Simon Pilgrim ab5200dfe9 [X86][SSE] Improve support for 128-bit vector sign extension ...

This patch improves support for sign extension of the lower lanes of vectors of integers by making use of the SSE41 pmovsx* sign extension instructions where possible, and optimizing the sign extension by shifts on pre-SSE41 targets (avoiding the use of i64 arithmetic shifts which require scalarization).

It converts SIGN_EXTEND nodes to SIGN_EXTEND_VECTOR_INREG where necessary, that more closely matches the pmovsx* instruction than the default approach of using SIGN_EXTEND_INREG which splits the operation (into an ANY_EXTEND lowered to a shuffle followed by shifts) making instruction matching difficult during lowering. Necessary support for SIGN_EXTEND_VECTOR_INREG has been added to the DAGCombiner.

Differential Revision: http://reviews.llvm.org/D9848

llvm-svn: 237885

2015-05-21 10:05:03 +00:00

..

CMakeLists.txt

…

DAGCombiner.cpp

[X86][SSE] Improve support for 128-bit vector sign extension

2015-05-21 10:05:03 +00:00

FastISel.cpp

[Fast-ISel] Don't mark the first use of a remat constant as killed.

2015-05-09 00:51:03 +00:00

FunctionLoweringInfo.cpp

Fix build warning

2015-05-20 23:28:03 +00:00

InstrEmitter.cpp

IR: Give 'DI' prefix to debug info metadata

2015-04-29 16:38:44 +00:00

InstrEmitter.h

…

LegalizeDAG.cpp

Add SDNodes for umin, umax, smin and smax.

2015-05-15 09:03:15 +00:00

LegalizeFloatTypes.cpp

Reapply r235977 "[DebugInfo] Add debug locations to constant SD nodes"

2015-04-28 14:05:47 +00:00

LegalizeIntegerTypes.cpp

Add SDNodes for umin, umax, smin and smax.

2015-05-15 09:03:15 +00:00

LegalizeTypes.cpp

Reapply r235977 "[DebugInfo] Add debug locations to constant SD nodes"

2015-04-28 14:05:47 +00:00

LegalizeTypes.h

Masked gather and scatter intrinsics - enabled codegen for KNL.

2015-05-03 07:12:25 +00:00

LegalizeTypesGeneric.cpp

Reapply r235977 "[DebugInfo] Add debug locations to constant SD nodes"

2015-04-28 14:05:47 +00:00

LegalizeVectorOps.cpp

Add SDNodes for umin, umax, smin and smax.

2015-05-15 09:03:15 +00:00

LegalizeVectorTypes.cpp

Add SDNodes for umin, umax, smin and smax.

2015-05-15 09:03:15 +00:00

LLVMBuild.txt

…

Makefile

…

ResourcePriorityQueue.cpp

unique_ptrify ResourcePriorityQueue::ResourceModel

2015-03-03 20:49:08 +00:00

ScheduleDAGFast.cpp

…

ScheduleDAGRRList.cpp

Use 'override/final' instead of 'virtual' for overridden methods

2015-04-11 02:11:45 +00:00

ScheduleDAGSDNodes.cpp

Prefer SmallVector::append/insert over push_back loops.

2015-02-17 15:29:18 +00:00

ScheduleDAGSDNodes.h

Use 'override/final' instead of 'virtual' for overridden methods

2015-04-11 02:11:45 +00:00

ScheduleDAGVLIW.cpp

Use 'override/final' instead of 'virtual' for overridden methods

2015-04-11 02:11:45 +00:00

SDNodeDbgValue.h

…

SelectionDAG.cpp

[X86][SSE] Improve support for 128-bit vector sign extension

2015-05-21 10:05:03 +00:00

SelectionDAGBuilder.cpp

Change Function::getIntrinsicID() to return an Intrinsic::ID. NFC.

2015-05-20 17:16:39 +00:00

SelectionDAGBuilder.h

[SelectionDAG] Delete SelectionDAGBuilder::removeValue. NFC.

2015-05-06 18:02:10 +00:00

SelectionDAGDumper.cpp

Add SDNodes for umin, umax, smin and smax.

2015-05-15 09:03:15 +00:00

SelectionDAGISel.cpp

Preserve the order of READ_REGISTER and WRITE_REGISTER

2015-05-18 16:42:10 +00:00

SelectionDAGPrinter.cpp

…

StatepointLowering.cpp

[StatepointLowering] Support of the gc.relocates for invoke statepoints.

2015-05-20 11:37:25 +00:00

StatepointLowering.h

[StatepointLowering] Support of the gc.relocates for invoke statepoints.

2015-05-20 11:37:25 +00:00

TargetLowering.cpp

DAGCombiner: Continue combining if FoldConstantArithmetic() fails.

2015-05-20 18:54:02 +00:00

TargetSelectionDAGInfo.cpp

…