RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 05:01:59 +01:00
Code Issues Projects Releases Wiki Activity

[ARM] Fixed an assumption of power-of-2 vector MVT

Browse Source 
I am about to introduce some non-power-of-2 width vector MVTs. This
commit fixes a power-of-2 assumption that my forthcoming change would
otherwise break, as shown by test/CodeGen/ARM/vcvt_combine.ll and
vdiv_combine.ll.

Differential Revision: https://reviews.llvm.org/D58927

Change-Id: I56a282e365d3874ab0621e5bdef98a612f702317
llvm-svn: 356341
This commit is contained in:
Tim Renouf 2019-03-17 20:48:54 +00:00
parent d3e664c5d8
commit 4ad3e0cc84
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
lib/Target/ARM/ARMISelLowering.cpp
View File

@ -12154,11 +12154,11 @@ static SDValue PerformVCVTCombine(SDNode *N, SelectionDAG &DAG,
MVT IntTy = N->getSimpleValueType(0).getVectorElementType();
uint32_t IntBits = IntTy.getSizeInBits();
unsigned NumLanes = Op.getValueType().getVectorNumElements();
if (FloatBits != 32 || IntBits > 32 || NumLanes > 4) {
if (FloatBits != 32 || IntBits > 32 || (NumLanes != 4 && NumLanes != 2)) {
// These instructions only exist converting from f32 to i32. We can handle
// smaller integers by generating an extra truncate, but larger ones would
// be lossy. We also can't handle more then 4 lanes, since these intructions
// only support v2i32/v4i32 types.
// be lossy. We also can't handle anything other than 2 or 4 lanes, since
// these intructions only support v2i32/v4i32 types.
return SDValue();
}
@ -12212,11 +12212,11 @@ static SDValue PerformVDIVCombine(SDNode *N, SelectionDAG &DAG,
MVT IntTy = Op.getOperand(0).getSimpleValueType().getVectorElementType();
uint32_t IntBits = IntTy.getSizeInBits();
unsigned NumLanes = Op.getValueType().getVectorNumElements();
if (FloatBits != 32 || IntBits > 32 || NumLanes > 4) {
if (FloatBits != 32 || IntBits > 32 || (NumLanes != 4 && NumLanes != 2)) {
// These instructions only exist converting from i32 to f32. We can handle
// smaller integers by generating an extra extend, but larger ones would
// be lossy. We also can't handle more then 4 lanes, since these intructions
// only support v2i32/v4i32 types.
// be lossy. We also can't handle anything other than 2 or 4 lanes, since
// these intructions only support v2i32/v4i32 types.
return SDValue();
}