maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AVX-512] Improve lowering of inserting a single element into lowest element of a 512-bit vector of zeroes by using vmovq/vmovd/vmovss/vmovsd. 

llvm-svn: 277965
This commit is contained in:
Craig Topper 2016-08-07 21:52:59 +00:00
parent da178822c2
commit f44423120f
4 changed files with 35 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -6691,12 +6691,8 @@ X86TargetLowering::LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const {
if (ExtVT == MVT::i32 || ExtVT == MVT::f32 || ExtVT == MVT::f64 ||
(ExtVT == MVT::i64 && Subtarget.is64Bit())) {
if (VT.is512BitVector()) {
SDValue ZeroVec = getZeroVector(VT, Subtarget, DAG, dl);
return DAG.getNode(ISD::INSERT_VECTOR_ELT, dl, VT, ZeroVec,
Item, DAG.getIntPtrConstant(0, dl));
}
assert((VT.is128BitVector() || VT.is256BitVector()) &&
assert((VT.is128BitVector() || VT.is256BitVector() ||
VT.is512BitVector()) &&
"Expected an SSE value type!");
Item = DAG.getNode(ISD::SCALAR_TO_VECTOR, dl, VT, Item);
// Turn it into a MOVL (i.e. movss, movsd, or movd) to a zero vector.
@ -12091,6 +12087,16 @@ static SDValue lower512BitVectorShuffle(const SDLoc &DL, ArrayRef<int> Mask,
assert(Subtarget.hasAVX512() &&
"Cannot lower 512-bit vectors w/ basic ISA!");
// If we have a single input to the zero element, insert that into V1 if we
// can do so cheaply.
int NumElts = Mask.size();
int NumV2Elements = count_if(Mask, [NumElts](int M) { return M >= NumElts; });
if (NumV2Elements == 1 && Mask[0] >= NumElts)
if (SDValue Insertion = lowerVectorShuffleAsElementInsertion(
DL, VT, V1, V2, Mask, Subtarget, DAG))
return Insertion;
// Check for being able to broadcast a single element.
if (SDValue Broadcast =
lowerVectorShuffleAsBroadcast(DL, VT, V1, V2, Mask, Subtarget, DAG))

8
llvm/lib/Target/X86/X86InstrAVX512.td
View File

@ -3305,6 +3305,10 @@ let Predicates = [HasAVX512] in {
def : Pat<(v4i64 (X86vzmovl (insert_subvector undef,
(v2i64 (scalar_to_vector GR64:$src)),(iPTR 0)))),
(SUBREG_TO_REG (i64 0), (VMOV64toPQIZrr GR64:$src), sub_xmm)>;
def : Pat<(v8i64 (X86vzmovl (insert_subvector undef,
(v2i64 (scalar_to_vector GR64:$src)),(iPTR 0)))),
(SUBREG_TO_REG (i64 0), (VMOV64toPQIZrr GR64:$src), sub_xmm)>;
}
// AVX 128-bit movd/movq instruction write zeros in the high 128-bit part.
let AddedComplexity = 20 in {
@ -3330,6 +3334,10 @@ let Predicates = [HasAVX512] in {
(v4i32 (scalar_to_vector GR32:$src)),(iPTR 0)))),
(SUBREG_TO_REG (i32 0), (VMOVDI2PDIZrr GR32:$src), sub_xmm)>;
def : Pat<(v16i32 (X86vzmovl (insert_subvector undef,
(v4i32 (scalar_to_vector GR32:$src)),(iPTR 0)))),
(SUBREG_TO_REG (i32 0), (VMOVDI2PDIZrr GR32:$src), sub_xmm)>;
// Use regular 128-bit instructions to match 512-bit scalar_to_vec+zext.
def : Pat<(v8i64 (X86vzload addr:$src)),
(SUBREG_TO_REG (i64 0), (VMOVZPQILo2PQIZrm addr:$src), sub_xmm)>;

11
llvm/test/CodeGen/X86/vector-shuffle-512-v16.ll
View File

@ -297,3 +297,14 @@ define <16 x float> @shuffle_v16f32_00_01_10_10_04_05_14_14_08_09_18_18_0c_0d_1c
%shuffle = shufflevector <16 x float> %a, <16 x float> %b, <16 x i32> <i32 0, i32 1, i32 16, i32 16, i32 4, i32 5, i32 20, i32 20, i32 8, i32 9, i32 24, i32 24, i32 12, i32 13, i32 28, i32 28>
ret <16 x float> %shuffle
}
define <16 x i32> @insert_mem_and_zero_v16i32(i32* %ptr) {
; ALL-LABEL: insert_mem_and_zero_v16i32:
; ALL: # BB#0:
; ALL-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; ALL-NEXT: retq
%a = load i32, i32* %ptr
%v = insertelement <16 x i32> undef, i32 %a, i32 0
%shuffle = shufflevector <16 x i32> %v, <16 x i32> zeroinitializer, <16 x i32> <i32 0, 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, i32 31>
ret <16 x i32> %shuffle
}

18
llvm/test/CodeGen/X86/vector-shuffle-512-v8.ll
View File

@ -147,20 +147,15 @@ define <8 x double> @shuffle_v8f64_06000000(<8 x double> %a, <8 x double> %b) {
define <8 x double> @shuffle_v8f64_70000000(<8 x double> %a, <8 x double> %b) {
; AVX512F-LABEL: shuffle_v8f64_70000000:
; AVX512F: # BB#0:
; AVX512F-NEXT: vpxord %zmm1, %zmm1, %zmm1
; AVX512F-NEXT: movl $7, %eax
; AVX512F-NEXT: vpinsrq $0, %rax, %xmm1, %xmm2
; AVX512F-NEXT: vinserti32x4 $0, %xmm2, %zmm1, %zmm1
; AVX512F-NEXT: vmovq %rax, %xmm1
; AVX512F-NEXT: vpermpd %zmm0, %zmm1, %zmm0
; AVX512F-NEXT: retq
;
; AVX512F-32-LABEL: shuffle_v8f64_70000000:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-32-NEXT: movl $7, %eax
; AVX512F-32-NEXT: vpinsrd $0, %eax, %xmm1, %xmm1
; AVX512F-32-NEXT: vpxord %zmm2, %zmm2, %zmm2
; AVX512F-32-NEXT: vinserti32x4 $0, %xmm1, %zmm2, %zmm1
; AVX512F-32-NEXT: vmovd %eax, %xmm1
; AVX512F-32-NEXT: vpermpd %zmm0, %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@ -1116,20 +1111,15 @@ define <8 x i64> @shuffle_v8i64_70000000(<8 x i64> %a, <8 x i64> %b) {
;
; AVX512F-LABEL: shuffle_v8i64_70000000:
; AVX512F: # BB#0:
; AVX512F-NEXT: vpxord %zmm1, %zmm1, %zmm1
; AVX512F-NEXT: movl $7, %eax
; AVX512F-NEXT: vpinsrq $0, %rax, %xmm1, %xmm2
; AVX512F-NEXT: vinserti32x4 $0, %xmm2, %zmm1, %zmm1
; AVX512F-NEXT: vmovq %rax, %xmm1
; AVX512F-NEXT: vpermq %zmm0, %zmm1, %zmm0
; AVX512F-NEXT: retq
;
; AVX512F-32-LABEL: shuffle_v8i64_70000000:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-32-NEXT: movl $7, %eax
; AVX512F-32-NEXT: vpinsrd $0, %eax, %xmm1, %xmm1
; AVX512F-32-NEXT: vpxord %zmm2, %zmm2, %zmm2
; AVX512F-32-NEXT: vinserti32x4 $0, %xmm1, %zmm2, %zmm1
; AVX512F-32-NEXT: vmovd %eax, %xmm1
; AVX512F-32-NEXT: vpermq %zmm0, %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>