| Commit message (Expand) | Author | Age | Files | Lines |
| * | [mips][microMIPS] Implement ADD.fmt, SUB.fmt, MOV.fmt, MUL.fmt, DIV.fmt, MADD... | Zoran Jovanovic | 2015-09-05 | 3 | -4/+159 |
| * | [PowerPC] Fix and(or(x, c1), c2) -> rlwimi generation | Hal Finkel | 2015-09-05 | 1 | -3/+15 |
| * | [PowerPC] Enable interleaved-access vectorization | Hal Finkel | 2015-09-04 | 2 | -1/+43 |
| * | [PowerPC] Always use aggressive interleaving on the A2 | Hal Finkel | 2015-09-03 | 1 | -0/+7 |
| * | [PowerPC] Try harder to find a base+offset when looking for consecutive accesses | Hal Finkel | 2015-09-03 | 1 | -7/+23 |
| * | [PowerPC] Include the permutation cost for unaligned vector loads | Hal Finkel | 2015-09-03 | 1 | -8/+12 |
| * | [PowerPC] Compute the MMO offset for an unaligned load with signed arithmetic | Hal Finkel | 2015-09-03 | 1 | -1/+2 |
| * | [AArch64] Improve ISel using across lane addition reduction. | Chad Rosier | 2015-09-03 | 1 | -0/+99 |
| * | Sink COFF.h MC include into .cpp files | Reid Kleckner | 2015-09-03 | 1 | -0/+1 |
| * | Revert "[AArch64] Improve load/store optimizer to handle LDUR + LDR." | Chad Rosier | 2015-09-03 | 1 | -77/+21 |
| * | [x86] enable machine combiner reassociations for scalar 'xor' insts | Sanjay Patel | 2015-09-03 | 1 | -0/+4 |
| * | check for fastness before merging in DAGCombiner::MergeConsecutiveStores() | Sanjay Patel | 2015-09-03 | 1 | -1/+4 |
| * | [AArch64] Improve load/store optimizer to handle LDUR + LDR. | Chad Rosier | 2015-09-03 | 1 | -21/+77 |
| * | [AArch64] Reuse MayLoad. NFC. | Chad Rosier | 2015-09-03 | 1 | -1/+1 |
| * | [mips] Added support for the div, divu, ddiv and ddivu macros which use traps... | Daniel Sanders | 2015-09-03 | 5 | -1/+182 |
| * | AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflic... | Igor Breger | 2015-09-03 | 5 | -117/+54 |
| * | [X86] Require 32-byte alignment for 32-byte VMOVNTs. | Ahmed Bougacha | 2015-09-02 | 1 | -2/+4 |
| * | [X86] Cleanup nontemporal fragments. NFCI. | Ahmed Bougacha | 2015-09-02 | 1 | -15/+6 |
| * | [PowerPC] Cleanup cost model for unaligned vector loads/stores | Hal Finkel | 2015-09-02 | 1 | -22/+37 |
| * | [AArch64] More consistently separate asm opc and operands with '\t'. | Ahmed Bougacha | 2015-09-02 | 1 | -30/+30 |
| * | [AArch64] Consistently separate asm opc and operands with '\t'. | Ahmed Bougacha | 2015-09-02 | 1 | -17/+17 |
| * | [PowerPC] Don't always consider P8Altivec-only masks in LowerVECTOR_SHUFFLE | Hal Finkel | 2015-09-02 | 1 | -6/+8 |
| * | [x86] fix allowsMisalignedMemoryAccesses() for 8-byte and smaller accesses | Sanjay Patel | 2015-09-02 | 1 | -5/+13 |
| * | [X86][AVX512VLBW] add support in byte shift and SAD | Asaf Badouh | 2015-09-02 | 4 | -7/+83 |
| * | AVX512: Implemented encoding and intrinsics for VGETMANTPD/S , VGETMANTSD/S i... | Igor Breger | 2015-09-02 | 5 | -17/+63 |
| * | AVX512: Implemented encoding and intrinsics for vshufps/d. | Igor Breger | 2015-09-02 | 3 | -44/+36 |
| * | AVX-512: store <4 x i1> and <2 x i1> values in memory | Elena Demikhovsky | 2015-09-02 | 1 | -0/+5 |
| * | [CodeGen] Fix FREM on 32-bit MSVC on x86 | Vedant Kumar | 2015-09-02 | 1 | -1/+11 |
| * | [ARM] Don't abort on variable-idx extractelt in ReconstructShuffle. | Ahmed Bougacha | 2015-09-01 | 1 | -0/+4 |
| * | rename "slow-unaligned-mem-under-32" to slow-unaligned-mem-16" (NFCI) | Sanjay Patel | 2015-09-01 | 5 | -53/+59 |
| * | [AArch64] Lower READCYCLECOUNTER using MRS PMCCTNR_EL0. | Ahmed Bougacha | 2015-09-01 | 5 | -6/+25 |
| * | AVX512: Implemented intrinsics for valign. | Igor Breger | 2015-09-01 | 1 | -0/+8 |
| * | [AArch64] Turn on by default interleaved access vectorization | Silviu Baranga | 2015-09-01 | 1 | -0/+2 |
| * | [ARM] Turn on by default interleaved access vectorization | Silviu Baranga | 2015-09-01 | 1 | -0/+2 |
| * | AMDGPU: Fix adding redundant implicit operands | Matt Arsenault | 2015-09-01 | 1 | -11/+7 |
| * | WebAssembly: generate load/store | JF Bastien | 2015-08-31 | 3 | -49/+113 |
| * | [x86] enable machine combiner reassociations for scalar 'or' insts | Sanjay Patel | 2015-08-31 | 1 | -0/+4 |
| * | [EH] Handle non-Function personalities like unknown personalities | Reid Kleckner | 2015-08-31 | 1 | -7/+7 |
| * | [AArch64][CollectLOH] Remove an invalid assertion and add a test case exposin... | Quentin Colombet | 2015-08-31 | 1 | -3/+11 |
| * | AArch64: Fix loads to lower NEON vector lanes using GPR registers | Matthias Braun | 2015-08-31 | 1 | -1/+4 |
| * | X86: Fix FastISel SSESelect register class | Matthias Braun | 2015-08-31 | 1 | -3/+9 |
| * | AVX512: ktest implemantation | Igor Breger | 2015-08-31 | 4 | -14/+16 |
| * | AVX512: Implemented encoding and intrinsics for vdbpsadbw | Igor Breger | 2015-08-31 | 5 | -1/+15 |
| * | AVX512: kadd implementation | Igor Breger | 2015-08-31 | 1 | -2/+4 |
| * | AVX512: Implemented encoding and intrinsics for vpalignr | Igor Breger | 2015-08-31 | 4 | -34/+92 |
| * | [PowerPC] Fixup SELECT_CC (and SETCC) patterns with i1 comparison operands | Hal Finkel | 2015-08-30 | 4 | -5/+168 |
| * | [MIR Serialization] static -> static const in getSerializable*MachineOperandT... | Hal Finkel | 2015-08-30 | 3 | -5/+5 |
| * | [PowerPC/MIR Serialization] Target flags serialization support | Hal Finkel | 2015-08-30 | 2 | -0/+41 |
| * | [PowerPC] Don't assume ADDISdtprelHA's source is r3 | Hal Finkel | 2015-08-30 | 1 | -5/+5 |
| * | [Triple] Stop abusing a class to have only static methods and just use | Chandler Carruth | 2015-08-30 | 3 | -13/+13 |