Commit Graph

13 Commits

Author SHA1 Message Date
Matt Arsenault 0b382a7cb8 DAG: Avoid OOB when legalizing vector indexing
If a vector index is out of bounds, the result is supposed to be
undefined but is not undefined behavior. Change the legalization
for indexing the vector on the stack so that an out of bounds
index does not create an out of bounds memory access.

llvm-svn: 291604
2017-01-10 22:02:30 +00:00
Simon Pilgrim 8893bd95f0 [X86][SSE] Consistently set MOVD/MOVQ load/store/move instructions to integer domain
We are being inconsistent with these instructions (and all their variants.....) with a random mix of them using the default float domain.

Differential Revision: https://reviews.llvm.org/D27419

llvm-svn: 288902
2016-12-07 12:10:49 +00:00
Zvi Rackover 839d15a194 [X86] Optimization for replacing LEA with MOV at frame index elimination time
Summary:
Replace a LEA instruction of the form 'lea (%esp), %ebx' --> 'mov %esp, %ebx'

MOV is preferable over LEA because usually there are more issue-slots available to execute MOVs than LEAs. Latest processors also support zero-latency MOVs.

Fixes pr29022.

Reviewers: hfinkel, delena, igorb, myatsina, mkuper

Differential Revision: https://reviews.llvm.org/D24705

llvm-svn: 282385
2016-09-26 06:42:07 +00:00
Matthias Braun 152e7c8b12 VirtRegMap: Replace some identity copies with KILL instructions.
An identity COPY like this:
   %AL = COPY %AL, %EAX<imp-def>
has no semantic effect, but encodes liveness information: Further users
of %EAX only depend on this instruction even though it does not define
the full register.

Replace the COPY with a KILL instruction in those cases to maintain this
liveness information. (This reverts a small part of r238588 but this
time adds a comment explaining why a KILL instruction is useful).

llvm-svn: 274952
2016-07-09 00:19:07 +00:00
Simon Pilgrim 1ced2a6390 [X86][SSE] Added extra i8 extract element test
llvm-svn: 270379
2016-05-22 20:35:42 +00:00
Simon Pilgrim 26fbc75e93 [X86][SSE] Added constant index tests for 128-bit integer vector types
llvm-svn: 269604
2016-05-15 19:27:28 +00:00
Simon Pilgrim 73b496e35c [X86][SSE] Added variable index tests for 128-bit integer vector types
llvm-svn: 269603
2016-05-15 19:12:39 +00:00
Simon Pilgrim 91c2839864 Fixed typo in test
llvm-svn: 269602
2016-05-15 18:50:22 +00:00
Simon Pilgrim 5b68a0df04 [X86][SSE] Added extra extractelement tests
Added constant index tests for all 256-bit integer vector types (touching lower / upper 128-bits)

Added variable index tests for all 256-bit integer vector types

Added out-of-range index tests for all 256-bit integer vector types

llvm-svn: 269600
2016-05-15 18:22:21 +00:00
Simon Pilgrim 8fe1b1fd4f [X86][SSE] Regenerate extractelement tests
Added SSE2/AVX2 target tests

llvm-svn: 269595
2016-05-15 18:02:39 +00:00
Pawel Bylica 3b0adaf6b0 Readd the regression test from r236584. Calling convention fixed to linux.
llvm-svn: 236610
2015-05-06 16:43:21 +00:00
Pawel Bylica b25491faf4 Revert regression test from r236584.
Temporary remove a regression test added in r236584. It fails on Windows.

llvm-svn: 236586
2015-05-06 10:41:46 +00:00
Pawel Bylica 9f1fb9d1ef SelectionDAG: Handle out-of-bounds index in extract vector element
Summary: This patch correctly handles undef case of EXTRACT_VECTOR_ELT node where the element index is constant and not less than vector size.

Test Plan:
CodeGen for X86 test included.
Also one incorrect regression test fixed.

Reviewers: qcolombet, chandlerc, hfinkel

Reviewed By: hfinkel

Subscribers: hfinkel, llvm-commits

Differential Revision: http://reviews.llvm.org/D9250

llvm-svn: 236584
2015-05-06 10:19:14 +00:00