| Age | Commit message (Expand) | Author |
|---|
| 2012-09-06 | Disable stack coloring by default in order to resolve the i386 failures. | Nadav Rotem |
| 2012-09-06 | AVX2 optimization. | Elena Demikhovsky |
| 2012-09-06 | Fix the test by specifying an exact cpu model. | Nadav Rotem |
| 2012-09-06 | Add a new optimization pass: Stack Coloring, that merges disjoint static allo... | Nadav Rotem |
| 2012-09-06 | Add patterns for converting stores of subvector_extracts of lower 128-bits of... | Craig Topper |
| 2012-09-04 | Generic Bypass Slow Div | Preston Gurd |
| 2012-09-04 | This patch optimizes shuffle instruction - generates 2 instructions instead o... | Elena Demikhovsky |
| 2012-09-01 | Revert "Take account of boolean vector contents when promoting a build vector... | Pete Cooper |
| 2012-09-01 | llvm/test/CodeGen/X86/fp-fast.ll: Suppress FMA4 on AMD Bulldozer host, corres... | NAKAMURA Takumi |
| 2012-09-01 | Fix Atom bots for r163036. | Manman Ren |
| 2012-08-31 | SelectionDAG: when constructing VZEXT_LOAD from other loads, make sure its | Manman Ren |
| 2012-08-31 | Mark FMA4 instructions as commutable and add them to the folding tables. | Craig Topper |
| 2012-08-31 | Fix PR12359 | Michael Liao |
| 2012-08-31 | Mark FMA3 instructions as commutable so that the operands to the multiply par... | Craig Topper |
| 2012-08-31 | Add support for converting llvm.fma to fma4 instructions. | Craig Topper |
| 2012-08-31 | Don't enforce ordered inline asm operands. | Jakob Stoklund Olesen |
| 2012-08-31 | llvm/test/CodeGen/X86/vec_select.ll: Fix failure on xmm-less hosts, to add -m... | NAKAMURA Takumi |
| 2012-08-30 | Take account of boolean vector contents when promoting a build vector from i1... | Pete Cooper |
| 2012-08-30 | Try to make this test more generic to unbreak buildbots. | Owen Anderson |
| 2012-08-30 | Teach the DAG combiner to turn chains of FADDs (x+x+x+x+...) into FMULs by co... | Owen Anderson |
| 2012-08-30 | Introduce 'UseSSEx' to force SSE legacy encoding | Michael Liao |
| 2012-08-30 | Should put test case under test/ExecutionEngine/MCJIT/ | Michael Liao |
| 2012-08-30 | Fix PR13727 | Michael Liao |
| 2012-08-28 | The commutative flag is already correctly set within the multiclass. If we set | Bill Wendling |
| 2012-08-28 | Merge AVX_SET0PSY/AVX_SET0PDY/AVX2_SET0 into a single post-RA pseudo. | Craig Topper |
| 2012-08-28 | llvm/test/CodeGen/X86/pr12312.ll: Add -mtriple=x86_64-unknown-unknown. | NAKAMURA Takumi |
| 2012-08-28 | Fix PR12312 | Michael Liao |
| 2012-08-27 | llvm/test/CodeGen/X86/fma.ll: Add -march=x86, or two tests would fail on non-... | NAKAMURA Takumi |
| 2012-08-27 | llvm/test/CodeGen/X86/fma_patterns.ll: Add -mtriple=x86_64. It was incompatib... | NAKAMURA Takumi |
| 2012-08-27 | Commit test change for r162658. | Craig Topper |
| 2012-08-27 | FMA3 tests on bdver2 target for changes made in rev 162012. Also made | Anitha Boyapati |
| 2012-08-27 | Make sure that FMA3 is favored even when FMA4 is also enabled. Test case for ... | Craig Topper |
| 2012-08-20 | fix a case where all operands of BUILD_VECTOR are undefined | Michael Liao |
| 2012-08-19 | When unsafe math is used, we can use commutative FMAX and FMIN. In some cases | Nadav Rotem |
| 2012-08-18 | Reapply r162160 with a fix: Optimize Arith->Trunc->SETCC sequence to allow be... | Nadav Rotem |
| 2012-08-18 | Revert r162160 because it made a few buildbots fail. | Nadav Rotem |
| 2012-08-18 | The X86 backend has a number of optimizations for SETCC nodes which use | Nadav Rotem |
| 2012-08-17 | Make atomic load and store of pointers work. Tighten verification of atomic ... | Eli Friedman |
| 2012-08-17 | TargetLowering: Use the large shift amount during legalize types. The legaliz... | Benjamin Kramer |
| 2012-08-17 | Fix broken check lines. | Benjamin Kramer |
| 2012-08-15 | Remove invalid test. This test requires that dead basic blocks be kept | Bill Wendling |
| 2012-08-14 | fix PR11334 | Michael Liao |
| 2012-08-14 | During the CodeGenPrepare we often lower intrinsics (such as objsize) | Nadav Rotem |
| 2012-08-13 | Rename test since it's not linux-specific. | Bill Wendling |
| 2012-08-13 | Handle extra Tail predecessors in if-conversion. | Jakob Stoklund Olesen |
| 2012-08-13 | Fix failure on Atom bot due to r161769 | Manman Ren |
| 2012-08-13 | X86: move Int_CVTSD2SSrr, Int_CVTSI2SSrr, Int_CVTSI2SDrr, Int_CVTSS2SDrr from | Manman Ren |
| 2012-08-11 | fix PR13577, an issue introduced by r161687 | Michael Liao |
| 2012-08-11 | PR13578: Teach MachineCSE that instructions that use a constant register can ... | Benjamin Kramer |
| 2012-08-10 | X86: when we are auto-detecting the subtarget features, make sure we turn on | Manman Ren |
