Show patches with: Submitter = Hongyu Wang       |    State = Action Required       |    Archived = No       |   151 patches
« 1 2 »
Patch Series A/F/R/T S/W/F Date Submitter Delegate State
[03/13,APX_EGPR] Initial support for APX_F Support Intel APX EGPR - - - - --- 2023-08-31 Hongyu Wang New
[02/13,APX,EGPR] middle-end: Add index_reg_class with insn argument. Support Intel APX EGPR - - - - --- 2023-08-31 Hongyu Wang New
[01/13,APX,EGPR] middle-end: Add insn argument to base_reg_class Support Intel APX EGPR - - - - --- 2023-08-31 Hongyu Wang New
Fix avx512ne2ps2bf16 wrong code [PR 111127] Fix avx512ne2ps2bf16 wrong code [PR 111127] - - - - --- 2023-08-24 Hongyu Wang New
i386: Update document for inlining rules i386: Update document for inlining rules - - - - --- 2023-07-06 Hongyu Wang New
[V2] i386: Inline function with default arch/tune to caller [V2] i386: Inline function with default arch/tune to caller - - - - --- 2023-07-04 Hongyu Wang New
i386: Relax inline requirement for functions with different target attrs i386: Relax inline requirement for functions with different target attrs - - - - --- 2023-06-26 Hongyu Wang New
i386: Sync tune_string with arch_string for target attribute arch=* i386: Sync tune_string with arch_string for target attribute arch=* - - - - --- 2023-06-26 Hongyu Wang New
libgomp: Fix default value of GOMP_SPINCOUNT [PR 109062] libgomp: Fix default value of GOMP_SPINCOUNT [PR 109062] - - - - --- 2023-03-08 Hongyu Wang New
i386: Avoid fma_chain for -march=alderlake and sapphirerapids. i386: Avoid fma_chain for -march=alderlake and sapphirerapids. - - - - --- 2022-12-07 Hongyu Wang New
i386: Only enable small loop unrolling in backend [PR 107602] i386: Only enable small loop unrolling in backend [PR 107602] - - - - --- 2022-11-19 Hongyu Wang New
rs6000: Adjust loop_unroll_adjust to match middle-end change [PR 107692] rs6000: Adjust loop_unroll_adjust to match middle-end change [PR 107692] - - - - --- 2022-11-16 Hongyu Wang New
doc: Reword the description of -mrelax-cmpxchg-loop [PR 107676] doc: Reword the description of -mrelax-cmpxchg-loop [PR 107676] - - - - --- 2022-11-15 Hongyu Wang New
Optimize VEC_PERM_EXPR with same permutation index and operation [PR98167] Optimize VEC_PERM_EXPR with same permutation index and operation [PR98167] - - - - --- 2022-11-04 Hongyu Wang New
[V2] Enable small loop unrolling for O2 [V2] Enable small loop unrolling for O2 - - - - --- 2022-11-02 Hongyu Wang New
i386: Enable small loop unrolling for O2 i386: Enable small loop unrolling for O2 - - - - --- 2022-10-26 Hongyu Wang New
Support Intel AVX-IFMA Support Intel AVX-IFMA - - - - --- 2022-10-19 Hongyu Wang New
i386: Add a constraint for absolute symboilc address [PR 105576] i386: Add a constraint for absolute symboilc address [PR 105576] - - - - --- 2022-05-18 Hongyu Wang New
AVX512F: Add missing macro for mask(z?)_scalf_s[sd] [PR 105339] AVX512F: Add missing macro for mask(z?)_scalf_s[sd] [PR 105339] - - - - --- 2022-04-22 Hongyu Wang New
i386: Correct target attribute for crc32 intrinsics i386: Correct target attribute for crc32 intrinsics - - - - --- 2022-04-15 Hongyu Wang New
i386: Disable stv under optimize_size [PR 105034] i386: Disable stv under optimize_size [PR 105034] - - - - --- 2022-04-14 Hongyu Wang New
i386: Fix infinite loop under -mrelax-cmpxchg-loop [PR 103069] i386: Fix infinite loop under -mrelax-cmpxchg-loop [PR 103069] - - - - --- 2022-04-13 Hongyu Wang New
[v3] AVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch [PR 104978] [v3] AVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch [PR 104978] - - - - --- 2022-03-22 Hongyu Wang New
[v2] AVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch [PR 104978] [v2] AVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch [PR 104978] - - - - --- 2022-03-21 Hongyu Wang New
AVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch [PR 104978] AVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch [PR 104978] - - - - --- 2022-03-19 Hongyu Wang New
AVX512FP16: Fix masm=intel output for vfc?(madd|mul)csh [PR 104977] AVX512FP16: Fix masm=intel output for vfc?(madd|mul)csh [PR 104977] - - - - --- 2022-03-19 Hongyu Wang New
AVX512FP16: Fix vcvt[u]si2sh runtime tests for Solaris AVX512FP16: Fix vcvt[u]si2sh runtime tests for Solaris - - - - --- 2022-03-02 Hongyu Wang New
i386: Fix pr104551 testcase for solaris [PR 104726] i386: Fix pr104551 testcase for solaris [PR 104726] - - - - --- 2022-03-02 Hongyu Wang New
i386: Fix V8HF vector init under -mno-avx [PR 104664] i386: Fix V8HF vector init under -mno-avx [PR 104664] - - - - --- 2022-02-28 Hongyu Wang New
AVX512F: Add helper enumeration for ternary logic intrinsics. AVX512F: Add helper enumeration for ternary logic intrinsics. - - - - --- 2022-02-25 Hongyu Wang New
i386: Relax cmpxchg instruction under -mrelax-cmpxchg-loop [PR 103069] i386: Relax cmpxchg instruction under -mrelax-cmpxchg-loop [PR 103069] - - - - --- 2022-02-21 Hongyu Wang New
[i386] GLC tuning: Break false dependency for dest register. [i386] GLC tuning: Break false dependency for dest register. - - - - --- 2022-01-13 Hongyu Wang New
i386: Fix wrong codegen for -mrelax-cmpxchg-loop i386: Fix wrong codegen for -mrelax-cmpxchg-loop - - - - --- 2021-11-18 Hongyu Wang New
PR libgomp/103068: Optimize gomp_mutex_lock_slow for x86 target PR libgomp/103068: Optimize gomp_mutex_lock_slow for x86 target - - - - --- 2021-11-14 Hongyu Wang New
PR target/103069: Relax cmpxchg loop for x86 target PR target/103069: Relax cmpxchg loop for x86 target - - - - --- 2021-11-13 Hongyu Wang New
i386: Auto vectorize sdot_prod, usdot_prod with VNNI instruction. i386: Auto vectorize sdot_prod, usdot_prod with VNNI instruction. - - - - --- 2021-11-04 Hongyu Wang New
i386: Fix wrong result for AMX-TILE intrinsic when parsing expression. i386: Fix wrong result for AMX-TILE intrinsic when parsing expression. - - - - --- 2021-11-04 Hongyu Wang New
AVX512FP16: Optimize _Float16 reciprocal for div and sqrt AVX512FP16: Optimize _Float16 reciprocal for div and sqrt - - - - --- 2021-10-26 Hongyu Wang New
Adjust testcase for 128/256 bit HF vector load/store Adjust testcase for 128/256 bit HF vector load/store - - - - --- 2021-10-21 Hongyu Wang New
i386: Fix wrong codegen for V8HF move without TARGET_AVX512F i386: Fix wrong codegen for V8HF move without TARGET_AVX512F - - - - --- 2021-10-20 Hongyu Wang New
AVX512FP16: Fix ICE for 2 v4hf vector concat AVX512FP16: Fix ICE for 2 v4hf vector concat - - - - --- 2021-10-15 Hongyu Wang New
AVX512FP16: Fix testcase for complex intrinsic AVX512FP16: Fix testcase for complex intrinsic - - - - --- 2021-10-15 Hongyu Wang New
AVX512FP16: Support vector shuffle builtins AVX512FP16: Support vector shuffle builtins - - - - --- 2021-10-14 Hongyu Wang New
AVX512FP16: Adjust builtin for mask complex fma AVX512FP16: Adjust builtin for mask complex fma - - - - --- 2021-10-13 Hongyu Wang New
AVX512FP16:support basic 64/32bit vector type and operation. AVX512FP16:support basic 64/32bit vector type and operation. - - - - --- 2021-09-27 Hongyu Wang New
AVX512FP16: Support cond_op for HFmode AVX512FP16: Support cond_op for HFmode - - - - --- 2021-09-23 Hongyu Wang New
AVX512FP16: Adjust builtin name for FP16 builtins to match AVX512F style AVX512FP16: Adjust builtin name for FP16 builtins to match AVX512F style - - - - --- 2021-09-15 Hongyu Wang New
i386: Add peephole for lea and zero extend [PR 101716] i386: Add peephole for lea and zero extend [PR 101716] - - - - --- 2021-08-13 Hongyu Wang New
i386: Fix typos in amxbf16 runtime test. i386: Fix typos in amxbf16 runtime test. - - - - --- 2021-08-10 Hongyu Wang New
[i386] Remove rex64suffix for v?cvtt?(ss|sd)*2si [i386] Remove rex64suffix for v?cvtt?(ss|sd)*2si - - - - --- 2021-07-02 Hongyu Wang New
[i386] Clear odata for aes(enc|dec)(wide)?kl intrinsics [i386] Clear odata for aes(enc|dec)(wide)?kl intrinsics - - - - --- 2021-07-01 Hongyu Wang New
« 1 2 »