ret <16 x i16> %shuffle
}
+define <16 x i16> @shuffle_v16i16_03_02_01_00_04_05_06_07_11_10_09_08_12_13_14_15_v8i16(<8 x i16> %a, <8 x i16> %b) {
+; AVX1-LABEL: shuffle_v16i16_03_02_01_00_04_05_06_07_11_10_09_08_12_13_14_15_v8i16:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,2,1,0,4,5,6,7]
+; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,2,1,0,4,5,6,7]
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2OR512VL-LABEL: shuffle_v16i16_03_02_01_00_04_05_06_07_11_10_09_08_12_13_14_15_v8i16:
+; AVX2OR512VL: # %bb.0:
+; AVX2OR512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,2,1,0,4,5,6,7]
+; AVX2OR512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,2,1,0,4,5,6,7]
+; AVX2OR512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX2OR512VL-NEXT: retq
+ %1 = shufflevector <8 x i16> %a, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 4, i32 5, i32 6, i32 7>
+ %2 = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 4, i32 5, i32 6, i32 7>
+ %3 = shufflevector <8 x i16> %1, <8 x i16> %2, <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 i16> %3
+}
+
+define <16 x i16> @shuffle_v16i16_00_01_02_04_07_06_05_04_08_09_10_11_15_14_13_12_v8i16(<8 x i16> %a, <8 x i16> %b) {
+; AVX1-LABEL: shuffle_v16i16_00_01_02_04_07_06_05_04_08_09_10_11_15_14_13_12_v8i16:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,6,5,4]
+; AVX1-NEXT: vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,7,6,5,4]
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2OR512VL-LABEL: shuffle_v16i16_00_01_02_04_07_06_05_04_08_09_10_11_15_14_13_12_v8i16:
+; AVX2OR512VL: # %bb.0:
+; AVX2OR512VL-NEXT: vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,6,5,4]
+; AVX2OR512VL-NEXT: vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,7,6,5,4]
+; AVX2OR512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX2OR512VL-NEXT: retq
+ %1 = shufflevector <8 x i16> %a, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 5, i32 4>
+ %2 = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 5, i32 4>
+ %3 = shufflevector <8 x i16> %1, <8 x i16> %2, <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 i16> %3
+}
+
define <16 x i16> @insert_v16i16_0elt_into_zero_vector(i16* %ptr) {
; ALL-LABEL: insert_v16i16_0elt_into_zero_vector:
; ALL: # %bb.0:
ret <4 x double> %3
}
+define <4 x double> @shuffle_v4f64_1032_v2f64(<2 x double> %a, <2 x double> %b) {
+; ALL-LABEL: shuffle_v4f64_1032_v2f64:
+; ALL: # %bb.0:
+; ALL-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; ALL-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: retq
+ %1 = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+ %2 = shufflevector <2 x double> %b, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+ %3 = shufflevector <2 x double> %1, <2 x double> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ ret <4 x double> %3
+}
+
define <4 x i64> @shuffle_v4i64_0000(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4i64_0000:
; AVX1: # %bb.0:
ret <4 x i64> %shuffle
}
+define <4 x i64> @shuffle_v4i64_1032_v2i64(<2 x i64> %a, <2 x i64> %b) {
+; ALL-LABEL: shuffle_v4i64_1032_v2i64:
+; ALL: # %bb.0:
+; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; ALL-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: retq
+ %1 = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> <i32 1, i32 0>
+ %2 = shufflevector <2 x i64> %b, <2 x i64> undef, <2 x i32> <i32 1, i32 0>
+ %3 = shufflevector <2 x i64> %1, <2 x i64> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ ret <4 x i64> %3
+}
+
define <4 x i64> @stress_test1(<4 x i64> %a, <4 x i64> %b) {
; ALL-LABEL: stress_test1:
; ALL: retq
ret <8 x float> %shuffle
}
+define <8 x float> @shuffle_v8f32_32107654_v4f32(<4 x float> %a, <4 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_32107654_v4f32:
+; ALL: # %bb.0:
+; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; ALL-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: retq
+ %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+ %2 = shufflevector <4 x float> %b, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+ %3 = shufflevector <4 x float> %1, <4 x float> %2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+ ret <8 x float> %3
+}
+
define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00000000:
; AVX1: # %bb.0:
ret <8 x i32> %shuffle
}
+define <8 x i32> @shuffle_v8i32_32107654_v4i32(<4 x i32> %a, <4 x i32> %b) {
+; ALL-LABEL: shuffle_v8i32_32107654_v4i32:
+; ALL: # %bb.0:
+; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; ALL-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: retq
+ %1 = shufflevector <4 x i32> %a, <4 x i32> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+ %2 = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+ %3 = shufflevector <4 x i32> %1, <4 x i32> %2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+ ret <8 x i32> %3
+}
+
define <8 x float> @splat_mem_v8f32_2(float* %p) {
; ALL-LABEL: splat_mem_v8f32_2:
; ALL: # %bb.0: