Age | Commit message (Expand) | Author | Files | Lines |
2022-01-11 | rs6000: powerpc suboptimal boolean test of contiguous bits [PR102239] | Xionghu Luo | 3 | -0/+46 |
2022-01-10 | rs6000: Remove useless code related to -mno-power10 | Kewen Lin | 1 | -1/+0 |
2022-01-11 | Extend predicate of operands[1] from register_operand to vector_operand for a... | Haochen Jiang | 1 | -1/+1 |
2022-01-10 | i386: Introduce V2QImode vector compares [PR103861] | Uros Bizjak | 2 | -28/+35 |
2022-01-10 | rs6000: Add Power10 optimization for _mm_blendv* | Paul A. Clarke | 1 | -1/+13 |
2022-01-10 | x86_64: Ignore zero width bitfields in ABI and issue -Wpsabi warning about C ... | Jakub Jelinek | 1 | -7/+58 |
2022-01-08 | x86_64: Improve (interunit) moves from TImode to V1TImode. | Roger Sayle | 1 | -0/+17 |
2022-01-07 | target: [PR102941] Fix inline-asm flags with non-REG_P output | Andrew Pinski | 1 | -1/+1 |
2022-01-07 | i386: Robustify V2QI and V4QI move patterns | Uros Bizjak | 1 | -4/+12 |
2022-01-07 | nvptx: Add support for PTX's cnot instruction. | Roger Sayle | 1 | -0/+7 |
2022-01-07 | rs6000: Define a pattern for mffscrni. If the RN is a constant, it can call ... | Haochen Gui | 1 | -5/+19 |
2022-01-07 | Support commutative alternative for AVX512 vpcmpeq{b,w,d,q} | liuhongt | 1 | -32/+32 |
2022-01-07 | Optimize V16HF vector insert to element 0 for AVX2. | liuhongt | 2 | -28/+25 |
2022-01-06 | x86: Generate INT3 for __builtin_eh_return | H.J. Lu | 1 | -3/+6 |
2022-01-06 | x86: Rename -harden-sls=indirect-branch to -harden-sls=indirect-jmp | H.J. Lu | 3 | -6/+6 |
2022-01-06 | i386: Improve HImode interunit moves | Uros Bizjak | 3 | -32/+48 |
2022-01-07 | RISC-V: Minimal support of vector extensions | Kito Cheng | 2 | -0/+39 |
2022-01-05 | rs6000: Skip overload instances with uninitialized fntype (PR103622) | Bill Schmidt | 1 | -0/+6 |
2022-01-05 | Fix target/103910: missing GTY on x86_mfence causing PCH usage to ICE | Andrew Pinski | 1 | -1/+1 |
2022-01-05 | i386: Introduce V2QImode minmax, abs and uavgv2hi3_ceil [PR103861] | Uros Bizjak | 1 | -14/+41 |
2022-01-05 | i386: Fix type of one_cmplv2qi2 alternatives 1,2 [PR103915] | Uros Bizjak | 1 | -1/+1 |
2022-01-05 | i386: Fix expand_vec_perm_pshufb for narrow modes [PR103905] | Uros Bizjak | 1 | -11/+12 |
2022-01-04 | ipa-inline: Add target info into fn summary [PR102059] | Kewen Lin | 2 | -1/+82 |
2022-01-04 | i386: Introduce V2QImode vectorized logic [PR103861] | Uros Bizjak | 1 | -0/+146 |
2022-01-04 | nvptx: Transition nvptx backend to STORE_FLAG_VALUE = 1 | Roger Sayle | 2 | -37/+41 |
2022-01-04 | Force_reg operand 1. | liuhongt | 1 | -1/+2 |
2022-01-03 | i386: Always enable mov<V_32:mode> patterns [PR103894] | Uros Bizjak | 1 | -17/+6 |
2022-01-03 | i386, fab: Optimize __atomic_{add,sub,and,or,xor}_fetch (x, y, z) {==,!=,<,<=... | Jakub Jelinek | 1 | -0/+104 |
2022-01-03 | Update copyright years. | Jakub Jelinek | 1608 | -1624/+1624 |
2022-01-02 | i386: Introduce V2QImode vectorized arithmetic [PR103861] | Uros Bizjak | 4 | -5/+331 |
2022-01-02 | Use optab_libfunc to access sync_lock_test_and_set libfunc on hppa-linux. | John David Anglin | 1 | -12/+12 |
2021-12-30 | c-family: Use BULTINS_LOCATION for predefined macros changed upon optimize or... | Jakub Jelinek | 4 | -0/+10 |
2021-12-29 | i386: Robustify some expanders w.r.t. paradoxical SUBREGs | Uros Bizjak | 1 | -50/+65 |
2021-12-28 | i386: Fix handling of SUBREGs in divv2sf3 [PR103842] | Jakub Jelinek | 1 | -4/+6 |
2021-12-27 | Improve atomic store implementation on hppa-linux. | John David Anglin | 3 | -93/+24 |
2021-12-27 | ix86: Don't use the 'm' constraint for x86_64_general_operand | H.J. Lu | 2 | -32/+45 |
2021-12-26 | i386: Check AX input in any_mul_highpart peepholes | H.J. Lu | 1 | -3/+7 |
2021-12-24 | i386: Add V2SFmode DIV insn pattern [PR95046, PR103797] | Uros Bizjak | 1 | -0/+20 |
2021-12-24 | Darwin: Amend a comment to be more inclusive [NFC]. | Iain Sandoe | 1 | -3/+3 |
2021-12-24 | Darwin: Update rules for handling alignment of globals. | Iain Sandoe | 2 | -9/+17 |
2021-12-24 | Darwin: Check for that flag-reorder-and-partition. | Iain Sandoe | 1 | -0/+1 |
2021-12-24 | Darwin: Define OBJECT_FORMAT_MACHO. | Iain Sandoe | 1 | -0/+2 |
2021-12-23 | x86: PR target/103773: Fix wrong-code with -Oz from pop to memory. | Roger Sayle | 1 | -18/+44 |
2021-12-23 | i386: Enable intrinsics that convert float and bf16 data to each other. | konglin1 | 2 | -0/+99 |
2021-12-23 | Combine vpcmpuw + zero_extend to vpcmpuw. | liuhongt | 1 | -0/+275 |
2021-12-22 | arm: Declare MVE types internally via pragma | Murray Steele | 7 | -29/+313 |
2021-12-22 | arm: Move arm_simd_info array declaration into header | Murray Steele | 2 | -86/+88 |
2021-12-21 | i386: Add missing BMI intrinsic to align with clang | Jiang Haochen | 1 | -0/+18 |
2021-12-20 | rs6000: Replace UNSPECS with ss_plus/us_plus and ss_minus/us_minus | Xionghu Luo | 1 | -19/+10 |
2021-12-20 | i386: Fix <sse2p4_1>_pinsr<ssemodesuffix> and its splitters [PR103772] | Uros Bizjak | 1 | -27/+4 |