; AVX1-LABEL: shuffle_v32i8_zz_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_17_zz_19_zz_21_zz_23_zz_25_zz_27_zz_29_zz_31:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [128,1,128,3,128,5,128,7,128,9,128,11,128,13,128,15]
-; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT: vmovaps {{.*#+}} xmm2 = [0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255]
+; AVX1-NEXT: vandps %xmm2, %xmm1, %xmm1
+; AVX1-NEXT: vandps %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_zz_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_17_zz_19_zz_21_zz_23_zz_25_zz_27_zz_29_zz_31:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
-; AVX2-NEXT: vpxor %ymm2, %ymm2, %ymm2
-; AVX2-NEXT: vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
+; AVX2-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 32, i32 1, i32 34, i32 3, i32 36, i32 5, i32 38, i32 7, i32 40, i32 9, i32 42, i32 11, i32 44, i32 13, i32 46, i32 15, i32 48, i32 17, i32 50, i32 19, i32 52, i32 21, i32 54, i32 23, i32 56, i32 25, i32 58, i32 27, i32 60, i32 29, i32 62, i32 31>
ret <32 x i8> %shuffle
; AVX1-LABEL: shuffle_v32i8_32_zz_zz_zz_zz_zz_zz_zz_33_zz_zz_zz_zz_zz_zz_zz_34_zz_zz_zz_zz_zz_zz_zz_35_zz_zz_zz_zz_zz_zz_zz:
; AVX1: # BB#0:
; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
+; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX1-LABEL: shuffle_v32i8_32_zz_zz_zz_33_zz_zz_zz_34_zz_zz_zz_35_zz_zz_zz_36_zz_zz_zz_37_zz_zz_zz_38_zz_zz_zz_39_zz_zz_zz:
; AVX1: # BB#0:
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
+; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 15, 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 31, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
ret <32 x i8> %shuffle
}
+
+define <32 x i8> @insert_dup_mem_v32i8_i32(i32* %ptr) {
+; AVX1-LABEL: insert_dup_mem_v32i8_i32:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: insert_dup_mem_v32i8_i32:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpbroadcastb (%rdi), %ymm0
+; AVX2-NEXT: retq
+ %tmp = load i32, i32* %ptr, align 4
+ %tmp1 = insertelement <4 x i32> zeroinitializer, i32 %tmp, i32 0
+ %tmp2 = bitcast <4 x i32> %tmp1 to <16 x i8>
+ %tmp3 = shufflevector <16 x i8> %tmp2, <16 x i8> undef, <32 x i32> zeroinitializer
+ ret <32 x i8> %tmp3
+}
+
+define <32 x i8> @insert_dup_mem_v32i8_sext_i8(i8* %ptr) {
+; AVX1-LABEL: insert_dup_mem_v32i8_sext_i8:
+; AVX1: # BB#0:
+; AVX1-NEXT: movsbl (%rdi), %eax
+; AVX1-NEXT: vmovd %eax, %xmm0
+; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: insert_dup_mem_v32i8_sext_i8:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpbroadcastb (%rdi), %ymm0
+; AVX2-NEXT: retq
+ %tmp = load i8, i8* %ptr, align 1
+ %tmp1 = sext i8 %tmp to i32
+ %tmp2 = insertelement <4 x i32> zeroinitializer, i32 %tmp1, i32 0
+ %tmp3 = bitcast <4 x i32> %tmp2 to <16 x i8>
+ %tmp4 = shufflevector <16 x i8> %tmp3, <16 x i8> undef, <32 x i32> zeroinitializer
+ ret <32 x i8> %tmp4
+}