aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/X86
Commit message (Expand)AuthorAgeFilesLines
...
* [ms-inline asm] Add back-end test case for r166632. Make sure we emit theChad Rosier2012-10-241-0/+23
* Special calling conventions for Intel OpenCL built-in library.Elena Demikhovsky2012-10-242-0/+200
* Teach DAG combine to fold (buildvec (Xint2fp x)) to (Xint2fp (buildvec x))Michael Liao2012-10-241-0/+14
* Add custom conversion from v2u32 to v2f32 in 32-bit modeMichael Liao2012-10-241-0/+11
* Change x86_fastcallcc to require inreg markers. This allows it to knownRafael Espindola2012-10-243-5/+5
* Fix PR14161Michael Liao2012-10-231-0/+38
* Enable lowering ZERO_EXTEND/ANY_EXTEND to PMOVZX from SSE4.1Michael Liao2012-10-238-21/+16
* Lower BUILD_VECTOR to SHUFFLE + INSERT_VECTOR_ELT for X86Michael Liao2012-10-191-0/+15
* Clear unknown mem ops when merging stack slots (pr14090)Sebastian Pop2012-10-181-0/+76
* In SimplifySelectOps we pulled two loads through a select node despite the fa...Nadav Rotem2012-10-181-0/+61
* Revert part of r166049 back and enable test case in r166125.Michael Liao2012-10-171-1/+0
* Disable extract-concat test case temporarilyMichael Liao2012-10-171-1/+2
* Revert r166049Michael Liao2012-10-171-18/+0
* Teach DAG combine to fold (extract_subvec (concat v1, ..) i) to v_iMichael Liao2012-10-171-0/+17
* Fix setjmp on models with non-Small code model nor non-Static relocation modelMichael Liao2012-10-171-2/+16
* Avoid rematerializing a redef immediately after the old def.Jakob Stoklund Olesen2012-10-161-0/+23
* Revert r166046 "Switch back to the old coalescer for now to fix the 32 bit bit"Jakob Stoklund Olesen2012-10-161-23/+0
* Teach DAG combine to fold (trunc (fptoXi x)) to (fptoXi x)Michael Liao2012-10-161-0/+18
* Switch back to the old coalescer for now to fix the 32 bit bitRafael Espindola2012-10-161-0/+23
* Reapply r165661, Patch by Shuxin Yang <shuxin.llvm@gmail.com>.NAKAMURA Takumi2012-10-161-0/+16
* Fix the cpu name and add -verify-machineinstrs.Rafael Espindola2012-10-161-1/+1
* misched: Added handleMove support for updating all kill flags, not just for a...Andrew Trick2012-10-161-2/+27
* Add __builtin_setjmp/_longjmp supprt in X86 backendMichael Liao2012-10-151-0/+46
* Check output of the misched unit testsAndrew Trick2012-10-151-1/+2
* Add a cpu to try to fix the atom builder.Rafael Espindola2012-10-151-1/+1
* Add testcase for pr14088.Rafael Espindola2012-10-151-0/+25
* misched tests: add a triple to speculatively fix windows builders.Andrew Trick2012-10-151-2/+2
* misched: ILP scheduler for experimental heuristics.Andrew Trick2012-10-151-0/+25
* X86: Fix accidentally swapped operands.Benjamin Kramer2012-10-131-4/+4
* X86: Promote i8 cmov when both operands are coming from truncates of the same...Benjamin Kramer2012-10-131-0/+13
* Fix buildbots: -misched=shuffle is only available in +Asserts builds.Jakob Stoklund Olesen2012-10-121-0/+1
* Use a transposed algorithm for handleMove().Jakob Stoklund Olesen2012-10-121-0/+73
* Fix coalescing with IMPLICIT_DEF values.Jakob Stoklund Olesen2012-10-121-0/+103
* Pass an explicit operand number to addLiveIns.Jakob Stoklund Olesen2012-10-111-0/+32
* Revert r165661, "Patch by Shuxin Yang <shuxin.llvm@gmail.com>."NAKAMURA Takumi2012-10-111-16/+0
* Patch by Shuxin Yang <shuxin.llvm@gmail.com>.Nadav Rotem2012-10-101-0/+16
* Specify CPU model to avoid breaking ATOM buildsMichael Liao2012-10-102-4/+4
* Add support for FP_ROUND from v2f64 to v2f32Michael Liao2012-10-102-14/+98
* When expanding atomic load arith instructions, do not lose target flags. rdar...Evan Cheng2012-10-091-42/+58
* Don't crash on extra evil irreducible control flow.Jakob Stoklund Olesen2012-10-081-0/+75
* X86: fcmov doesn't handle all possible EFLAGS, fall back to a branch for the ...Benjamin Kramer2012-10-071-0/+451
* Follow up to r165072. Try a different approach: only move the load when it's ...Evan Cheng2012-10-051-0/+36
* When merging connsecutive stores, use vectors to store the constant zero.Nadav Rotem2012-10-041-3/+35
* [ms-inline asm] Add support in the X86AsmPrinter for printing memory referencesChad Rosier2012-10-031-0/+14
* Fix a cycle in the DAG. In this code we replace multiple loads with a single ...Nadav Rotem2012-10-031-0/+31
* A DAGCombine optimization for mergeing consecutive stores to memory. The opti...Nadav Rotem2012-10-031-0/+273
* The early if conversion pass is ready to be used as an opt-in.Jakob Stoklund Olesen2012-10-031-1/+1
* Fix a serious X86 instruction selection bug. InEvan Cheng2012-10-021-0/+16
* Make sure to put our sret argument into %rax on x86-64. Fixes PR13563!Nick Lewycky2012-10-021-0/+13
* Fix PR13991: legalizing an overflowing multiplication operation is harder thanDuncan Sands2012-10-021-0/+14
generated by cgit v1.1 at 2025-04-01 04:53:12 +0000