Commit Graph

15 Commits

Author SHA1 Message Date
Simon Pilgrim 5b78c9d58d [SelectionDAG] Add partial sign-bit support to ComputeNumSignBits for BITCAST nodes
Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.

Handle the case where the sign bit extends to only part of the small elements.

llvm-svn: 340169
2018-08-20 13:05:48 +00:00
Simon Pilgrim 11bec5b80c [X86][SSE] Fix PACKSS bitcast test from rL340166
We need the signbits to extends to lower 16-bits of the even elements

llvm-svn: 340167
2018-08-20 11:47:15 +00:00
Simon Pilgrim cee9c64838 [X86][SSE] Add PACKSS test showing ComputeNumSignBits failure to handle a partial sign bits extension through a bitcast
llvm-svn: 340166
2018-08-20 11:10:12 +00:00
Simon Pilgrim 686090a45f [X86] Drop unnecessary exact qualifier from packss test
llvm-svn: 340165
2018-08-20 11:01:51 +00:00
Simon Pilgrim 5b936ec89e [SelectionDAG] Add basic demanded elements support to ComputeNumSignBits for BITCAST nodes
Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.

The next step would be to support cases where the large elements aren't all sign bits, and determine the small element equivalent based on the demanded elements.

llvm-svn: 340143
2018-08-19 17:47:50 +00:00
Simon Pilgrim 0fd72ab44f [X86][SSE] Add PACKSS test showing ComputeNumSignBits failure to handle demanded elts through a bitcast
llvm-svn: 340139
2018-08-19 16:01:47 +00:00
Simon Pilgrim ee7694442d [Utils][X86] Help update_llc_test_checks.py to recognise retl/retq to reduce CHECK duplication (PR35003)
This patch replaces the --x86_extra_scrub command line argument to automatically support a second level of regex-scrubbing if it improves the matching of nearly-identical code patterns. The argument '--extra_scrub' is there now to force extra matching if required.

This is mostly useful to help us share 32-bit/64-bit x86 vector tests which only differs by retl/retq instructions, but any scrubber can now technically support this, meaning test checks don't have to be needlessly obfuscated.

I've updated some of the existing checks that had been manually run with --x86_extra_scrub, to demonstrate the extra "ret{{[l|q]}}" scrub now only happens when useful, and re-run the sse42-intrinsics file to show extra matches - most sse/avx intrinsics files should be able to now share 32/64 checks.

Tested with the opt/analysis scripts as well which share common code - AFAICT the other update scripts use their own versions.

Differential Revision: https://reviews.llvm.org/D47485

llvm-svn: 333749
2018-06-01 13:37:01 +00:00
Francis Visoiu Mistrih 25528d6de7 [CodeGen] Unify MBB reference format in both MIR and debug output
As part of the unification of the debug format and the MIR format, print
MBB references as '%bb.5'.

The MIR printer prints the IR name of a MBB only for block definitions.

* find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g'
* find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g'
* find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g'
* grep -nr 'BB#' and fix

Differential Revision: https://reviews.llvm.org/D40422

llvm-svn: 319665
2017-12-04 17:18:51 +00:00
Simon Pilgrim 0a12c239b6 [X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB.
By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits.

llvm-svn: 316448
2017-10-24 15:38:16 +00:00
Simon Pilgrim 6bda996cab [X86][SSE] Regenerate PACKSS tests on 32 + 64-bit targets
llvm-svn: 316354
2017-10-23 17:50:40 +00:00
Dinar Temirbulatov aead31a36f [X86] SET0 to use XMM registers where possible PR26018 PR32862
Differential Revision: https://reviews.llvm.org/D35839

llvm-svn: 309298
2017-07-27 17:47:01 +00:00
Simon Pilgrim ca3a63a849 [X86][SSE42] Lower v2i64/v4i64 ASHR(X, 63) as PCMPGTQ(0, X)
Similar to what we do for vXi8 ASHR(X, 7), use SSE42's PCMPGTQ to splat the sign instead of using the PSRAD+PSHUFD.

Avoiding bitcasts this improves combines that utilize computeNumSignBits, permits memory folding and reduces pipe pressure. Although it does require a second register, given that this is a (cheap) zero register the impact is minimal.

Differential Revision: https://reviews.llvm.org/D32973

llvm-svn: 302525
2017-05-09 13:14:40 +00:00
Simon Pilgrim 49d7eda968 [SelectionDAG] Add ComputeNumSignBits support for CONCAT_VECTORS opcode
llvm-svn: 287541
2016-11-21 14:36:19 +00:00
Simon Pilgrim b7bbaa669b [X86][SSE] Allow PACKSS to be used to truncate any type of all/none sign bits input
At the moment we only use truncateVectorCompareWithPACKSS with direct vector comparison results (just one example of a known all/none signbits input).

This change relaxes the direct matching of a SETCC opcode by moving the logic up into SelectionDAG::ComputeNumSignBits and accepting any input with a known splatted signbit.

llvm-svn: 287535
2016-11-21 12:05:49 +00:00
Simon Pilgrim 0878d46416 [X86][SSE] Add some initial combine tests that could (should?) use PACKSS
llvm-svn: 287504
2016-11-20 21:12:49 +00:00