2014-10-03 08:36:29 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
|
2013-08-07 20:34:55 +08:00
|
|
|
|
|
|
|
define <16 x i32> @_inreg16xi32(i32 %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: _inreg16xi32:
|
|
|
|
; CHECK: ## BB#0:
|
[AVX512] Bring back vector-shuffle lowering support through broadcasts
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
2014-10-28 20:28:51 +08:00
|
|
|
; CHECK-NEXT: vpbroadcastd %edi, %zmm0
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-NEXT: retq
|
2013-08-07 20:34:55 +08:00
|
|
|
%b = insertelement <16 x i32> undef, i32 %a, i32 0
|
|
|
|
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x i32> %c
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i64> @_inreg8xi64(i64 %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: _inreg8xi64:
|
|
|
|
; CHECK: ## BB#0:
|
[AVX512] Bring back vector-shuffle lowering support through broadcasts
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
2014-10-28 20:28:51 +08:00
|
|
|
; CHECK-NEXT: vpbroadcastq %rdi, %zmm0
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-NEXT: retq
|
2013-08-07 20:34:55 +08:00
|
|
|
%b = insertelement <8 x i64> undef, i64 %a, i32 0
|
|
|
|
%c = shufflevector <8 x i64> %b, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
|
|
ret <8 x i64> %c
|
|
|
|
}
|
|
|
|
|
2014-12-10 02:45:30 +08:00
|
|
|
;CHECK-LABEL: _ss16xfloat_v4
|
|
|
|
;CHECK: vbroadcastss %xmm0, %zmm0
|
|
|
|
;CHECK: ret
|
|
|
|
define <16 x float> @_ss16xfloat_v4(<4 x float> %a) {
|
|
|
|
%b = shufflevector <4 x float> %a, <4 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x float> %b
|
|
|
|
}
|
|
|
|
|
2013-08-07 20:34:55 +08:00
|
|
|
define <16 x float> @_inreg16xfloat(float %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: _inreg16xfloat:
|
|
|
|
; CHECK: ## BB#0:
|
[AVX512] Bring back vector-shuffle lowering support through broadcasts
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
2014-10-28 20:28:51 +08:00
|
|
|
; CHECK-NEXT: vbroadcastss %xmm0, %zmm0
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-NEXT: retq
|
2013-08-07 20:34:55 +08:00
|
|
|
%b = insertelement <16 x float> undef, float %a, i32 0
|
|
|
|
%c = shufflevector <16 x float> %b, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x float> %c
|
|
|
|
}
|
|
|
|
|
2014-12-10 02:45:30 +08:00
|
|
|
;CHECK-LABEL: _ss16xfloat_mask:
|
|
|
|
;CHECK: vbroadcastss %xmm0, %zmm1 {%k1}
|
|
|
|
;CHECK: ret
|
|
|
|
define <16 x float> @_ss16xfloat_mask(float %a, <16 x float> %i, <16 x i32> %mask1) {
|
|
|
|
%mask = icmp ne <16 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <16 x float> undef, float %a, i32 0
|
|
|
|
%c = shufflevector <16 x float> %b, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
%r = select <16 x i1> %mask, <16 x float> %c, <16 x float> %i
|
|
|
|
ret <16 x float> %r
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _ss16xfloat_maskz:
|
|
|
|
;CHECK: vbroadcastss %xmm0, %zmm0 {%k1} {z}
|
|
|
|
;CHECK: ret
|
|
|
|
define <16 x float> @_ss16xfloat_maskz(float %a, <16 x i32> %mask1) {
|
|
|
|
%mask = icmp ne <16 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <16 x float> undef, float %a, i32 0
|
|
|
|
%c = shufflevector <16 x float> %b, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
%r = select <16 x i1> %mask, <16 x float> %c, <16 x float> zeroinitializer
|
|
|
|
ret <16 x float> %r
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _ss16xfloat_load:
|
|
|
|
;CHECK: vbroadcastss (%{{.*}}, %zmm
|
|
|
|
;CHECK: ret
|
|
|
|
define <16 x float> @_ss16xfloat_load(float* %a.ptr) {
|
2015-02-28 05:17:42 +08:00
|
|
|
%a = load float, float* %a.ptr
|
2014-12-10 02:45:30 +08:00
|
|
|
%b = insertelement <16 x float> undef, float %a, i32 0
|
|
|
|
%c = shufflevector <16 x float> %b, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x float> %c
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _ss16xfloat_mask_load:
|
|
|
|
;CHECK: vbroadcastss (%rdi), %zmm0 {%k1}
|
|
|
|
;CHECK: ret
|
|
|
|
define <16 x float> @_ss16xfloat_mask_load(float* %a.ptr, <16 x float> %i, <16 x i32> %mask1) {
|
2015-02-28 05:17:42 +08:00
|
|
|
%a = load float, float* %a.ptr
|
2014-12-10 02:45:30 +08:00
|
|
|
%mask = icmp ne <16 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <16 x float> undef, float %a, i32 0
|
|
|
|
%c = shufflevector <16 x float> %b, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
%r = select <16 x i1> %mask, <16 x float> %c, <16 x float> %i
|
|
|
|
ret <16 x float> %r
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _ss16xfloat_maskz_load:
|
|
|
|
;CHECK: vbroadcastss (%rdi), %zmm0 {%k1} {z}
|
|
|
|
;CHECK: ret
|
|
|
|
define <16 x float> @_ss16xfloat_maskz_load(float* %a.ptr, <16 x i32> %mask1) {
|
2015-02-28 05:17:42 +08:00
|
|
|
%a = load float, float* %a.ptr
|
2014-12-10 02:45:30 +08:00
|
|
|
%mask = icmp ne <16 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <16 x float> undef, float %a, i32 0
|
|
|
|
%c = shufflevector <16 x float> %b, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
%r = select <16 x i1> %mask, <16 x float> %c, <16 x float> zeroinitializer
|
|
|
|
ret <16 x float> %r
|
|
|
|
}
|
|
|
|
|
2013-08-07 20:34:55 +08:00
|
|
|
define <8 x double> @_inreg8xdouble(double %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: _inreg8xdouble:
|
|
|
|
; CHECK: ## BB#0:
|
[AVX512] Bring back vector-shuffle lowering support through broadcasts
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
2014-10-28 20:28:51 +08:00
|
|
|
; CHECK-NEXT: vbroadcastsd %xmm0, %zmm0
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-NEXT: retq
|
2013-08-07 20:34:55 +08:00
|
|
|
%b = insertelement <8 x double> undef, double %a, i32 0
|
|
|
|
%c = shufflevector <8 x double> %b, <8 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
ret <8 x double> %c
|
|
|
|
}
|
2013-08-11 20:29:16 +08:00
|
|
|
|
2014-12-10 02:45:30 +08:00
|
|
|
;CHECK-LABEL: _sd8xdouble_mask:
|
|
|
|
;CHECK: vbroadcastsd %xmm0, %zmm1 {%k1}
|
|
|
|
;CHECK: ret
|
|
|
|
define <8 x double> @_sd8xdouble_mask(double %a, <8 x double> %i, <8 x i32> %mask1) {
|
|
|
|
%mask = icmp ne <8 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <8 x double> undef, double %a, i32 0
|
|
|
|
%c = shufflevector <8 x double> %b, <8 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
%r = select <8 x i1> %mask, <8 x double> %c, <8 x double> %i
|
|
|
|
ret <8 x double> %r
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _sd8xdouble_maskz:
|
|
|
|
;CHECK: vbroadcastsd %xmm0, %zmm0 {%k1} {z}
|
|
|
|
;CHECK: ret
|
|
|
|
define <8 x double> @_sd8xdouble_maskz(double %a, <8 x i32> %mask1) {
|
|
|
|
%mask = icmp ne <8 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <8 x double> undef, double %a, i32 0
|
|
|
|
%c = shufflevector <8 x double> %b, <8 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
%r = select <8 x i1> %mask, <8 x double> %c, <8 x double> zeroinitializer
|
|
|
|
ret <8 x double> %r
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _sd8xdouble_load:
|
|
|
|
;CHECK: vbroadcastsd (%rdi), %zmm
|
|
|
|
;CHECK: ret
|
|
|
|
define <8 x double> @_sd8xdouble_load(double* %a.ptr) {
|
2015-02-28 05:17:42 +08:00
|
|
|
%a = load double, double* %a.ptr
|
2014-12-10 02:45:30 +08:00
|
|
|
%b = insertelement <8 x double> undef, double %a, i32 0
|
|
|
|
%c = shufflevector <8 x double> %b, <8 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
ret <8 x double> %c
|
|
|
|
}
|
|
|
|
|
|
|
|
;CHECK-LABEL: _sd8xdouble_mask_load:
|
|
|
|
;CHECK: vbroadcastsd (%rdi), %zmm0 {%k1}
|
|
|
|
;CHECK: ret
|
|
|
|
define <8 x double> @_sd8xdouble_mask_load(double* %a.ptr, <8 x double> %i, <8 x i32> %mask1) {
|
2015-02-28 05:17:42 +08:00
|
|
|
%a = load double, double* %a.ptr
|
2014-12-10 02:45:30 +08:00
|
|
|
%mask = icmp ne <8 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <8 x double> undef, double %a, i32 0
|
|
|
|
%c = shufflevector <8 x double> %b, <8 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
%r = select <8 x i1> %mask, <8 x double> %c, <8 x double> %i
|
|
|
|
ret <8 x double> %r
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x double> @_sd8xdouble_maskz_load(double* %a.ptr, <8 x i32> %mask1) {
|
|
|
|
; CHECK-LABEL: _sd8xdouble_maskz_load:
|
|
|
|
; CHECK: vbroadcastsd (%rdi), %zmm0 {%k1} {z}
|
|
|
|
; CHECK: ret
|
2015-02-28 05:17:42 +08:00
|
|
|
%a = load double, double* %a.ptr
|
2014-12-10 02:45:30 +08:00
|
|
|
%mask = icmp ne <8 x i32> %mask1, zeroinitializer
|
|
|
|
%b = insertelement <8 x double> undef, double %a, i32 0
|
|
|
|
%c = shufflevector <8 x double> %b, <8 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
%r = select <8 x i1> %mask, <8 x double> %c, <8 x double> zeroinitializer
|
|
|
|
ret <8 x double> %r
|
|
|
|
}
|
|
|
|
|
2013-08-11 20:29:16 +08:00
|
|
|
define <16 x i32> @_xmm16xi32(<16 x i32> %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: _xmm16xi32:
|
|
|
|
; CHECK: ## BB#0:
|
[AVX512] Bring back vector-shuffle lowering support through broadcasts
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
2014-10-28 20:28:51 +08:00
|
|
|
; CHECK-NEXT: vpbroadcastd %xmm0, %zmm0
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-NEXT: retq
|
2013-08-11 20:29:16 +08:00
|
|
|
%b = shufflevector <16 x i32> %a, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x i32> %b
|
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x float> @_xmm16xfloat(<16 x float> %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: _xmm16xfloat:
|
|
|
|
; CHECK: ## BB#0:
|
[AVX512] Bring back vector-shuffle lowering support through broadcasts
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
2014-10-28 20:28:51 +08:00
|
|
|
; CHECK-NEXT: vbroadcastss %xmm0, %zmm0
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-NEXT: retq
|
2013-08-11 20:29:16 +08:00
|
|
|
%b = shufflevector <16 x float> %a, <16 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x float> %b
|
|
|
|
}
|
2013-12-11 22:31:04 +08:00
|
|
|
|
|
|
|
define <16 x i32> @test_vbroadcast() {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: test_vbroadcast:
|
|
|
|
; CHECK: ## BB#0: ## %entry
|
|
|
|
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
|
|
|
|
; CHECK-NEXT: vcmpunordps %zmm0, %zmm0, %k1
|
|
|
|
; CHECK-NEXT: vpbroadcastd {{.*}}(%rip), %zmm0 {%k1} {z}
|
|
|
|
; CHECK-NEXT: knotw %k1, %k1
|
|
|
|
; CHECK-NEXT: vmovdqu32 %zmm0, %zmm0 {%k1} {z}
|
|
|
|
; CHECK-NEXT: retq
|
2013-12-11 22:31:04 +08:00
|
|
|
entry:
|
|
|
|
%0 = sext <16 x i1> zeroinitializer to <16 x i32>
|
|
|
|
%1 = fcmp uno <16 x float> undef, zeroinitializer
|
|
|
|
%2 = sext <16 x i1> %1 to <16 x i32>
|
|
|
|
%3 = select <16 x i1> %1, <16 x i32> %0, <16 x i32> %2
|
|
|
|
ret <16 x i32> %3
|
|
|
|
}
|
|
|
|
|
2014-07-30 09:30:51 +08:00
|
|
|
; We implement the set1 intrinsics with vector initializers. Verify that the
|
|
|
|
; IR generated will produce broadcasts at the end.
|
|
|
|
define <8 x double> @test_set1_pd(double %d) #2 {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: test_set1_pd:
|
|
|
|
; CHECK: ## BB#0: ## %entry
|
|
|
|
; CHECK-NEXT: vbroadcastsd %xmm0, %zmm0
|
|
|
|
; CHECK-NEXT: retq
|
2014-07-30 09:30:51 +08:00
|
|
|
entry:
|
|
|
|
%vecinit.i = insertelement <8 x double> undef, double %d, i32 0
|
|
|
|
%vecinit1.i = insertelement <8 x double> %vecinit.i, double %d, i32 1
|
|
|
|
%vecinit2.i = insertelement <8 x double> %vecinit1.i, double %d, i32 2
|
|
|
|
%vecinit3.i = insertelement <8 x double> %vecinit2.i, double %d, i32 3
|
|
|
|
%vecinit4.i = insertelement <8 x double> %vecinit3.i, double %d, i32 4
|
|
|
|
%vecinit5.i = insertelement <8 x double> %vecinit4.i, double %d, i32 5
|
|
|
|
%vecinit6.i = insertelement <8 x double> %vecinit5.i, double %d, i32 6
|
|
|
|
%vecinit7.i = insertelement <8 x double> %vecinit6.i, double %d, i32 7
|
|
|
|
ret <8 x double> %vecinit7.i
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i64> @test_set1_epi64(i64 %d) #2 {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: test_set1_epi64:
|
|
|
|
; CHECK: ## BB#0: ## %entry
|
|
|
|
; CHECK-NEXT: vpbroadcastq %rdi, %zmm0
|
|
|
|
; CHECK-NEXT: retq
|
2014-07-30 09:30:51 +08:00
|
|
|
entry:
|
|
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %d, i32 0
|
|
|
|
%vecinit1.i = insertelement <8 x i64> %vecinit.i, i64 %d, i32 1
|
|
|
|
%vecinit2.i = insertelement <8 x i64> %vecinit1.i, i64 %d, i32 2
|
|
|
|
%vecinit3.i = insertelement <8 x i64> %vecinit2.i, i64 %d, i32 3
|
|
|
|
%vecinit4.i = insertelement <8 x i64> %vecinit3.i, i64 %d, i32 4
|
|
|
|
%vecinit5.i = insertelement <8 x i64> %vecinit4.i, i64 %d, i32 5
|
|
|
|
%vecinit6.i = insertelement <8 x i64> %vecinit5.i, i64 %d, i32 6
|
|
|
|
%vecinit7.i = insertelement <8 x i64> %vecinit6.i, i64 %d, i32 7
|
|
|
|
ret <8 x i64> %vecinit7.i
|
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x float> @test_set1_ps(float %f) #2 {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: test_set1_ps:
|
|
|
|
; CHECK: ## BB#0: ## %entry
|
|
|
|
; CHECK-NEXT: vbroadcastss %xmm0, %zmm0
|
|
|
|
; CHECK-NEXT: retq
|
2014-07-30 09:30:51 +08:00
|
|
|
entry:
|
|
|
|
%vecinit.i = insertelement <16 x float> undef, float %f, i32 0
|
|
|
|
%vecinit1.i = insertelement <16 x float> %vecinit.i, float %f, i32 1
|
|
|
|
%vecinit2.i = insertelement <16 x float> %vecinit1.i, float %f, i32 2
|
|
|
|
%vecinit3.i = insertelement <16 x float> %vecinit2.i, float %f, i32 3
|
|
|
|
%vecinit4.i = insertelement <16 x float> %vecinit3.i, float %f, i32 4
|
|
|
|
%vecinit5.i = insertelement <16 x float> %vecinit4.i, float %f, i32 5
|
|
|
|
%vecinit6.i = insertelement <16 x float> %vecinit5.i, float %f, i32 6
|
|
|
|
%vecinit7.i = insertelement <16 x float> %vecinit6.i, float %f, i32 7
|
|
|
|
%vecinit8.i = insertelement <16 x float> %vecinit7.i, float %f, i32 8
|
|
|
|
%vecinit9.i = insertelement <16 x float> %vecinit8.i, float %f, i32 9
|
|
|
|
%vecinit10.i = insertelement <16 x float> %vecinit9.i, float %f, i32 10
|
|
|
|
%vecinit11.i = insertelement <16 x float> %vecinit10.i, float %f, i32 11
|
|
|
|
%vecinit12.i = insertelement <16 x float> %vecinit11.i, float %f, i32 12
|
|
|
|
%vecinit13.i = insertelement <16 x float> %vecinit12.i, float %f, i32 13
|
|
|
|
%vecinit14.i = insertelement <16 x float> %vecinit13.i, float %f, i32 14
|
|
|
|
%vecinit15.i = insertelement <16 x float> %vecinit14.i, float %f, i32 15
|
|
|
|
ret <16 x float> %vecinit15.i
|
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x i32> @test_set1_epi32(i32 %f) #2 {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: test_set1_epi32:
|
|
|
|
; CHECK: ## BB#0: ## %entry
|
|
|
|
; CHECK-NEXT: vpbroadcastd %edi, %zmm0
|
|
|
|
; CHECK-NEXT: retq
|
2014-07-30 09:30:51 +08:00
|
|
|
entry:
|
|
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %f, i32 0
|
|
|
|
%vecinit1.i = insertelement <16 x i32> %vecinit.i, i32 %f, i32 1
|
|
|
|
%vecinit2.i = insertelement <16 x i32> %vecinit1.i, i32 %f, i32 2
|
|
|
|
%vecinit3.i = insertelement <16 x i32> %vecinit2.i, i32 %f, i32 3
|
|
|
|
%vecinit4.i = insertelement <16 x i32> %vecinit3.i, i32 %f, i32 4
|
|
|
|
%vecinit5.i = insertelement <16 x i32> %vecinit4.i, i32 %f, i32 5
|
|
|
|
%vecinit6.i = insertelement <16 x i32> %vecinit5.i, i32 %f, i32 6
|
|
|
|
%vecinit7.i = insertelement <16 x i32> %vecinit6.i, i32 %f, i32 7
|
|
|
|
%vecinit8.i = insertelement <16 x i32> %vecinit7.i, i32 %f, i32 8
|
|
|
|
%vecinit9.i = insertelement <16 x i32> %vecinit8.i, i32 %f, i32 9
|
|
|
|
%vecinit10.i = insertelement <16 x i32> %vecinit9.i, i32 %f, i32 10
|
|
|
|
%vecinit11.i = insertelement <16 x i32> %vecinit10.i, i32 %f, i32 11
|
|
|
|
%vecinit12.i = insertelement <16 x i32> %vecinit11.i, i32 %f, i32 12
|
|
|
|
%vecinit13.i = insertelement <16 x i32> %vecinit12.i, i32 %f, i32 13
|
|
|
|
%vecinit14.i = insertelement <16 x i32> %vecinit13.i, i32 %f, i32 14
|
|
|
|
%vecinit15.i = insertelement <16 x i32> %vecinit14.i, i32 %f, i32 15
|
|
|
|
ret <16 x i32> %vecinit15.i
|
|
|
|
}
|
2014-08-13 08:30:05 +08:00
|
|
|
|
|
|
|
; We implement the scalar broadcast intrinsics with vector initializers.
|
|
|
|
; Verify that the IR generated will produce the broadcast at the end.
|
|
|
|
define <8 x double> @test_mm512_broadcastsd_pd(<2 x double> %a) {
|
2014-10-03 08:50:03 +08:00
|
|
|
; CHECK-LABEL: test_mm512_broadcastsd_pd:
|
|
|
|
; CHECK: ## BB#0: ## %entry
|
|
|
|
; CHECK-NEXT: vbroadcastsd %xmm0, %zmm0
|
|
|
|
; CHECK-NEXT: retq
|
2014-08-13 08:30:05 +08:00
|
|
|
entry:
|
|
|
|
%0 = extractelement <2 x double> %a, i32 0
|
|
|
|
%vecinit.i = insertelement <8 x double> undef, double %0, i32 0
|
|
|
|
%vecinit1.i = insertelement <8 x double> %vecinit.i, double %0, i32 1
|
|
|
|
%vecinit2.i = insertelement <8 x double> %vecinit1.i, double %0, i32 2
|
|
|
|
%vecinit3.i = insertelement <8 x double> %vecinit2.i, double %0, i32 3
|
|
|
|
%vecinit4.i = insertelement <8 x double> %vecinit3.i, double %0, i32 4
|
|
|
|
%vecinit5.i = insertelement <8 x double> %vecinit4.i, double %0, i32 5
|
|
|
|
%vecinit6.i = insertelement <8 x double> %vecinit5.i, double %0, i32 6
|
|
|
|
%vecinit7.i = insertelement <8 x double> %vecinit6.i, double %0, i32 7
|
|
|
|
ret <8 x double> %vecinit7.i
|
|
|
|
}
|
2015-05-18 15:06:23 +08:00
|
|
|
|
|
|
|
; CHECK-LABEL: test1
|
|
|
|
; CHECK: vbroadcastss
|
|
|
|
define <16 x float> @test1(<8 x float>%a) {
|
|
|
|
%res = shufflevector <8 x float> %a, <8 x float> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x float>%res
|
|
|
|
}
|
|
|
|
|
|
|
|
; CHECK-LABEL: test2
|
|
|
|
; CHECK: vbroadcastsd
|
|
|
|
define <8 x double> @test2(<4 x double>%a) {
|
|
|
|
%res = shufflevector <4 x double> %a, <4 x double> undef, <8 x i32> zeroinitializer
|
|
|
|
ret <8 x double>%res
|
|
|
|
}
|
|
|
|
|
|
|
|
; CHECK-LABEL: test3
|
|
|
|
; CHECK: vpbroadcastd
|
|
|
|
define <16 x i32> @test3(<8 x i32>%a) {
|
|
|
|
%res = shufflevector <8 x i32> %a, <8 x i32> undef, <16 x i32> zeroinitializer
|
|
|
|
ret <16 x i32>%res
|
|
|
|
}
|
|
|
|
|
|
|
|
; CHECK-LABEL: test4
|
|
|
|
; CHECK: vpbroadcastq
|
|
|
|
define <8 x i64> @test4(<4 x i64>%a) {
|
|
|
|
%res = shufflevector <4 x i64> %a, <4 x i64> undef, <8 x i32> zeroinitializer
|
|
|
|
ret <8 x i64>%res
|
|
|
|
}
|