1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 02:33:06 +01:00

[ARM][MVE] Tail predicate VML[A|S]LDAV

Make the non-exchanging versions of the multiply add/sub instructions
validForTailPredication.

Differential Revision: https://reviews.llvm.org/D77648
This commit is contained in:
Sam Parker 2020-04-09 07:51:33 +01:00
parent 05f943ebcd
commit f0c31cc496
3 changed files with 49 additions and 2 deletions

View File

@ -909,6 +909,11 @@ class MVE_VMLAMLSDAV<string iname, string suffix, dag iops, string cstr,
let Inst{3-1} = Qm{2-0};
let Inst{0} = bit_0;
let horizontalReduction = 1;
// Allow tail predication for non-exchanging versions. As this is also a
// horizontalReduction, ARMLowOverheadLoops will also have to check that
// the vector operands contain zeros in their false lanes for the instruction
// to be properly valid.
let validForTailPredication = !eq(X, 0);
}
multiclass MVE_VMLAMLSDAV_A<string iname, string x, MVEVectorVTInfo VTI,
@ -1068,6 +1073,11 @@ class MVE_VMLALDAVBase<string iname, string suffix, dag iops, string cstr,
let Inst{3-1} = Qm{2-0};
let Inst{0} = bit_0;
let horizontalReduction = 1;
// Allow tail predication for non-exchanging versions. As this is also a
// horizontalReduction, ARMLowOverheadLoops will also have to check that
// the vector operands contain zeros in their false lanes for the instruction
// to be properly valid.
let validForTailPredication = !eq(X, 0);
let hasSideEffects = 0;
}

View File

@ -393,7 +393,8 @@ namespace ARMII {
// in an IT block).
ThumbArithFlagSetting = 1 << 19,
// Whether an instruction can be included in an MVE tail-predicated loop.
// Whether an instruction can be included in an MVE tail-predicated loop,
// though extra validity checks may need to be performed too.
ValidForTailPredication = 1 << 20,
// Whether an instruction writes to the top/bottom half of a vector element

View File

@ -368,7 +368,7 @@ TEST(MachineInstructionRetainsPreviousHalfElement, IsCorrect) {
// descriptions. Currently we, conservatively, disallow:
// - cross beat carries.
// - complex operations.
// - horizontal operations.
// - horizontal operations with exchange.
// - byte swapping.
// - interleaved memory instructions.
// TODO: Add to this list once we can handle them safely.
@ -531,6 +531,42 @@ TEST(MachineInstrValidTailPredication, IsCorrect) {
case MVE_VMINu16:
case MVE_VMINu32:
case MVE_VMINu8:
case MVE_VMLADAVas16:
case MVE_VMLADAVas32:
case MVE_VMLADAVas8:
case MVE_VMLADAVau16:
case MVE_VMLADAVau32:
case MVE_VMLADAVau8:
case MVE_VMLADAVs16:
case MVE_VMLADAVs32:
case MVE_VMLADAVs8:
case MVE_VMLADAVu16:
case MVE_VMLADAVu32:
case MVE_VMLADAVu8:
case MVE_VMLALDAVs16:
case MVE_VMLALDAVs32:
case MVE_VMLALDAVu16:
case MVE_VMLALDAVu32:
case MVE_VMLALDAVas16:
case MVE_VMLALDAVas32:
case MVE_VMLALDAVau16:
case MVE_VMLALDAVau32:
case MVE_VMLSDAVas16:
case MVE_VMLSDAVas32:
case MVE_VMLSDAVas8:
case MVE_VMLSDAVs16:
case MVE_VMLSDAVs32:
case MVE_VMLSDAVs8:
case MVE_VMLSLDAVas16:
case MVE_VMLSLDAVas32:
case MVE_VMLSLDAVs16:
case MVE_VMLSLDAVs32:
case MVE_VRMLALDAVHas32:
case MVE_VRMLALDAVHau32:
case MVE_VRMLALDAVHs32:
case MVE_VRMLALDAVHu32:
case MVE_VRMLSLDAVHas32:
case MVE_VRMLSLDAVHs32:
case MVE_VMLAS_qr_s16:
case MVE_VMLAS_qr_s32:
case MVE_VMLAS_qr_s8: