forked from OSchip/llvm-project
[AVX512] add PSRAW Intrinsic
Differential Revision: http://reviews.llvm.org/D15850 llvm-svn: 256751
This commit is contained in:
parent
42011b2106
commit
000fca44a8
|
@ -2224,6 +2224,25 @@ let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
|
|||
Intrinsic<[llvm_v32i16_ty], [llvm_v32i16_ty,
|
||||
llvm_i8_ty, llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
|
||||
|
||||
def int_x86_avx512_mask_psra_w_128 : GCCBuiltin<"__builtin_ia32_psraw128_mask">,
|
||||
Intrinsic<[llvm_v8i16_ty], [llvm_v8i16_ty,
|
||||
llvm_v8i16_ty, llvm_v8i16_ty, llvm_i8_ty], [IntrNoMem]>;
|
||||
def int_x86_avx512_mask_psra_w_256 : GCCBuiltin<"__builtin_ia32_psraw256_mask">,
|
||||
Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
|
||||
llvm_v8i16_ty, llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
|
||||
def int_x86_avx512_mask_psra_w_512 : GCCBuiltin<"__builtin_ia32_psraw512_mask">,
|
||||
Intrinsic<[llvm_v32i16_ty], [llvm_v32i16_ty,
|
||||
llvm_v8i16_ty, llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
|
||||
def int_x86_avx512_mask_psra_wi_128 : GCCBuiltin<"__builtin_ia32_psrawi128_mask">,
|
||||
Intrinsic<[llvm_v8i16_ty], [llvm_v8i16_ty,
|
||||
llvm_i8_ty, llvm_v8i16_ty, llvm_i8_ty], [IntrNoMem]>;
|
||||
def int_x86_avx512_mask_psra_wi_256 : GCCBuiltin<"__builtin_ia32_psrawi256_mask">,
|
||||
Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
|
||||
llvm_i8_ty, llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
|
||||
def int_x86_avx512_mask_psra_wi_512 : GCCBuiltin<"__builtin_ia32_psrawi512_mask">,
|
||||
Intrinsic<[llvm_v32i16_ty], [llvm_v32i16_ty,
|
||||
llvm_i8_ty, llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
|
||||
|
||||
def int_x86_avx512_mask_psll_d : GCCBuiltin<"__builtin_ia32_pslld512_mask">,
|
||||
Intrinsic<[llvm_v16i32_ty], [llvm_v16i32_ty,
|
||||
llvm_v4i32_ty, llvm_v16i32_ty, llvm_i16_ty], [IntrNoMem]>;
|
||||
|
|
|
@ -1215,6 +1215,12 @@ static const IntrinsicData IntrinsicsWithoutChain[] = {
|
|||
X86_INTRINSIC_DATA(avx512_mask_psllv_q, INTR_TYPE_2OP_MASK, ISD::SHL, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_d, INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_q, INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_w_128, INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_w_256, INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_w_512, INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_wi_128, INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_wi_256, INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psra_wi_512, INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psrai_d, VSHIFT_MASK, X86ISD::VSRAI, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psrai_q, VSHIFT_MASK, X86ISD::VSRAI, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_psrav_d, INTR_TYPE_2OP_MASK, ISD::SRA, 0),
|
||||
|
|
|
@ -2926,3 +2926,43 @@ define <32 x i16>@test_int_x86_avx512_mask_psrlv32hi(<32 x i16> %x0, <32 x i16>
|
|||
%res4 = add <32 x i16> %res3, %res2
|
||||
ret <32 x i16> %res4
|
||||
}
|
||||
|
||||
declare <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16>, <8 x i16>, <32 x i16>, i32)
|
||||
|
||||
define <32 x i16>@test_int_x86_avx512_mask_psra_w_512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_psra_w_512:
|
||||
; CHECK: ## BB#0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: vpsraw %xmm1, %zmm0, %zmm2 {%k1}
|
||||
; CHECK-NEXT: vpsraw %xmm1, %zmm0, %zmm3 {%k1} {z}
|
||||
; CHECK-NEXT: vpsraw %xmm1, %zmm0, %zmm0
|
||||
; CHECK-NEXT: vpaddw %zmm3, %zmm2, %zmm1
|
||||
; CHECK-NEXT: vpaddw %zmm0, %zmm1, %zmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 %x3)
|
||||
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
|
||||
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 -1)
|
||||
%res3 = add <32 x i16> %res, %res1
|
||||
%res4 = add <32 x i16> %res3, %res2
|
||||
ret <32 x i16> %res4
|
||||
}
|
||||
|
||||
declare <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16>, i8, <32 x i16>, i32)
|
||||
|
||||
define <32 x i16>@test_int_x86_avx512_mask_psra_wi_512(<32 x i16> %x0, i8 %x1, <32 x i16> %x2, i32 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_psra_wi_512:
|
||||
; CHECK: ## BB#0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpsraw $3, %zmm0, %zmm1 {%k1}
|
||||
; CHECK-NEXT: vpsraw $3, %zmm0, %zmm2 {%k1} {z}
|
||||
; CHECK-NEXT: vpsraw $3, %zmm0, %zmm0
|
||||
; CHECK-NEXT: vpaddw %zmm2, %zmm1, %zmm1
|
||||
; CHECK-NEXT: vpaddw %zmm0, %zmm1, %zmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 %x3)
|
||||
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i8 3, <32 x i16> zeroinitializer, i32 %x3)
|
||||
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 -1)
|
||||
%res3 = add <32 x i16> %res, %res1
|
||||
%res4 = add <32 x i16> %res3, %res2
|
||||
ret <32 x i16> %res4
|
||||
}
|
||||
|
|
|
@ -4632,3 +4632,85 @@ define <8 x i16>@test_int_x86_avx512_mask_psrlv8_hi(<8 x i16> %x0, <8 x i16> %x1
|
|||
%res4 = add <8 x i16> %res3, %res2
|
||||
ret <8 x i16> %res4
|
||||
}
|
||||
|
||||
declare <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16>, <8 x i16>, <8 x i16>, i8)
|
||||
|
||||
define <8 x i16>@test_int_x86_avx512_mask_psra_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_psra_w_128:
|
||||
; CHECK: ## BB#0:
|
||||
; CHECK-NEXT: movzbl %dil, %eax
|
||||
; CHECK-NEXT: kmovw %eax, %k1
|
||||
; CHECK-NEXT: vpsraw %xmm1, %xmm0, %xmm2 {%k1}
|
||||
; CHECK-NEXT: vpsraw %xmm1, %xmm0, %xmm3 {%k1} {z}
|
||||
; CHECK-NEXT: vpsraw %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vpaddw %xmm3, %xmm2, %xmm1
|
||||
; CHECK-NEXT: vpaddw %xmm0, %xmm1, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
|
||||
%res1 = call <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> zeroinitializer, i8 %x3)
|
||||
%res2 = call <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 -1)
|
||||
%res3 = add <8 x i16> %res, %res1
|
||||
%res4 = add <8 x i16> %res3, %res2
|
||||
ret <8 x i16> %res4
|
||||
}
|
||||
|
||||
declare <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16>, i8, <8 x i16>, i8)
|
||||
|
||||
define <8 x i16>@test_int_x86_avx512_mask_psra_wi_128(<8 x i16> %x0, i8 %x1, <8 x i16> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_psra_wi_128:
|
||||
; CHECK: ## BB#0:
|
||||
; CHECK-NEXT: movzbl %sil, %eax
|
||||
; CHECK-NEXT: kmovw %eax, %k1
|
||||
; CHECK-NEXT: vpsraw $3, %xmm0, %xmm1 {%k1}
|
||||
; CHECK-NEXT: vpsraw $3, %xmm0, %xmm2 {%k1} {z}
|
||||
; CHECK-NEXT: vpsraw $3, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vpaddw %xmm2, %xmm1, %xmm1
|
||||
; CHECK-NEXT: vpaddw %xmm0, %xmm1, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i8 3, <8 x i16> %x2, i8 %x3)
|
||||
%res1 = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i8 3, <8 x i16> zeroinitializer, i8 %x3)
|
||||
%res2 = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i8 3, <8 x i16> %x2, i8 -1)
|
||||
%res3 = add <8 x i16> %res, %res1
|
||||
%res4 = add <8 x i16> %res3, %res2
|
||||
ret <8 x i16> %res4
|
||||
}
|
||||
|
||||
declare <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16>, <8 x i16>, <16 x i16>, i16)
|
||||
|
||||
define <16 x i16>@test_int_x86_avx512_mask_psra_w_256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> %x2, i16 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_psra_w_256:
|
||||
; CHECK: ## BB#0:
|
||||
; CHECK-NEXT: kmovw %edi, %k1
|
||||
; CHECK-NEXT: vpsraw %xmm1, %ymm0, %ymm2 {%k1}
|
||||
; CHECK-NEXT: vpsraw %xmm1, %ymm0, %ymm3 {%k1} {z}
|
||||
; CHECK-NEXT: vpsraw %xmm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vpaddw %ymm3, %ymm2, %ymm1
|
||||
; CHECK-NEXT: vpaddw %ymm0, %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> %x2, i16 %x3)
|
||||
%res1 = call <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> zeroinitializer, i16 %x3)
|
||||
%res2 = call <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> %x2, i16 -1)
|
||||
%res3 = add <16 x i16> %res, %res1
|
||||
%res4 = add <16 x i16> %res3, %res2
|
||||
ret <16 x i16> %res4
|
||||
}
|
||||
|
||||
declare <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16>, i8, <16 x i16>, i16)
|
||||
|
||||
define <16 x i16>@test_int_x86_avx512_mask_psra_wi_256(<16 x i16> %x0, i8 %x1, <16 x i16> %x2, i16 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_psra_wi_256:
|
||||
; CHECK: ## BB#0:
|
||||
; CHECK-NEXT: kmovw %esi, %k1
|
||||
; CHECK-NEXT: vpsraw $3, %ymm0, %ymm1 {%k1}
|
||||
; CHECK-NEXT: vpsraw $3, %ymm0, %ymm2 {%k1} {z}
|
||||
; CHECK-NEXT: vpsraw $3, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vpaddw %ymm2, %ymm1, %ymm1
|
||||
; CHECK-NEXT: vpaddw %ymm0, %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i8 3, <16 x i16> %x2, i16 %x3)
|
||||
%res1 = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i8 3, <16 x i16> zeroinitializer, i16 %x3)
|
||||
%res2 = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i8 3, <16 x i16> %x2, i16 -1)
|
||||
%res3 = add <16 x i16> %res, %res1
|
||||
%res4 = add <16 x i16> %res3, %res2
|
||||
ret <16 x i16> %res4
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue