;
; AVX2-LABEL: shuffle_v4f64_0000:
; AVX2: # BB#0:
-; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
+; AVX2-NEXT: vbroadcastsd %xmm0, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x double> %shuffle
}
define <4 x double> @shuffle_v4f64_0423(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: shuffle_v4f64_0423:
-; ALL: # BB#0:
-; ALL-NEXT: vpermilpd {{.*#+}} ymm1 = ymm1[0,0,2,2]
-; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
-; ALL-NEXT: retq
+; AVX1-LABEL: shuffle_v4f64_0423:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilpd {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v4f64_0423:
+; AVX2: # BB#0:
+; AVX2-NEXT: vbroadcastsd %xmm1, %ymm1
+; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
+; AVX2-NEXT: retq
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 3>
ret <4 x double> %shuffle
}
}
define <4 x double> @shuffle_v4f64_0145(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: shuffle_v4f64_0145:
-; AVX1: # BB#0:
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v4f64_0145:
-; AVX2: # BB#0:
-; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,1]
-; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v4f64_0145:
+; ALL: # BB#0:
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: retq
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x double> %shuffle
}
define <4 x double> @shuffle_v4f64_4501(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: shuffle_v4f64_4501:
-; AVX1: # BB#0:
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v4f64_4501:
-; AVX2: # BB#0:
-; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,1]
-; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v4f64_4501:
+; ALL: # BB#0:
+; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; ALL-NEXT: retq
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x double> %shuffle
}
;
; AVX2-LABEL: shuffle_v4i64_0000:
; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
+; AVX2-NEXT: vbroadcastsd %xmm0, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i64> %shuffle
;
; AVX2-LABEL: shuffle_v4i64_0124:
; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,1,2,0]
+; AVX2-NEXT: vpbroadcastq %xmm1, %ymm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
define <4 x i64> @shuffle_v4i64_0142(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4i64_0142:
; AVX1: # BB#0:
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
; AVX1-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[0,1,2,2]
; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4i64_0142:
; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,1,0,3]
+; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,2,2]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
; AVX2-NEXT: retq
;
; AVX2-LABEL: shuffle_v4i64_0412:
; AVX2: # BB#0:
-; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,1,2]
+; AVX2-NEXT: vpbroadcastq %xmm1, %ymm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 2>
}
define <4 x i64> @shuffle_v4i64_0145(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: shuffle_v4i64_0145:
-; AVX1: # BB#0:
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v4i64_0145:
-; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,1,0,1]
-; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v4i64_0145:
+; ALL: # BB#0:
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: retq
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x i64> %shuffle
}
;
; AVX2-LABEL: shuffle_v4i64_0451:
; AVX2: # BB#0:
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,0,1,3]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,2,1]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5],ymm0[6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 5, i32 1>
}
define <4 x i64> @shuffle_v4i64_4501(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: shuffle_v4i64_4501:
-; AVX1: # BB#0:
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v4i64_4501:
-; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
-; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v4i64_4501:
+; ALL: # BB#0:
+; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; ALL-NEXT: retq
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x i64> %shuffle
}
;
; AVX2-LABEL: shuffle_v4i64_4015:
; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,1,2,1]
+; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,1,3]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5],ymm1[6,7]
; AVX2-NEXT: retq
define <4 x i64> @shuffle_v4i64_2u35(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4i64_2u35:
; AVX1: # BB#0:
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
;
; AVX2-LABEL: shuffle_v4i64_2u35:
; AVX2: # BB#0:
-; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,1,2,1]
+; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[2,1,3,3]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
; AVX2-NEXT: retq
define <4 x double> @insert_reg_and_zero_v4f64(double %a) {
; ALL-LABEL: insert_reg_and_zero_v4f64:
; ALL: # BB#0:
-; ALL-NEXT: # kill: XMM0<def> XMM0<kill> YMM0<def>
-; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
-; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
+; ALL-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; ALL-NEXT: vmovsd %xmm0, %xmm1, %xmm0
; ALL-NEXT: retq
%v = insertelement <4 x double> undef, double %a, i32 0
%shuffle = shufflevector <4 x double> %v, <4 x double> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
; ALL-LABEL: insert_mem_and_zero_v4f64:
; ALL: # BB#0:
; ALL-NEXT: vmovsd (%rdi), %xmm0
-; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
-; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
; ALL-NEXT: retq
%a = load double* %ptr
%v = insertelement <4 x double> undef, double %a, i32 0
%shuffle = shufflevector <4 x double> %v, <4 x double> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x double> %shuffle
}
+
+define <4 x double> @splat_mem_v4f64(double* %ptr) {
+; ALL-LABEL: splat_mem_v4f64:
+; ALL: # BB#0:
+; ALL-NEXT: vbroadcastsd (%rdi), %ymm0
+; ALL-NEXT: retq
+ %a = load double* %ptr
+ %v = insertelement <4 x double> undef, double %a, i32 0
+ %shuffle = shufflevector <4 x double> %v, <4 x double> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
+ ret <4 x double> %shuffle
+}
+
+define <4 x i64> @splat_mem_v4i64(i64* %ptr) {
+; AVX1-LABEL: splat_mem_v4i64:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovddup (%rdi), %xmm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: splat_mem_v4i64:
+; AVX2: # BB#0:
+; AVX2-NEXT: vbroadcastsd (%rdi), %ymm0
+; AVX2-NEXT: retq
+ %a = load i64* %ptr
+ %v = insertelement <4 x i64> undef, i64 %a, i64 0
+ %shuffle = shufflevector <4 x i64> %v, <4 x i64> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
+ ret <4 x i64> %shuffle
+}
+
+define <4 x double> @splat_mem_v4f64_2(double* %p) {
+; ALL-LABEL: splat_mem_v4f64_2:
+; ALL: # BB#0:
+; ALL-NEXT: vbroadcastsd (%rdi), %ymm0
+; ALL-NEXT: retq
+ %1 = load double* %p
+ %2 = insertelement <2 x double> undef, double %1, i32 0
+ %3 = shufflevector <2 x double> %2, <2 x double> undef, <4 x i32> zeroinitializer
+ ret <4 x double> %3
+}
+
+define <4 x double> @splat_v4f64(<2 x double> %r) {
+; AVX1-LABEL: splat_v4f64:
+; AVX1: # BB#0:
+; AVX1-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: splat_v4f64:
+; AVX2: # BB#0:
+; AVX2-NEXT: vbroadcastsd %xmm0, %ymm0
+; AVX2-NEXT: retq
+ %1 = shufflevector <2 x double> %r, <2 x double> undef, <4 x i32> zeroinitializer
+ ret <4 x double> %1
+}