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

[RISCV] Convert (splat_vector (load)) to vlse with 0 stride. 

We already do this for splat nodes that carry a VL, but not for
splats that use VLMAX.

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D115483
This commit is contained in:
Craig Topper 2021-12-14 08:58:16 -08:00
parent aedb328a4d
commit 7598ac5ec5
2 changed files with 24 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
View File

@ -1515,6 +1515,7 @@ void RISCVDAGToDAGISel::Select(SDNode *Node) {
ReplaceNode(Node, Extract.getNode());
return;
}
case ISD::SPLAT_VECTOR:
case RISCVISD::VMV_V_X_VL:
case RISCVISD::VFMV_V_F_VL: {
// Try to match splat of a scalar load to a strided load with stride of x0.
@ -1531,7 +1532,10 @@ void RISCVDAGToDAGISel::Select(SDNode *Node) {
break;
SDValue VL;
selectVLOp(Node->getOperand(1), VL);
if (Node->getOpcode() == ISD::SPLAT_VECTOR)
VL = CurDAG->getTargetConstant(RISCV::VLMaxSentinel, DL, XLenVT);
else
selectVLOp(Node->getOperand(1), VL);
unsigned Log2SEW = Log2_32(VT.getScalarSizeInBits());
SDValue SEW = CurDAG->getTargetConstant(Log2SEW, DL, XLenVT);

19
llvm/test/CodeGen/RISCV/rvv/vsplats-fp.ll
View File

@ -105,3 +105,22 @@ define <vscale x 8 x double> @vsplat_zero_nxv8f64() {
%splat = shufflevector <vscale x 8 x double> %head, <vscale x 8 x double> undef, <vscale x 8 x i32> zeroinitializer
ret <vscale x 8 x double> %splat
}
; Test that we fold this to a vlse with 0 stride.
define <vscale x 8 x float> @vsplat_load_nxv8f32(float* %ptr) {
; RV32V-LABEL: vsplat_load_nxv8f32:
; RV32V: # %bb.0:
; RV32V-NEXT: vsetvli a1, zero, e32, m4, ta, mu
; RV32V-NEXT: vlse32.v v8, (a0), zero
; RV32V-NEXT: ret
;
; RV64V-LABEL: vsplat_load_nxv8f32:
; RV64V: # %bb.0:
; RV64V-NEXT: vsetvli a1, zero, e32, m4, ta, mu
; RV64V-NEXT: vlse32.v v8, (a0), zero
; RV64V-NEXT: ret
%f = load float, float* %ptr
%head = insertelement <vscale x 8 x float> undef, float %f, i32 0
%splat = shufflevector <vscale x 8 x float> %head, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
ret <vscale x 8 x float> %splat
}