle_8_18_uuuuuuuuuuuuuu(<16 x i8> %a, <16 x i8> %b) {
; BTVER1-LABEL: shuffle_8_18_uuuuuuuuuuuuuu:
; BTVER1: # BB#0:
; BTVER1-NEXT: psrld $16, %xmm1
; BTVER1-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; BTVER1-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuffle_8_18_uuuuuuuuuuuuuu:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpsrld $16, %xmm1, %xmm1
; BTVER2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; BTVER2-NEXT: vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; BTVER2-NEXT: retq
%1 = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 8, i32 18, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %1
}
[X86][SSE4A] Fix issue with EXTRQI shuffles not starting at the correct start index. Found during stress testing. llvm-svn: 253611
2015-11-20 06:13:56 +08:00
define <16 x i8> @shuffle_uu_0_5_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu(<16 x i8> %v) {
; BTVER1-LABEL: shuffle_uu_0_5_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
; BTVER1: # BB#0:
; BTVER1-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,0,5,5,4,4,5,5,4,4,5,5,6,6,7,7]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuffle_uu_0_5_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,0,5,5,4,4,5,5,4,4,5,5,6,6,7,7]
; BTVER2-NEXT: retq
%1 = shufflevector <16 x i8> %v, <16 x i8> zeroinitializer, <16 x i32> <i32 undef, i32 0, i32 5, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %1
}
define <16 x i8> @shuffle_uu_16_4_16_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu(<16 x i8> %v) {
; BTVER1-LABEL: shuffle_uu_16_4_16_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
; BTVER1: # BB#0:
; BTVER1-NEXT: pshufb {{.*#+}} xmm0 = xmm0[u],zero,xmm0[4],zero,xmm0[u,u,u,u,u,u,u,u,u,u,u,u]
; BTVER1-NEXT: retq
;
; BTVER2-LABEL: shuffle_uu_16_4_16_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[u],zero,xmm0[4],zero,xmm0[u,u,u,u,u,u,u,u,u,u,u,u]
; BTVER2-NEXT: retq
%1 = shufflevector <16 x i8> %v, <16 x i8> zeroinitializer, <16 x i32> <i32 undef, i32 16, i32 4, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %1
}
define <16 x i8> @shuffle_uu_uu_4_16_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu(<16 x i8> %v) {
; ALL-LABEL: shuffle_uu_uu_4_16_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
; ALL: # BB#0:
; ALL-NEXT: extrq {{.*#+}} xmm0 = xmm0[2,3,4],zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
; ALL-NEXT: retq
%1 = shufflevector <16 x i8> %v, <16 x i8> zeroinitializer, <16 x i32> <i32 undef, i32 undef, i32 4, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %1
}
[X86][SSE4A] Added shuffle decode tests for 'special case' SSE4A EXTRQI/INSERTQI ops. llvm-svn: 249263
2015-10-04 18:12:53 +08:00
declare <2 x i64> @llvm.x86.sse4a.extrqi(<2 x i64>, i8, i8) nounwind
declare <2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64>, <2 x i64>, i8, i8) nounwind