[X86][SSE] Add additional PR40318 shuffle test cases
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@351333 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/X86/vector-shuffle-128-v16.ll b/test/CodeGen/X86/vector-shuffle-128-v16.ll
index d9790aa..34bc3cf 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v16.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v16.ll
@@ -1532,6 +1532,111 @@
ret <16 x i8> %shuffle
}
+define <16 x i8> @shuffle_v16i8_zz_zz_zz_zz_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz(<16 x i8> %a) {
+; SSE2-LABEL: shuffle_v16i8_zz_zz_zz_zz_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz:
+; SSE2: # %bb.0:
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
+; SSE2-NEXT: pxor %xmm1, %xmm1
+; SSE2-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]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm0[0,1,2,3,6,5,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,0,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[3,2,0,0,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,4,4,4]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,0]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,7,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,3,2,1]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[2,2,2,2,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,6,7,4]
+; SSE2-NEXT: packuswb %xmm1, %xmm0
+; SSE2-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v16i8_zz_zz_zz_zz_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz:
+; SSSE3: # %bb.0:
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,xmm0[1,2,3,4,5,6],zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v16i8_zz_zz_zz_zz_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz:
+; SSE41: # %bb.0:
+; SSE41-NEXT: pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,xmm0[1,2,3,4,5,6],zero,zero,zero,zero,zero,zero
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v16i8_zz_zz_zz_zz_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz:
+; AVX: # %bb.0:
+; AVX-NEXT: vpshufb {{.*#+}} xmm0 = zero,zero,zero,zero,xmm0[1,2,3,4,5,6],zero,zero,zero,zero,zero,zero
+; AVX-NEXT: retq
+ %shuffle = shufflevector <16 x i8> %a, <16 x i8> <i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, <16 x i32> <i32 16, i32 16, i32 16, i32 16, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ ret <16 x i8> %shuffle
+}
+
+define <16 x i8> @shuffle_v16i8_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz(<16 x i8> %a) {
+; SSE2-LABEL: shuffle_v16i8_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; SSE2: # %bb.0:
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
+; SSE2-NEXT: pxor %xmm1, %xmm1
+; SSE2-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]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,0,2,3,4,5,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,0]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,5,4,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,0]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,2,3,0,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,6,4,4]
+; SSE2-NEXT: packuswb %xmm1, %xmm0
+; SSE2-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v16i8_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; SSSE3: # %bb.0:
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v16i8_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; SSE41: # %bb.0:
+; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v16i8_01_02_03_04_05_06_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; AVX: # %bb.0:
+; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT: retq
+ %shuffle = shufflevector <16 x i8> %a, <16 x i8> <i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, <16 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ ret <16 x i8> %shuffle
+}
+
+define <16 x i8> @shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_01_02_03_04_05_06(<16 x i8> %a) {
+; SSE2-LABEL: shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_01_02_03_04_05_06:
+; SSE2: # %bb.0:
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
+; SSE2-NEXT: pxor %xmm1, %xmm1
+; SSE2-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]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,0,2,3,4,5,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,0]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,3,2,3,4,5,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,0]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,1,2,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,4,5,6]
+; SSE2-NEXT: packuswb %xmm0, %xmm1
+; SSE2-NEXT: movdqa %xmm1, %xmm0
+; SSE2-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_01_02_03_04_05_06:
+; SSSE3: # %bb.0:
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[1,2,3,4,5,6]
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_01_02_03_04_05_06:
+; SSE41: # %bb.0:
+; SSE41-NEXT: pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[1,2,3,4,5,6]
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_01_02_03_04_05_06:
+; AVX: # %bb.0:
+; AVX-NEXT: vpshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[1,2,3,4,5,6]
+; AVX-NEXT: retq
+ %shuffle = shufflevector <16 x i8> %a, <16 x i8> <i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, <16 x i32> <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6>
+ ret <16 x i8> %shuffle
+}
+
define <16 x i8> @PR12412(<16 x i8> %inval1, <16 x i8> %inval2) {
; SSE2-LABEL: PR12412:
; SSE2: # %bb.0: # %entry
diff --git a/test/CodeGen/X86/vector-shuffle-128-v8.ll b/test/CodeGen/X86/vector-shuffle-128-v8.ll
index c5224bb..90b8cdf 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v8.ll
@@ -2535,6 +2535,55 @@
ret <8 x i16> %r
}
+define <8 x i16> @shuffle_v8i16_3uu6zzzz(<8 x i16> %x) {
+; SSE2-LABEL: shuffle_v8i16_3uu6zzzz:
+; SSE2: # %bb.0:
+; SSE2-NEXT: psrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
+; SSE2-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
+; SSE2-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v8i16_3uu6zzzz:
+; SSSE3: # %bb.0:
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[6,7,u,u,u,u,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v8i16_3uu6zzzz:
+; SSE41: # %bb.0:
+; SSE41-NEXT: psrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
+; SSE41-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
+; SSE41-NEXT: retq
+;
+; AVX1-LABEL: shuffle_v8i16_3uu6zzzz:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
+; AVX1-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX1-NEXT: retq
+;
+; AVX2-SLOW-LABEL: shuffle_v8i16_3uu6zzzz:
+; AVX2-SLOW: # %bb.0:
+; AVX2-SLOW-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
+; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX2-SLOW-NEXT: retq
+;
+; AVX2-FAST-LABEL: shuffle_v8i16_3uu6zzzz:
+; AVX2-FAST: # %bb.0:
+; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-FAST-NEXT: retq
+;
+; AVX512VL-SLOW-LABEL: shuffle_v8i16_3uu6zzzz:
+; AVX512VL-SLOW: # %bb.0:
+; AVX512VL-SLOW-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
+; AVX512VL-SLOW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX512VL-SLOW-NEXT: retq
+;
+; AVX512VL-FAST-LABEL: shuffle_v8i16_3uu6zzzz:
+; AVX512VL-FAST: # %bb.0:
+; AVX512VL-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512VL-FAST-NEXT: retq
+ %r = shufflevector <8 x i16> %x, <8 x i16> zeroinitializer, <8 x i32> <i32 3, i32 undef, i32 undef, i32 6, i32 8, i32 8, i32 8, i32 8>
+ ret <8 x i16> %r
+}
+
define <8 x i16> @mask_v8i16_012345ef(<8 x i16> %a, <8 x i16> %b) {
; SSE2-LABEL: mask_v8i16_012345ef:
; SSE2: # %bb.0:
