RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-08 13:26:19 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

TRUNCATE constant folding - minor fix for rL233224

Browse Source 
Fix for test case found by James Molloy - TRUNCATE of constant build vectors can be more simply achieved by simply replacing with a new build vector node with the truncated value type - no need to touch the scalar operands at all.

llvm-svn: 235079
This commit is contained in:
Simon Pilgrim 2015-04-16 08:21:09 +00:00
parent 19c236a358
commit 969718c5af
2 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -2851,13 +2851,16 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL,
// FIXME: Entirely reasonable to perform folding of other unary
// operations here as the need arises.
break;
case ISD::TRUNCATE:
// Constant build vector truncation can be done with the original scalar
// operands but with a new build vector with the truncated value type.
return getNode(ISD::BUILD_VECTOR, DL, VT, BV->ops());
case ISD::FNEG:
case ISD::FABS:
case ISD::FCEIL:
case ISD::FTRUNC:
case ISD::FFLOOR:
case ISD::FP_EXTEND:
case ISD::TRUNCATE:
case ISD::UINT_TO_FP:
case ISD::SINT_TO_FP: {
// Let the above scalar folding handle the folding of each element.

21
test/CodeGen/AArch64/fold-constants.ll Normal file
View File

@ -0,0 +1,21 @@
; RUN: llc -mtriple=aarch64-linux-gnu -o - %s | FileCheck %s
define i64 @dotests_616() {
; CHECK-LABEL: dotests_616
; CHECK: movi d0, #0000000000000000
; CHECK-NEXT: umov w8, v0.b[2]
; CHECK-NEXT: sbfx w8, w8, #0, #1
; CHECK-NEXT: fmov s0, w8
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: ret
entry:
%0 = bitcast <2 x i64> zeroinitializer to <8 x i16>
%1 = and <8 x i16> zeroinitializer, %0
%2 = icmp ne <8 x i16> %1, zeroinitializer
%3 = extractelement <8 x i1> %2, i32 2
%vgetq_lane285 = sext i1 %3 to i16
%vset_lane = insertelement <4 x i16> undef, i16 %vgetq_lane285, i32 0
%4 = bitcast <4 x i16> %vset_lane to <1 x i64>
%vget_lane = extractelement <1 x i64> %4, i32 0
ret i64 %vget_lane
}