Simon Pilgrim
42caa7142b
[X86][AVX] Allow 32-bit targets to peek through subvectors to extract constant splats for vXi64 shifts.
...
llvm-svn: 303009
2017-05-14 11:46:26 +00:00
Simon Pilgrim
fb7acbc016
[SelectionDAG] Added support for EXTRACT_SUBVECTOR/CONCAT_VECTORS demandedelts in ComputeNumSignBits
...
llvm-svn: 302997
2017-05-13 22:10:58 +00:00
Simon Pilgrim
e3e00995f1
[X86][SSE] Test showing missing EXTRACT_SUBVECTOR/CONCAT_VECTORS demandedelts support in ComputeNumSignBits
...
llvm-svn: 302994
2017-05-13 21:50:18 +00:00
Simon Pilgrim
dd6308c45b
[SelectionDAG] Add VECTOR_SHUFFLE support to ComputeNumSignBits
...
llvm-svn: 302993
2017-05-13 19:57:10 +00:00
Simon Pilgrim
64ce41df9a
[X86][SSE] Test showing inability of ComputeNumSignBits to resolve shuffles
...
llvm-svn: 302992
2017-05-13 17:41:07 +00:00
Simon Pilgrim
89841b2f1f
[DAGCombiner] Add ComputeNumSignBits vector demanded elements support to ASHR and INSERT_VECTOR_ELT (reapplied)
...
Reapplied r299221 after fix for nondeterminism in ThinLTO builder (rL301599), with extra check for implicit truncation of inserted element.
llvm-svn: 301644
2017-04-28 13:21:18 +00:00
Galina Kistanova
8f924ac9d8
Temporarily revert r299221 to fix nondeterminism in ThinLTO builder.
...
llvm-svn: 300783
2017-04-19 23:16:14 +00:00
Simon Pilgrim
ef98e5126a
[DAGCombiner] Add ComputeNumSignBits vector demanded elements support to ASHR and INSERT_VECTOR_ELT
...
Followup to D31311
llvm-svn: 299221
2017-03-31 14:21:50 +00:00
Simon Pilgrim
d5a95baa98
[X86][SSE] Add extra computeNumSignBits test case for D31311.
...
llvm-svn: 298774
2017-03-25 15:43:36 +00:00
Simon Pilgrim
d401591143
[X86][SSE] Extract elements from narrower shuffle masks.
...
Add support for widening narrow shuffle masks so we can directly extract from the relevant input vector of the shuffle.
llvm-svn: 298616
2017-03-23 16:09:34 +00:00
Simon Pilgrim
36d17fd2e8
[X86][SSE] Add computeNumSignBits test for sitofp of (extended) i64 extracted element
...
llvm-svn: 298592
2017-03-23 13:18:09 +00:00
Simon Pilgrim
aa329ec2e1
[X86][SSE] Fix load folding for (V)CVTDQ2PD
...
This only requires a 64-bit memory source, not the whole 128-bits. But the 128-bit case is still supported via X86InstrInfo::foldMemoryOperandImpl
llvm-svn: 297523
2017-03-10 22:35:07 +00:00
Simon Pilgrim
0f8a406c91
[SelectionDAG] Add support for BUILD_VECTOR to ComputeNumSignBits
...
llvm-svn: 297492
2017-03-10 18:36:46 +00:00
Simon Pilgrim
67bb89515f
[X86][SSE] Added tests showing missed truncations for sitofp conversion
...
SelectionDAG::ComputeNumSignBits is poor at build_vector handling, meaning that we can't see that all the vXi64 sources are in fact sign extended i32 or smaller.
llvm-svn: 297486
2017-03-10 18:01:53 +00:00
