| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| ... | |
| * | ARM: peephole optimization to remove cmp instruction | Manman Ren | 2012-05-11 | 1 | -0/+34 |
| * | Revert: 156550 "ARM: peephole optimization to remove cmp instruction" | Manman Ren | 2012-05-10 | 1 | -34/+0 |
| * | ARM: peephole optimization to remove cmp instruction | Manman Ren | 2012-05-10 | 1 | -0/+34 |
| * | change the objectsize intrinsic signature: add a 3rd parameter to denote the ... | Nuno Lopes | 2012-05-09 | 1 | -2/+2 |
| * | Teach DAG combine to fold x-x to 0.0 when unsafe FP math is enabled. | Owen Anderson | 2012-05-07 | 1 | -0/+18 |
| * | Teach DAGCombine the same multiply-by-1.0 folding trick when doing FMAs, just... | Owen Anderson | 2012-05-02 | 1 | -0/+9 |
| * | Teach DAG combine that multiplication by 1.0 can always be constant folded. | Owen Anderson | 2012-05-02 | 1 | -0/+9 |
| * | Don't introduce illegal types when creating vmull operations. <rdar://11324364> | Bob Wilson | 2012-04-30 | 1 | -0/+74 |
| * | Fix the order of the operands in the llvm.fma intrinsic patterns for ARM, | Lang Hames | 2012-04-27 | 1 | -3/+3 |
| * | Implement a bastardized ABI. | Evan Cheng | 2012-04-27 | 1 | -1/+0 |
| * | Use VLD1 in NEON extenting-load patterns instead of VLDR. | Tim Northover | 2012-04-26 | 1 | -2/+6 |
| * | MachineBasicBlock::SplitCriticalEdge() should follow LLVM IR variant and refu... | Evan Cheng | 2012-04-24 | 1 | -0/+71 |
| * | Fix bad EXTRACT_SUBREG in instruction selection for extending-loads on NEON. | James Molloy | 2012-04-17 | 1 | -0/+14 |
| * | FileCheckize these tests. | Jakob Stoklund Olesen | 2012-04-16 | 2 | -6/+23 |
| * | Disable code placement for this test. | Jakob Stoklund Olesen | 2012-04-16 | 1 | -1/+2 |
| * | Flip the new block-placement pass to be on by default. | Chandler Carruth | 2012-04-16 | 2 | -2/+2 |
| * | On Darwin targets, only use vfma etc. if the source use fma() intrinsic expli... | Evan Cheng | 2012-04-13 | 1 | -1/+1 |
| * | Add more fused mul+add/sub patterns. rdar://10139676 | Evan Cheng | 2012-04-11 | 1 | -16/+54 |
| * | Match (fneg (fma) to vfnma. rdar://10139676 | Evan Cheng | 2012-04-11 | 1 | -6/+25 |
| * | Merge fma.ll into fusedMAC.ll | Evan Cheng | 2012-04-11 | 2 | -30/+28 |
| * | Move the constant-folding support for FP_ROUND in SelectionDAG from the one-o... | Owen Anderson | 2012-04-10 | 1 | -18/+2 |
| * | Handle llvm.fma.* intrinsics. rdar://10914096 | Evan Cheng | 2012-04-10 | 1 | -0/+30 |
| * | To ensure that we have more accurate line information for a block | Eric Christopher | 2012-04-10 | 1 | -1/+2 |
| * | Transform div to mul with reciprocal only when fp imm is legal. | Anton Korobeynikov | 2012-04-10 | 1 | -0/+31 |
| * | Add proper checks. | Evan Cheng | 2012-04-10 | 1 | -1/+5 |
| * | Fix a long standing tail call optimization bug. When a libcall is emitted | Evan Cheng | 2012-04-10 | 1 | -0/+21 |
| * | When performing a truncating store, it's possible to rearrange the data | Chad Rosier | 2012-04-09 | 3 | -6/+22 |
| * | Convert floating point division by a constant into multiplication by the | Duncan Sands | 2012-04-07 | 1 | -6/+6 |
| * | Allow negative immediates in ARM and Thumb2 compares. | Jakob Stoklund Olesen | 2012-04-06 | 1 | -0/+33 |
| * | An oversight when applying the patches for r150956 and r150957 to a vanilla t... | James Molloy | 2012-04-05 | 2 | -0/+76 |
| * | Pass the right sign to TLI->isLegalICmpImmediate. | Jakob Stoklund Olesen | 2012-04-05 | 1 | -0/+4 |
| * | Implement ARMBaseInstrInfo::commuteInstruction() for MOVCCr. | Jakob Stoklund Olesen | 2012-04-04 | 3 | -2/+65 |
| * | Allocate virtual registers in ascending order. | Jakob Stoklund Olesen | 2012-04-02 | 3 | -7/+22 |
| * | During two-address lowering, rescheduling an instruction does not untie | Lang Hames | 2012-04-02 | 1 | -0/+24 |
| * | This commit contains a few changes that had to go in together. | Nadav Rotem | 2012-04-01 | 1 | -1/+1 |
| * | ARM target should allow codegenprep to duplicate ret instructions to enable t... | Evan Cheng | 2012-03-30 | 1 | -0/+42 |
| * | Change the constant in this testcase so that it results in a constant pool | Lang Hames | 2012-03-29 | 1 | -3/+3 |
| * | ARM has a peephole optimization which looks for a def / use pair. The def | Evan Cheng | 2012-03-26 | 1 | -0/+33 |
| * | Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu | Eli Bendersky | 2012-03-25 | 1 | -8/+1 |
| * | Remove -enable-lsr-nested in time for 3.1. | Andrew Trick | 2012-03-22 | 1 | -640/+0 |
| * | [fast-isel] Fold "urem x, pow2" -> "and x, pow2-1". This should fix the 271% | Chad Rosier | 2012-03-22 | 1 | -0/+9 |
| * | Fix test case from r153135. | Chad Rosier | 2012-03-20 | 1 | -1/+1 |
| * | Perform mul combine when multiplying wiht negative constants. | Anton Korobeynikov | 2012-03-19 | 1 | -0/+42 |
| * | [fast-isel] Address Eli's comments for r152847. Specifically, add a test case | Chad Rosier | 2012-03-15 | 1 | -0/+19 |
| * | ARM case-insensitive checking for APSR_nzcv. | Jim Grosbach | 2012-03-15 | 3 | -4/+4 |
| * | Use vmov.f32 to materialize f32 consts on ARM. This relaxes constraints on | Lang Hames | 2012-03-15 | 2 | -27/+3 |
| * | DAG combine incorrectly optimize (i32 vextract (v4i16 load $addr), c) to | Evan Cheng | 2012-03-13 | 1 | -0/+16 |
| * | Extend r148086 to check for [r +/- reg] address mode. This fixes queens perfo... | Evan Cheng | 2012-03-06 | 1 | -4/+8 |
| * | Add <imp-def> operands when reloading into physregs. | Jakob Stoklund Olesen | 2012-03-06 | 1 | -0/+1 |
| * | Split fpscr into two registers: FPSCR and FPSCR_NZCV. | Lang Hames | 2012-03-06 | 1 | -0/+36 |
