Age | Commit message (Expand) | Author | Files | Lines |
2022-10-21 | i386: Fix up BFmode comparisons in conditional moves [PR107322] | Jakub Jelinek | 1 | -0/+37 |
2022-10-21 | Enable AMD znver4 support and add instruction reservations | Tejas Joshi | 9 | -41/+983 |
2022-10-21 | i386: Auto vectorize sdot_prod, udot_prod with VNNIINT8 instruction. | Haochen Jiang | 1 | -11/+50 |
2022-10-21 | Support Intel AVX-VNNI-INT8 | Kong Lingling | 9 | -21/+217 |
2022-10-21 | Support Intel AVX-IFMA | Hongyu Wang | 13 | -68/+195 |
2022-10-19 | gcc: Add 'mcf' thread model support from mcfgthread | LIU Hao | 2 | -1/+13 |
2022-10-19 | i386: Fix up __bf16 handling on ia32 | Jakub Jelinek | 2 | -10/+9 |
2022-10-19 | Canonicalize vec_perm index to make the first index come from the first vector. | liuhongt | 1 | -0/+17 |
2022-10-17 | Remove accidential commits | Jeff Law | 12 | -31671/+0 |
2022-10-17 | Enable REE for H8 | Jeff Law | 12 | -0/+31671 |
2022-10-14 | middle-end, c++, i386, libgcc: std::bfloat16_t and __bf16 arithmetic support | Jakub Jelinek | 4 | -69/+94 |
2022-10-13 | machmode: Introduce GET_MODE_NEXT_MODE with previous GET_MODE_WIDER_MODE mean... | Jakub Jelinek | 1 | -1/+1 |
2022-10-12 | Remove AVX512_VP2INTERSECT from PTA_SAPPHIRERAPIDS | Cui,Lili | 2 | -12/+8 |
2022-10-11 | i386: Fix up RTL checking ICE [PR107185] | Jakub Jelinek | 1 | -1/+1 |
2022-10-11 | Add define_insn_and_split to support general version of "kxnor". | liuhongt | 1 | -0/+71 |
2022-10-10 | Fix unrecognizable insn of cvtss2si. | liuhongt | 1 | -2/+2 |
2022-10-07 | fix clang warnings | Martin Liska | 1 | -2/+2 |
2022-10-03 | gcc/config/t-i386: add build dependencies on i386-builtin-types.inc | Sergei Trofimovich | 1 | -0/+5 |
2022-09-30 | i386, rs6000, ia64, s390: Fix C++ ICEs with _Float64x or _Float128 [PR107080] | Jakub Jelinek | 1 | -4/+4 |
2022-09-28 | i386: Mark XMM4-XMM6 as clobbered by encodekey128/encodekey256 | H.J. Lu | 2 | -12/+12 |
2022-09-27 | c++: Implement P1467R9 - Extended floating-point types and standard names com... | Jakub Jelinek | 3 | -9/+22 |
2022-09-26 | Support 2-instruction vector shuffle for V4SI/V4SF in ix86_expand_vec_perm_co... | liuhongt | 1 | -0/+116 |
2022-09-23 | i386: Optimize code generation of __mm256_zextsi128_si256(__mm_set1_epi8(-1)) | Hu, Lin1 | 4 | -5/+86 |
2022-09-22 | Fix typo in floorv2sf2, should be register_operand for op1, not vector_operand. | liuhongt | 1 | -1/+1 |
2022-09-20 | Support 64-bit vectorization for single-precision floating rounding operation. | liuhongt | 1 | -0/+154 |
2022-09-20 | Adjust issue_rate for latest Intel processors. | liuhongt | 1 | -0/+14 |
2022-09-20 | i386: Fixed vec_init_dup_v16bf [PR106887] | konglin1 | 1 | -7/+36 |
2022-09-16 | Modernize ix86_builtin_vectorized_function with corresponding expanders. | liuhongt | 2 | -181/+84 |
2022-09-06 | Fix _mm512_cvt_roundps_ph to generate sae instruction. | liuhongt | 2 | -3/+29 |
2022-09-05 | i386: avoid zero extension for crc32q | Alexander Monakov | 1 | -4/+5 |
2022-09-05 | rename DBX_REGISTER_NUMBER to DEBUGGER_REGNO | Martin Liska | 19 | -58/+58 |
2022-09-05 | x86: Handle V8BF in expand_vec_perm_broadcast_1 | konglin1 | 3 | -9/+14 |
2022-09-02 | d: Fix #error You must define PREFERRED_DEBUGGING_TYPE if DWARF is not supported | Iain Buclaw | 5 | -11/+28 |
2022-09-02 | STABS: remove -gstabs and -gxcoff functionality | Martin Liska | 2 | -10/+0 |
2022-09-02 | ipa: Fix throw in multi-versioned functions [PR106627] | Simon Rainer | 1 | -0/+1 |
2022-09-01 | i386: Fix conversion of move to/from AX_REG into xchg [PR106707] | Uros Bizjak | 1 | -2/+2 |
2022-08-29 | x86: Handle V16BF in ix86_avx256_split_vector_move_misalign | H.J. Lu | 2 | -2/+6 |
2022-08-27 | contrib: modernize gen_autofdo_event.py | Xi Ruoyao | 1 | -14/+17 |
2022-08-26 | Implement __builtin_issignaling | Jakub Jelinek | 1 | -0/+52 |
2022-08-26 | Don't gimple fold ymm-version vblendvpd/vblendvps/vpblendvb w/o TARGET_AVX2 | liuhongt | 2 | -5/+11 |
2022-08-24 | i386: Fix up mode iterators that weren't expanded [PR106721] | Jakub Jelinek | 1 | -7/+8 |
2022-08-23 | x86: Cast stride to __PTRDIFF_TYPE__ in AMX intrinsics | H.J. Lu | 1 | -3/+3 |
2022-08-19 | mkoffload: Cleanup temporary omp_requires_file | Tobias Burnus | 1 | -0/+1 |
2022-08-18 | x86: Support vector __bf16 type | konglin1 | 5 | -119/+258 |
2022-08-17 | [Committed] PR target/106640: Fix use of XINT in TImode compute_convert_gain. | Roger Sayle | 1 | -3/+3 |
2022-08-16 | i386: add 'final' and 'override' to scalar_chain | Martin Liska | 1 | -2/+2 |
2022-08-15 | Support shifts and rotates by integer constants in TImode STV on x86_64. | Roger Sayle | 1 | -6/+144 |
2022-08-15 | Improved gain calculation for COMPARE to 0 or -1 in TImode STV on x86_64. | Roger Sayle | 1 | -0/+17 |
2022-08-15 | x86: Enable __bf16 type for TARGET_SSE2 and above | konglin1 | 6 | -24/+129 |
2022-08-13 | Move V1TI shift/rotate lowering from expand to pre-reload split on x86_64. | Roger Sayle | 2 | -2/+101 |