forked from OSchip/llvm-project
1186 lines
42 KiB
LLVM
1186 lines
42 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=X32
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=X64
|
|
|
|
define <16 x i8> @BB16(i8* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: BB16:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastb (%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: BB16:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastb (%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i8, i8* %ptr, align 4
|
|
%q0 = insertelement <16 x i8> undef, i8 %q, i32 0
|
|
%q1 = insertelement <16 x i8> %q0, i8 %q, i32 1
|
|
%q2 = insertelement <16 x i8> %q1, i8 %q, i32 2
|
|
%q3 = insertelement <16 x i8> %q2, i8 %q, i32 3
|
|
%q4 = insertelement <16 x i8> %q3, i8 %q, i32 4
|
|
%q5 = insertelement <16 x i8> %q4, i8 %q, i32 5
|
|
%q6 = insertelement <16 x i8> %q5, i8 %q, i32 6
|
|
%q7 = insertelement <16 x i8> %q6, i8 %q, i32 7
|
|
%q8 = insertelement <16 x i8> %q7, i8 %q, i32 8
|
|
%q9 = insertelement <16 x i8> %q8, i8 %q, i32 9
|
|
%qa = insertelement <16 x i8> %q9, i8 %q, i32 10
|
|
%qb = insertelement <16 x i8> %qa, i8 %q, i32 11
|
|
%qc = insertelement <16 x i8> %qb, i8 %q, i32 12
|
|
%qd = insertelement <16 x i8> %qc, i8 %q, i32 13
|
|
%qe = insertelement <16 x i8> %qd, i8 %q, i32 14
|
|
%qf = insertelement <16 x i8> %qe, i8 %q, i32 15
|
|
ret <16 x i8> %qf
|
|
}
|
|
|
|
define <32 x i8> @BB32(i8* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: BB32:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastb (%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: BB32:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastb (%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i8, i8* %ptr, align 4
|
|
%q0 = insertelement <32 x i8> undef, i8 %q, i32 0
|
|
%q1 = insertelement <32 x i8> %q0, i8 %q, i32 1
|
|
%q2 = insertelement <32 x i8> %q1, i8 %q, i32 2
|
|
%q3 = insertelement <32 x i8> %q2, i8 %q, i32 3
|
|
%q4 = insertelement <32 x i8> %q3, i8 %q, i32 4
|
|
%q5 = insertelement <32 x i8> %q4, i8 %q, i32 5
|
|
%q6 = insertelement <32 x i8> %q5, i8 %q, i32 6
|
|
%q7 = insertelement <32 x i8> %q6, i8 %q, i32 7
|
|
%q8 = insertelement <32 x i8> %q7, i8 %q, i32 8
|
|
%q9 = insertelement <32 x i8> %q8, i8 %q, i32 9
|
|
%qa = insertelement <32 x i8> %q9, i8 %q, i32 10
|
|
%qb = insertelement <32 x i8> %qa, i8 %q, i32 11
|
|
%qc = insertelement <32 x i8> %qb, i8 %q, i32 12
|
|
%qd = insertelement <32 x i8> %qc, i8 %q, i32 13
|
|
%qe = insertelement <32 x i8> %qd, i8 %q, i32 14
|
|
%qf = insertelement <32 x i8> %qe, i8 %q, i32 15
|
|
|
|
%q20 = insertelement <32 x i8> %qf, i8 %q, i32 16
|
|
%q21 = insertelement <32 x i8> %q20, i8 %q, i32 17
|
|
%q22 = insertelement <32 x i8> %q21, i8 %q, i32 18
|
|
%q23 = insertelement <32 x i8> %q22, i8 %q, i32 19
|
|
%q24 = insertelement <32 x i8> %q23, i8 %q, i32 20
|
|
%q25 = insertelement <32 x i8> %q24, i8 %q, i32 21
|
|
%q26 = insertelement <32 x i8> %q25, i8 %q, i32 22
|
|
%q27 = insertelement <32 x i8> %q26, i8 %q, i32 23
|
|
%q28 = insertelement <32 x i8> %q27, i8 %q, i32 24
|
|
%q29 = insertelement <32 x i8> %q28, i8 %q, i32 25
|
|
%q2a = insertelement <32 x i8> %q29, i8 %q, i32 26
|
|
%q2b = insertelement <32 x i8> %q2a, i8 %q, i32 27
|
|
%q2c = insertelement <32 x i8> %q2b, i8 %q, i32 28
|
|
%q2d = insertelement <32 x i8> %q2c, i8 %q, i32 29
|
|
%q2e = insertelement <32 x i8> %q2d, i8 %q, i32 30
|
|
%q2f = insertelement <32 x i8> %q2e, i8 %q, i32 31
|
|
ret <32 x i8> %q2f
|
|
}
|
|
|
|
define <8 x i16> @W16(i16* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: W16:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastw (%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: W16:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastw (%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i16, i16* %ptr, align 4
|
|
%q0 = insertelement <8 x i16> undef, i16 %q, i32 0
|
|
%q1 = insertelement <8 x i16> %q0, i16 %q, i32 1
|
|
%q2 = insertelement <8 x i16> %q1, i16 %q, i32 2
|
|
%q3 = insertelement <8 x i16> %q2, i16 %q, i32 3
|
|
%q4 = insertelement <8 x i16> %q3, i16 %q, i32 4
|
|
%q5 = insertelement <8 x i16> %q4, i16 %q, i32 5
|
|
%q6 = insertelement <8 x i16> %q5, i16 %q, i32 6
|
|
%q7 = insertelement <8 x i16> %q6, i16 %q, i32 7
|
|
ret <8 x i16> %q7
|
|
}
|
|
|
|
define <16 x i16> @WW16(i16* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: WW16:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastw (%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: WW16:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastw (%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i16, i16* %ptr, align 4
|
|
%q0 = insertelement <16 x i16> undef, i16 %q, i32 0
|
|
%q1 = insertelement <16 x i16> %q0, i16 %q, i32 1
|
|
%q2 = insertelement <16 x i16> %q1, i16 %q, i32 2
|
|
%q3 = insertelement <16 x i16> %q2, i16 %q, i32 3
|
|
%q4 = insertelement <16 x i16> %q3, i16 %q, i32 4
|
|
%q5 = insertelement <16 x i16> %q4, i16 %q, i32 5
|
|
%q6 = insertelement <16 x i16> %q5, i16 %q, i32 6
|
|
%q7 = insertelement <16 x i16> %q6, i16 %q, i32 7
|
|
%q8 = insertelement <16 x i16> %q7, i16 %q, i32 8
|
|
%q9 = insertelement <16 x i16> %q8, i16 %q, i32 9
|
|
%qa = insertelement <16 x i16> %q9, i16 %q, i32 10
|
|
%qb = insertelement <16 x i16> %qa, i16 %q, i32 11
|
|
%qc = insertelement <16 x i16> %qb, i16 %q, i32 12
|
|
%qd = insertelement <16 x i16> %qc, i16 %q, i32 13
|
|
%qe = insertelement <16 x i16> %qd, i16 %q, i32 14
|
|
%qf = insertelement <16 x i16> %qe, i16 %q, i32 15
|
|
ret <16 x i16> %qf
|
|
}
|
|
|
|
define <4 x i32> @D32(i32* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: D32:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss (%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: D32:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss (%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i32, i32* %ptr, align 4
|
|
%q0 = insertelement <4 x i32> undef, i32 %q, i32 0
|
|
%q1 = insertelement <4 x i32> %q0, i32 %q, i32 1
|
|
%q2 = insertelement <4 x i32> %q1, i32 %q, i32 2
|
|
%q3 = insertelement <4 x i32> %q2, i32 %q, i32 3
|
|
ret <4 x i32> %q3
|
|
}
|
|
|
|
define <8 x i32> @DD32(i32* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: DD32:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss (%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: DD32:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss (%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i32, i32* %ptr, align 4
|
|
%q0 = insertelement <8 x i32> undef, i32 %q, i32 0
|
|
%q1 = insertelement <8 x i32> %q0, i32 %q, i32 1
|
|
%q2 = insertelement <8 x i32> %q1, i32 %q, i32 2
|
|
%q3 = insertelement <8 x i32> %q2, i32 %q, i32 3
|
|
%q4 = insertelement <8 x i32> %q3, i32 %q, i32 4
|
|
%q5 = insertelement <8 x i32> %q4, i32 %q, i32 5
|
|
%q6 = insertelement <8 x i32> %q5, i32 %q, i32 6
|
|
%q7 = insertelement <8 x i32> %q6, i32 %q, i32 7
|
|
ret <8 x i32> %q7
|
|
}
|
|
|
|
define <2 x i64> @Q64(i64* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: Q64:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: movl (%eax), %ecx
|
|
; X32-NEXT: movl 4(%eax), %eax
|
|
; X32-NEXT: vmovd %ecx, %xmm0
|
|
; X32-NEXT: vpinsrd $1, %eax, %xmm0, %xmm0
|
|
; X32-NEXT: vpinsrd $2, %ecx, %xmm0, %xmm0
|
|
; X32-NEXT: vpinsrd $3, %eax, %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: Q64:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastq (%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i64, i64* %ptr, align 4
|
|
%q0 = insertelement <2 x i64> undef, i64 %q, i32 0
|
|
%q1 = insertelement <2 x i64> %q0, i64 %q, i32 1
|
|
ret <2 x i64> %q1
|
|
}
|
|
|
|
define <4 x i64> @QQ64(i64* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: QQ64:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: movl (%eax), %ecx
|
|
; X32-NEXT: movl 4(%eax), %eax
|
|
; X32-NEXT: vmovd %ecx, %xmm0
|
|
; X32-NEXT: vpinsrd $1, %eax, %xmm0, %xmm0
|
|
; X32-NEXT: vpinsrd $2, %ecx, %xmm0, %xmm0
|
|
; X32-NEXT: vpinsrd $3, %eax, %xmm0, %xmm0
|
|
; X32-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: QQ64:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastsd (%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load i64, i64* %ptr, align 4
|
|
%q0 = insertelement <4 x i64> undef, i64 %q, i32 0
|
|
%q1 = insertelement <4 x i64> %q0, i64 %q, i32 1
|
|
%q2 = insertelement <4 x i64> %q1, i64 %q, i32 2
|
|
%q3 = insertelement <4 x i64> %q2, i64 %q, i32 3
|
|
ret <4 x i64> %q3
|
|
}
|
|
|
|
define <8 x i16> @broadcast_mem_v4i16_v8i16(<4 x i16>* %ptr) {
|
|
; X32-LABEL: broadcast_mem_v4i16_v8i16:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
|
; X32-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: broadcast_mem_v4i16_v8i16:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpbroadcastq (%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
%load = load <4 x i16>, <4 x i16>* %ptr
|
|
%shuf = shufflevector <4 x i16> %load, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
|
ret <8 x i16> %shuf
|
|
}
|
|
|
|
define <16 x i16> @broadcast_mem_v4i16_v16i16(<4 x i16>* %ptr) {
|
|
; X32-LABEL: broadcast_mem_v4i16_v16i16:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
|
|
; X32-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
|
; X32-NEXT: vpbroadcastq %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: broadcast_mem_v4i16_v16i16:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
|
|
; X64-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
|
; X64-NEXT: vpbroadcastq %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%load = load <4 x i16>, <4 x i16>* %ptr
|
|
%shuf = shufflevector <4 x i16> %load, <4 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
|
ret <16 x i16> %shuf
|
|
}
|
|
|
|
; FIXME: Pointer adjusted broadcasts
|
|
|
|
define <16 x i8> @load_splat_16i8_16i8_1111111111111111(<16 x i8>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_16i8_16i8_1111111111111111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastb 1(%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_16i8_16i8_1111111111111111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastb 1(%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <16 x i8>, <16 x i8>* %ptr
|
|
%ret = shufflevector <16 x i8> %ld, <16 x i8> undef, <16 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <16 x i8> %ret
|
|
}
|
|
|
|
define <32 x i8> @load_splat_32i8_16i8_11111111111111111111111111111111(<16 x i8>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_32i8_16i8_11111111111111111111111111111111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastb 1(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_32i8_16i8_11111111111111111111111111111111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastb 1(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <16 x i8>, <16 x i8>* %ptr
|
|
%ret = shufflevector <16 x i8> %ld, <16 x i8> undef, <32 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <32 x i8> %ret
|
|
}
|
|
|
|
define <32 x i8> @load_splat_32i8_32i8_11111111111111111111111111111111(<32 x i8>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_32i8_32i8_11111111111111111111111111111111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastb 1(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_32i8_32i8_11111111111111111111111111111111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastb 1(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <32 x i8>, <32 x i8>* %ptr
|
|
%ret = shufflevector <32 x i8> %ld, <32 x i8> undef, <32 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <32 x i8> %ret
|
|
}
|
|
|
|
define <8 x i16> @load_splat_8i16_8i16_11111111(<8 x i16>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_8i16_8i16_11111111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastw 2(%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_8i16_8i16_11111111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastw 2(%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <8 x i16>, <8 x i16>* %ptr
|
|
%ret = shufflevector <8 x i16> %ld, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <8 x i16> %ret
|
|
}
|
|
|
|
define <16 x i16> @load_splat_16i16_8i16_1111111111111111(<8 x i16>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_16i16_8i16_1111111111111111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastw 2(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_16i16_8i16_1111111111111111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastw 2(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <8 x i16>, <8 x i16>* %ptr
|
|
%ret = shufflevector <8 x i16> %ld, <8 x i16> undef, <16 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <16 x i16> %ret
|
|
}
|
|
|
|
define <16 x i16> @load_splat_16i16_16i16_1111111111111111(<16 x i16>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_16i16_16i16_1111111111111111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vpbroadcastw 2(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_16i16_16i16_1111111111111111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastw 2(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <16 x i16>, <16 x i16>* %ptr
|
|
%ret = shufflevector <16 x i16> %ld, <16 x i16> undef, <16 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <16 x i16> %ret
|
|
}
|
|
|
|
define <4 x i32> @load_splat_4i32_4i32_1111(<4 x i32>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_4i32_4i32_1111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss 4(%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_4i32_4i32_1111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss 4(%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <4 x i32>, <4 x i32>* %ptr
|
|
%ret = shufflevector <4 x i32> %ld, <4 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
ret <4 x i32> %ret
|
|
}
|
|
|
|
define <8 x i32> @load_splat_8i32_4i32_33333333(<4 x i32>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_8i32_4i32_33333333:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss 12(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_8i32_4i32_33333333:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss 12(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <4 x i32>, <4 x i32>* %ptr
|
|
%ret = shufflevector <4 x i32> %ld, <4 x i32> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
|
|
ret <8 x i32> %ret
|
|
}
|
|
|
|
define <8 x i32> @load_splat_8i32_8i32_55555555(<8 x i32>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_8i32_8i32_55555555:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss 20(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_8i32_8i32_55555555:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss 20(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <8 x i32>, <8 x i32>* %ptr
|
|
%ret = shufflevector <8 x i32> %ld, <8 x i32> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
|
|
ret <8 x i32> %ret
|
|
}
|
|
|
|
define <4 x float> @load_splat_4f32_4f32_1111(<4 x float>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_4f32_4f32_1111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss 4(%eax), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_4f32_4f32_1111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss 4(%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <4 x float>, <4 x float>* %ptr
|
|
%ret = shufflevector <4 x float> %ld, <4 x float> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
ret <4 x float> %ret
|
|
}
|
|
|
|
define <8 x float> @load_splat_8f32_4f32_33333333(<4 x float>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_8f32_4f32_33333333:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss 12(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_8f32_4f32_33333333:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss 12(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <4 x float>, <4 x float>* %ptr
|
|
%ret = shufflevector <4 x float> %ld, <4 x float> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
|
|
ret <8 x float> %ret
|
|
}
|
|
|
|
define <8 x float> @load_splat_8f32_8f32_55555555(<8 x float>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_8f32_8f32_55555555:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastss 20(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_8f32_8f32_55555555:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss 20(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <8 x float>, <8 x float>* %ptr
|
|
%ret = shufflevector <8 x float> %ld, <8 x float> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
|
|
ret <8 x float> %ret
|
|
}
|
|
|
|
define <2 x i64> @load_splat_2i64_2i64_1111(<2 x i64>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_2i64_2i64_1111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_2i64_2i64_1111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastq 8(%rdi), %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <2 x i64>, <2 x i64>* %ptr
|
|
%ret = shufflevector <2 x i64> %ld, <2 x i64> undef, <2 x i32> <i32 1, i32 1>
|
|
ret <2 x i64> %ret
|
|
}
|
|
|
|
define <4 x i64> @load_splat_4i64_2i64_1111(<2 x i64>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_4i64_2i64_1111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastsd 8(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_4i64_2i64_1111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastsd 8(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <2 x i64>, <2 x i64>* %ptr
|
|
%ret = shufflevector <2 x i64> %ld, <2 x i64> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
ret <4 x i64> %ret
|
|
}
|
|
|
|
define <4 x i64> @load_splat_4i64_4i64_2222(<4 x i64>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_4i64_4i64_2222:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastsd 16(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_4i64_4i64_2222:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastsd 16(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <4 x i64>, <4 x i64>* %ptr
|
|
%ret = shufflevector <4 x i64> %ld, <4 x i64> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
|
|
ret <4 x i64> %ret
|
|
}
|
|
|
|
define <2 x double> @load_splat_2f64_2f64_1111(<2 x double>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_2f64_2f64_1111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_2f64_2f64_1111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <2 x double>, <2 x double>* %ptr
|
|
%ret = shufflevector <2 x double> %ld, <2 x double> undef, <2 x i32> <i32 1, i32 1>
|
|
ret <2 x double> %ret
|
|
}
|
|
|
|
define <4 x double> @load_splat_4f64_2f64_1111(<2 x double>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_4f64_2f64_1111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastsd 8(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_4f64_2f64_1111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastsd 8(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <2 x double>, <2 x double>* %ptr
|
|
%ret = shufflevector <2 x double> %ld, <2 x double> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
ret <4 x double> %ret
|
|
}
|
|
|
|
define <4 x double> @load_splat_4f64_4f64_2222(<4 x double>* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: load_splat_4f64_4f64_2222:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vbroadcastsd 16(%eax), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: load_splat_4f64_4f64_2222:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastsd 16(%rdi), %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%ld = load <4 x double>, <4 x double>* %ptr
|
|
%ret = shufflevector <4 x double> %ld, <4 x double> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
|
|
ret <4 x double> %ret
|
|
}
|
|
|
|
; make sure that we still don't support broadcast double into 128-bit vector
|
|
; this used to crash
|
|
define <2 x double> @I(double* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: I:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: I:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%q = load double, double* %ptr, align 4
|
|
%vecinit.i = insertelement <2 x double> undef, double %q, i32 0
|
|
%vecinit2.i = insertelement <2 x double> %vecinit.i, double %q, i32 1
|
|
ret <2 x double> %vecinit2.i
|
|
}
|
|
|
|
define <8 x i32> @V111(<8 x i32> %in) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: V111:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: vpbroadcastd LCPI29_0, %ymm1
|
|
; X32-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: V111:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
|
|
; X64-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%g = add <8 x i32> %in, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
ret <8 x i32> %g
|
|
}
|
|
|
|
define <8 x float> @V113(<8 x float> %in) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: V113:
|
|
; X32: ## BB#0: ## %entry
|
|
; X32-NEXT: vbroadcastss LCPI30_0, %ymm1
|
|
; X32-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: V113:
|
|
; X64: ## BB#0: ## %entry
|
|
; X64-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
|
|
; X64-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%g = fadd <8 x float> %in, <float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000>
|
|
ret <8 x float> %g
|
|
}
|
|
|
|
define <4 x float> @_e2(float* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: _e2:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss LCPI31_0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _e2:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss {{.*}}(%rip), %xmm0
|
|
; X64-NEXT: retq
|
|
%vecinit.i = insertelement <4 x float> undef, float 0xbf80000000000000, i32 0
|
|
%vecinit2.i = insertelement <4 x float> %vecinit.i, float 0xbf80000000000000, i32 1
|
|
%vecinit4.i = insertelement <4 x float> %vecinit2.i, float 0xbf80000000000000, i32 2
|
|
%vecinit6.i = insertelement <4 x float> %vecinit4.i, float 0xbf80000000000000, i32 3
|
|
ret <4 x float> %vecinit6.i
|
|
}
|
|
|
|
define <8 x i8> @_e4(i8* %ptr) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: _e4:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vmovaps {{.*#+}} xmm0 = [52,52,52,52,52,52,52,52]
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _e4:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vmovaps {{.*#+}} xmm0 = [52,52,52,52,52,52,52,52]
|
|
; X64-NEXT: retq
|
|
%vecinit0.i = insertelement <8 x i8> undef, i8 52, i32 0
|
|
%vecinit1.i = insertelement <8 x i8> %vecinit0.i, i8 52, i32 1
|
|
%vecinit2.i = insertelement <8 x i8> %vecinit1.i, i8 52, i32 2
|
|
%vecinit3.i = insertelement <8 x i8> %vecinit2.i, i8 52, i32 3
|
|
%vecinit4.i = insertelement <8 x i8> %vecinit3.i, i8 52, i32 4
|
|
%vecinit5.i = insertelement <8 x i8> %vecinit4.i, i8 52, i32 5
|
|
%vecinit6.i = insertelement <8 x i8> %vecinit5.i, i8 52, i32 6
|
|
%vecinit7.i = insertelement <8 x i8> %vecinit6.i, i8 52, i32 7
|
|
ret <8 x i8> %vecinit7.i
|
|
}
|
|
|
|
define void @crash() nounwind alwaysinline {
|
|
; X32-LABEL: crash:
|
|
; X32: ## BB#0: ## %WGLoopsEntry
|
|
; X32-NEXT: xorl %eax, %eax
|
|
; X32-NEXT: testb %al, %al
|
|
; X32-NEXT: je LBB33_1
|
|
; X32-NEXT: ## BB#2: ## %ret
|
|
; X32-NEXT: retl
|
|
; X32-NEXT: .p2align 4, 0x90
|
|
; X32-NEXT: LBB33_1: ## %footer349VF
|
|
; X32-NEXT: ## =>This Inner Loop Header: Depth=1
|
|
; X32-NEXT: jmp LBB33_1
|
|
;
|
|
; X64-LABEL: crash:
|
|
; X64: ## BB#0: ## %WGLoopsEntry
|
|
; X64-NEXT: xorl %eax, %eax
|
|
; X64-NEXT: testb %al, %al
|
|
; X64-NEXT: je LBB33_1
|
|
; X64-NEXT: ## BB#2: ## %ret
|
|
; X64-NEXT: retq
|
|
; X64-NEXT: .p2align 4, 0x90
|
|
; X64-NEXT: LBB33_1: ## %footer349VF
|
|
; X64-NEXT: ## =>This Inner Loop Header: Depth=1
|
|
; X64-NEXT: jmp LBB33_1
|
|
WGLoopsEntry:
|
|
br i1 undef, label %ret, label %footer329VF
|
|
|
|
footer329VF:
|
|
%A.0.inVF = fmul float undef, 6.553600e+04
|
|
%B.0.in407VF = fmul <8 x float> undef, <float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04>
|
|
%A.0VF = fptosi float %A.0.inVF to i32
|
|
%B.0408VF = fptosi <8 x float> %B.0.in407VF to <8 x i32>
|
|
%0 = and <8 x i32> %B.0408VF, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
|
|
%1 = and i32 %A.0VF, 65535
|
|
%temp1098VF = insertelement <8 x i32> undef, i32 %1, i32 0
|
|
%vector1099VF = shufflevector <8 x i32> %temp1098VF, <8 x i32> undef, <8 x i32> zeroinitializer
|
|
br i1 undef, label %preload1201VF, label %footer349VF
|
|
|
|
preload1201VF:
|
|
br label %footer349VF
|
|
|
|
footer349VF:
|
|
%2 = mul nsw <8 x i32> undef, %0
|
|
%3 = mul nsw <8 x i32> undef, %vector1099VF
|
|
br label %footer329VF
|
|
|
|
ret:
|
|
ret void
|
|
}
|
|
|
|
define <8 x i32> @_inreg0(i32 %scalar) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: _inreg0:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg0:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vmovd %edi, %xmm0
|
|
; X64-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%in = insertelement <8 x i32> undef, i32 %scalar, i32 0
|
|
%wide = shufflevector <8 x i32> %in, <8 x i32> undef, <8 x i32> zeroinitializer
|
|
ret <8 x i32> %wide
|
|
}
|
|
|
|
define <8 x float> @_inreg1(float %scalar) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: _inreg1:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg1:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%in = insertelement <8 x float> undef, float %scalar, i32 0
|
|
%wide = shufflevector <8 x float> %in, <8 x float> undef, <8 x i32> zeroinitializer
|
|
ret <8 x float> %wide
|
|
}
|
|
|
|
define <4 x float> @_inreg2(float %scalar) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: _inreg2:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg2:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%in = insertelement <4 x float> undef, float %scalar, i32 0
|
|
%wide = shufflevector <4 x float> %in, <4 x float> undef, <4 x i32> zeroinitializer
|
|
ret <4 x float> %wide
|
|
}
|
|
|
|
define <4 x double> @_inreg3(double %scalar) nounwind uwtable readnone ssp {
|
|
; X32-LABEL: _inreg3:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastsd {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg3:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%in = insertelement <4 x double> undef, double %scalar, i32 0
|
|
%wide = shufflevector <4 x double> %in, <4 x double> undef, <4 x i32> zeroinitializer
|
|
ret <4 x double> %wide
|
|
}
|
|
|
|
define <8 x float> @_inreg8xfloat(<8 x float> %a) {
|
|
; X32-LABEL: _inreg8xfloat:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg8xfloat:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> zeroinitializer
|
|
ret <8 x float> %b
|
|
}
|
|
|
|
define <4 x float> @_inreg4xfloat(<4 x float> %a) {
|
|
; X32-LABEL: _inreg4xfloat:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg4xfloat:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> zeroinitializer
|
|
ret <4 x float> %b
|
|
}
|
|
|
|
define <16 x i16> @_inreg16xi16(<16 x i16> %a) {
|
|
; X32-LABEL: _inreg16xi16:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vpbroadcastw %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg16xi16:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpbroadcastw %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <16 x i16> %a, <16 x i16> undef, <16 x i32> zeroinitializer
|
|
ret <16 x i16> %b
|
|
}
|
|
|
|
define <8 x i16> @_inreg8xi16(<8 x i16> %a) {
|
|
; X32-LABEL: _inreg8xi16:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vpbroadcastw %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg8xi16:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpbroadcastw %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <8 x i16> %a, <8 x i16> undef, <8 x i32> zeroinitializer
|
|
ret <8 x i16> %b
|
|
}
|
|
|
|
define <4 x i64> @_inreg4xi64(<4 x i64> %a) {
|
|
; X32-LABEL: _inreg4xi64:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg4xi64:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <4 x i64> %a, <4 x i64> undef, <4 x i32> zeroinitializer
|
|
ret <4 x i64> %b
|
|
}
|
|
|
|
define <2 x i64> @_inreg2xi64(<2 x i64> %a) {
|
|
; X32-LABEL: _inreg2xi64:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vpbroadcastq %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg2xi64:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpbroadcastq %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> zeroinitializer
|
|
ret <2 x i64> %b
|
|
}
|
|
|
|
define <4 x double> @_inreg4xdouble(<4 x double> %a) {
|
|
; X32-LABEL: _inreg4xdouble:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg4xdouble:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <4 x double> %a, <4 x double> undef, <4 x i32> zeroinitializer
|
|
ret <4 x double> %b
|
|
}
|
|
|
|
define <2 x double> @_inreg2xdouble(<2 x double> %a) {
|
|
; X32-LABEL: _inreg2xdouble:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg2xdouble:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> zeroinitializer
|
|
ret <2 x double> %b
|
|
}
|
|
|
|
define <8 x i32> @_inreg8xi32(<8 x i32> %a) {
|
|
; X32-LABEL: _inreg8xi32:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg8xi32:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <8 x i32> %a, <8 x i32> undef, <8 x i32> zeroinitializer
|
|
ret <8 x i32> %b
|
|
}
|
|
|
|
define <4 x i32> @_inreg4xi32(<4 x i32> %a) {
|
|
; X32-LABEL: _inreg4xi32:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg4xi32:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <4 x i32> %a, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
ret <4 x i32> %b
|
|
}
|
|
|
|
define <32 x i8> @_inreg32xi8(<32 x i8> %a) {
|
|
; X32-LABEL: _inreg32xi8:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vpbroadcastb %xmm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg32xi8:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpbroadcastb %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <32 x i8> %a, <32 x i8> undef, <32 x i32> zeroinitializer
|
|
ret <32 x i8> %b
|
|
}
|
|
|
|
define <16 x i8> @_inreg16xi8(<16 x i8> %a) {
|
|
; X32-LABEL: _inreg16xi8:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vpbroadcastb %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: _inreg16xi8:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vpbroadcastb %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%b = shufflevector <16 x i8> %a, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
ret <16 x i8> %b
|
|
}
|
|
|
|
; These tests check that a vbroadcast instruction is used when we have a splat
|
|
; formed from a concat_vectors (via the shufflevector) of two BUILD_VECTORs
|
|
; (via the insertelements).
|
|
|
|
define <8 x float> @splat_concat1(float %f) {
|
|
; X32-LABEL: splat_concat1:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: splat_concat1:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%1 = insertelement <4 x float> undef, float %f, i32 0
|
|
%2 = insertelement <4 x float> %1, float %f, i32 1
|
|
%3 = insertelement <4 x float> %2, float %f, i32 2
|
|
%4 = insertelement <4 x float> %3, float %f, i32 3
|
|
%5 = shufflevector <4 x float> %4, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
|
ret <8 x float> %5
|
|
}
|
|
|
|
define <8 x float> @splat_concat2(float %f) {
|
|
; X32-LABEL: splat_concat2:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: splat_concat2:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastss %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%1 = insertelement <4 x float> undef, float %f, i32 0
|
|
%2 = insertelement <4 x float> %1, float %f, i32 1
|
|
%3 = insertelement <4 x float> %2, float %f, i32 2
|
|
%4 = insertelement <4 x float> %3, float %f, i32 3
|
|
%5 = insertelement <4 x float> undef, float %f, i32 0
|
|
%6 = insertelement <4 x float> %5, float %f, i32 1
|
|
%7 = insertelement <4 x float> %6, float %f, i32 2
|
|
%8 = insertelement <4 x float> %7, float %f, i32 3
|
|
%9 = shufflevector <4 x float> %4, <4 x float> %8, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
ret <8 x float> %9
|
|
}
|
|
|
|
define <4 x double> @splat_concat3(double %d) {
|
|
; X32-LABEL: splat_concat3:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastsd {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: splat_concat3:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%1 = insertelement <2 x double> undef, double %d, i32 0
|
|
%2 = insertelement <2 x double> %1, double %d, i32 1
|
|
%3 = shufflevector <2 x double> %2, <2 x double> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
|
|
ret <4 x double> %3
|
|
}
|
|
|
|
define <4 x double> @splat_concat4(double %d) {
|
|
; X32-LABEL: splat_concat4:
|
|
; X32: ## BB#0:
|
|
; X32-NEXT: vbroadcastsd {{[0-9]+}}(%esp), %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: splat_concat4:
|
|
; X64: ## BB#0:
|
|
; X64-NEXT: vbroadcastsd %xmm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%1 = insertelement <2 x double> undef, double %d, i32 0
|
|
%2 = insertelement <2 x double> %1, double %d, i32 1
|
|
%3 = insertelement <2 x double> undef, double %d, i32 0
|
|
%4 = insertelement <2 x double> %3, double %d, i32 1
|
|
%5 = shufflevector <2 x double> %2, <2 x double> %4, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
ret <4 x double> %5
|
|
}
|
|
|
|
; Test cases for <rdar://problem/16074331>.
|
|
; Instruction selection for broacast instruction fails if
|
|
; the load cannot be folded into the broadcast.
|
|
; This happens if the load has initial one use but other uses are
|
|
; created later, or if selection DAG cannot prove that folding the
|
|
; load will not create a cycle in the DAG.
|
|
; Those test cases exerce the latter.
|
|
|
|
; CHECK-LABEL: isel_crash_16b
|
|
; CHECK: vpbroadcastb {{[^,]+}}, %xmm{{[0-9]+}}
|
|
; CHECK: ret
|
|
define void @isel_crash_16b(i8* %cV_R.addr) {
|
|
eintry:
|
|
%__a.addr.i = alloca <2 x i64>, align 16
|
|
%__b.addr.i = alloca <2 x i64>, align 16
|
|
%vCr = alloca <2 x i64>, align 16
|
|
store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
|
|
%tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
|
|
%tmp2 = load i8, i8* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <16 x i8> undef, i8 %tmp2, i32 0
|
|
%splat.splat = shufflevector <16 x i8> %splat.splatinsert, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
%tmp3 = bitcast <16 x i8> %splat.splat to <2 x i64>
|
|
store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
|
|
store <2 x i64> %tmp3, <2 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: isel_crash_32b
|
|
; CHECK: vpbroadcastb {{[^,]+}}, %ymm{{[0-9]+}}
|
|
; CHECK: ret
|
|
define void @isel_crash_32b(i8* %cV_R.addr) {
|
|
eintry:
|
|
%__a.addr.i = alloca <4 x i64>, align 16
|
|
%__b.addr.i = alloca <4 x i64>, align 16
|
|
%vCr = alloca <4 x i64>, align 16
|
|
store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
|
|
%tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
|
|
%tmp2 = load i8, i8* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <32 x i8> undef, i8 %tmp2, i32 0
|
|
%splat.splat = shufflevector <32 x i8> %splat.splatinsert, <32 x i8> undef, <32 x i32> zeroinitializer
|
|
%tmp3 = bitcast <32 x i8> %splat.splat to <4 x i64>
|
|
store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
|
|
store <4 x i64> %tmp3, <4 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: isel_crash_8w
|
|
; CHECK: vpbroadcastw {{[^,]+}}, %xmm{{[0-9]+}}
|
|
; CHECK: ret
|
|
define void @isel_crash_8w(i16* %cV_R.addr) {
|
|
entry:
|
|
%__a.addr.i = alloca <2 x i64>, align 16
|
|
%__b.addr.i = alloca <2 x i64>, align 16
|
|
%vCr = alloca <2 x i64>, align 16
|
|
store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
|
|
%tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
|
|
%tmp2 = load i16, i16* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <8 x i16> undef, i16 %tmp2, i32 0
|
|
%splat.splat = shufflevector <8 x i16> %splat.splatinsert, <8 x i16> undef, <8 x i32> zeroinitializer
|
|
%tmp3 = bitcast <8 x i16> %splat.splat to <2 x i64>
|
|
store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
|
|
store <2 x i64> %tmp3, <2 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: isel_crash_16w
|
|
; CHECK: vpbroadcastw {{[^,]+}}, %ymm{{[0-9]+}}
|
|
; CHECK: ret
|
|
define void @isel_crash_16w(i16* %cV_R.addr) {
|
|
eintry:
|
|
%__a.addr.i = alloca <4 x i64>, align 16
|
|
%__b.addr.i = alloca <4 x i64>, align 16
|
|
%vCr = alloca <4 x i64>, align 16
|
|
store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
|
|
%tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
|
|
%tmp2 = load i16, i16* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <16 x i16> undef, i16 %tmp2, i32 0
|
|
%splat.splat = shufflevector <16 x i16> %splat.splatinsert, <16 x i16> undef, <16 x i32> zeroinitializer
|
|
%tmp3 = bitcast <16 x i16> %splat.splat to <4 x i64>
|
|
store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
|
|
store <4 x i64> %tmp3, <4 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: isel_crash_4d
|
|
; CHECK: vbroadcastss {{[^,]+}}, %xmm{{[0-9]+}}
|
|
; CHECK: ret
|
|
define void @isel_crash_4d(i32* %cV_R.addr) {
|
|
entry:
|
|
%__a.addr.i = alloca <2 x i64>, align 16
|
|
%__b.addr.i = alloca <2 x i64>, align 16
|
|
%vCr = alloca <2 x i64>, align 16
|
|
store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
|
|
%tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
|
|
%tmp2 = load i32, i32* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <4 x i32> undef, i32 %tmp2, i32 0
|
|
%splat.splat = shufflevector <4 x i32> %splat.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
%tmp3 = bitcast <4 x i32> %splat.splat to <2 x i64>
|
|
store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
|
|
store <2 x i64> %tmp3, <2 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: isel_crash_8d
|
|
; CHECK: vbroadcastss {{[^,]+}}, %ymm{{[0-9]+}}
|
|
; CHECK: ret
|
|
define void @isel_crash_8d(i32* %cV_R.addr) {
|
|
eintry:
|
|
%__a.addr.i = alloca <4 x i64>, align 16
|
|
%__b.addr.i = alloca <4 x i64>, align 16
|
|
%vCr = alloca <4 x i64>, align 16
|
|
store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
|
|
%tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
|
|
%tmp2 = load i32, i32* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <8 x i32> undef, i32 %tmp2, i32 0
|
|
%splat.splat = shufflevector <8 x i32> %splat.splatinsert, <8 x i32> undef, <8 x i32> zeroinitializer
|
|
%tmp3 = bitcast <8 x i32> %splat.splat to <4 x i64>
|
|
store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
|
|
store <4 x i64> %tmp3, <4 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; X64-LABEL: isel_crash_2q
|
|
; X64: vpbroadcastq {{[^,]+}}, %xmm{{[0-9]+}}
|
|
; X64: ret
|
|
define void @isel_crash_2q(i64* %cV_R.addr) {
|
|
entry:
|
|
%__a.addr.i = alloca <2 x i64>, align 16
|
|
%__b.addr.i = alloca <2 x i64>, align 16
|
|
%vCr = alloca <2 x i64>, align 16
|
|
store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
|
|
%tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
|
|
%tmp2 = load i64, i64* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <2 x i64> undef, i64 %tmp2, i32 0
|
|
%splat.splat = shufflevector <2 x i64> %splat.splatinsert, <2 x i64> undef, <2 x i32> zeroinitializer
|
|
store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
|
|
store <2 x i64> %splat.splat, <2 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|
|
|
|
; X64-LABEL: isel_crash_4q
|
|
; X64: vbroadcastsd {{[^,]+}}, %ymm{{[0-9]+}}
|
|
; X64: ret
|
|
define void @isel_crash_4q(i64* %cV_R.addr) {
|
|
eintry:
|
|
%__a.addr.i = alloca <4 x i64>, align 16
|
|
%__b.addr.i = alloca <4 x i64>, align 16
|
|
%vCr = alloca <4 x i64>, align 16
|
|
store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
|
|
%tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
|
|
%tmp2 = load i64, i64* %cV_R.addr, align 4
|
|
%splat.splatinsert = insertelement <4 x i64> undef, i64 %tmp2, i32 0
|
|
%splat.splat = shufflevector <4 x i64> %splat.splatinsert, <4 x i64> undef, <4 x i32> zeroinitializer
|
|
store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
|
|
store <4 x i64> %splat.splat, <4 x i64>* %__b.addr.i, align 16
|
|
ret void
|
|
}
|