aboutsummaryrefslogtreecommitdiff
path: root/test/CodeGen/X86
AgeCommit message (Expand)Author
2011-08-17Introduce matching patterns for vbroadcast AVX instruction. The idea is toBruno Cardoso Lopes
2011-08-17Update test to not use the scalar type to splat from a loadBruno Cardoso Lopes
2011-08-17Now that we have a canonical way to handle 256-bit splats:Bruno Cardoso Lopes
2011-08-16Instead of always leaving the work to the generic legalizer whenBruno Cardoso Lopes
2011-08-15Fix PR10656. It's only profitable to use 128-bit inserts and extractsBruno Cardoso Lopes
2011-08-12The VPERM2F128 is a AVX instruction which permutes between two 256-bitBruno Cardoso Lopes
2011-08-11Add a dag combine to xform 256-bit shuffles into simple vectorBruno Cardoso Lopes
2011-08-11Fix the test added by Nadav in r137308. Make it more strict:Bruno Cardoso Lopes
2011-08-11Fix PR10492 by teaching MOVHLPS and MOVLPS mask matching to be more strict.Bruno Cardoso Lopes
2011-08-11[AVX] If the data which is going to be saved is already in two XMM registersNadav Rotem
2011-08-11add missing colon, thanks peter.Chris Lattner
2011-08-11fix PR10605 / rdar://9930964 by adding a pretty scary missed check.Chris Lattner
2011-08-11Splats for v8i32/v8f32 can be handled by VPERMILPSY. This was causingBruno Cardoso Lopes
2011-08-11Use the splat index to generate the desired shuffle. Otherwise weBruno Cardoso Lopes
2011-08-11Fix X86TargetLowering::LowerExternalSymbol so that it actually works in non-t...Eli Friedman
2011-08-10test/CodeGen/X86/opt-shuff-tstore.ll: Add explicit -mtriple=x86_64-linux.NAKAMURA Takumi
2011-08-10While extending definition range of a debug variable, consult lexical scopes ...Devang Patel
2011-08-10Fix the test. Add cpu target.Nadav Rotem
2011-08-10When performing a truncating store, it is sometimes possible to rearrange theNadav Rotem
2011-08-10The following X86 pattern is incorrect:Bruno Cardoso Lopes
2011-08-10Fix a bug in vpermilps mask checking. Fix PR10560Bruno Cardoso Lopes
2011-08-09Add 256-bit support for v8i32, v4i64 and v4f64 ISD::SELECT. Fix PR10556Bruno Cardoso Lopes
2011-08-09Add v16i16 and v32i8 store patternsBruno Cardoso Lopes
2011-08-09Use fp unpack instructions to unpack int types. Until we have AVX2, thisBruno Cardoso Lopes
2011-08-09Fix a couple ridiculous copy-paste errors. rdar://9914773 .Eli Friedman
2011-08-09Reapply a more appropriate solution than in r137114. AVX supportsBruno Cardoso Lopes
2011-08-09Revert r137114Bruno Cardoso Lopes
2011-08-09Handle sitofp between v4f64 <- v4i32. Fix PR10559Bruno Cardoso Lopes
2011-08-09Add support for avx vector fextendBruno Cardoso Lopes
2011-08-09Rename and tidy up testsBruno Cardoso Lopes
2011-08-09Add two patterns to match special vmovss and vmovsd cases. Also fixBruno Cardoso Lopes
2011-08-09Make LowerVSETCC aware of AVX types and add patterns to match them.Bruno Cardoso Lopes
2011-08-08Add support for several vector shifts operations while in AVX mode. Fix PR10581Bruno Cardoso Lopes
2011-08-08Don't clobber pending ST regs when FP regs are killed.Jakob Stoklund Olesen
2011-08-04Only access both operands of an INSERT_SUBVECTOR if it is an INSERT_SUBVECTOR.Bill Wendling
2011-08-03Handle IMPLICIT_DEF instructions in X86FloatingPoint.Jakob Stoklund Olesen
2011-08-02Assume .cfi_startproc is the first thing in a function. If the function isRafael Espindola
2011-08-02Make this kind of lowering to be supported by 256-bit instructions:Bruno Cardoso Lopes
2011-08-01Add v4f64 -> v2f32 fp_round support. Also add a testcase to exerciseBruno Cardoso Lopes
2011-08-01Since vectors with all ones can't be created with a 256-bit instruction,Bruno Cardoso Lopes
2011-07-30Revert "Don't check liveness of unallocatable registers."Jakob Stoklund Olesen
2011-07-29Don't check liveness of unallocatable registers.Jakob Stoklund Olesen
2011-07-29Fix two tests that I crashed in the previous commits. The mask eltsBruno Cardoso Lopes
2011-07-29Match VPERMIL masks more strictly and update the target specific maskBruno Cardoso Lopes
2011-07-29Add v8i32 and v4i64 vpermil patternsBruno Cardoso Lopes
2011-07-28Add patterns to generate copies for extract_subvector instead ofBruno Cardoso Lopes
2011-07-28Add a few patterns to match allzeros without having to use the fp unit.Bruno Cardoso Lopes
2011-07-28Add SINT_TO_FP and FP_TO_SINT support for v8i32 types. Also moveBruno Cardoso Lopes
2011-07-27The vpermilps and vpermilpd have different behaviour regarding theBruno Cardoso Lopes
2011-07-27It is quiet possible that inlined function body is split into multiple chunks...Devang Patel
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2026-01-17 23:49:17 +0000