Show patches with: Submitter = Hongtao Liu       |    State = Action Required       |    Archived = No       |   534 patches
« 1 2 3 4 … 5 6 »
Patch Series A/F/R/T S/W/F Date Submitter Delegate State
Disparage slightly for the alternative which move DFmode between SSE_REGS and GENERAL_REGS. Disparage slightly for the alternative which move DFmode between SSE_REGS and GENERAL_REGS. - - - - --- 2023-07-06 Liu, Hongtao New
Break false dependence for vpternlog by inserting vpxor. Break false dependence for vpternlog by inserting vpxor. - - - - --- 2023-07-04 Liu, Hongtao New
[2/2] Make option mvzeroupper independent of optimization level. [1/2] Don't issue vzeroupper for vzeroupper call_insn. - - - - --- 2023-06-27 Liu, Hongtao New
[1/2] Don't issue vzeroupper for vzeroupper call_insn. [1/2] Don't issue vzeroupper for vzeroupper call_insn. - - - - --- 2023-06-27 Liu, Hongtao New
[x86] Refine maskstore patterns with UNSPEC_MASKMOV. [x86] Refine maskstore patterns with UNSPEC_MASKMOV. - - - - --- 2023-06-27 Liu, Hongtao New
Issue a warning for conversion between short and __bf16 under TARGET_AVX512BF16. Issue a warning for conversion between short and __bf16 under TARGET_AVX512BF16. - - - - --- 2023-06-26 Liu, Hongtao New
[3/3,aarch64] Adjust testcase to match assembly output after r14-2007. [1/3] Use cvt_op to save intermediate type operand instead of "subtle" vec_dest. - - - - --- 2023-06-26 Liu, Hongtao New
[2/3] Don't use intermiediate type for FIX_TRUNC_EXPR when ftrapping-math. [1/3] Use cvt_op to save intermediate type operand instead of "subtle" vec_dest. - - - - --- 2023-06-26 Liu, Hongtao New
[1/3] Use cvt_op to save intermediate type operand instead of "subtle" vec_dest. [1/3] Use cvt_op to save intermediate type operand instead of "subtle" vec_dest. - - - - --- 2023-06-26 Liu, Hongtao New
Refine maskloadmn pattern with UNSPEC_MASKLOAD. Refine maskloadmn pattern with UNSPEC_MASKLOAD. - - - - --- 2023-06-21 Liu, Hongtao New
[vect] Use intermiediate integer type for float_expr/fix_trunc_expr when direct optab is not existe… [vect] Use intermiediate integer type for float_expr/fix_trunc_expr when direct optab is not existe… - - - - --- 2023-06-20 Liu, Hongtao New
[2/2] Refined 256/512-bit vpacksswb/vpackssdw patterns. [1/2] Reimplement packuswb/packusdw with UNSPEC_US_TRUNCATE instead of original us_truncate. - - - - --- 2023-06-16 Liu, Hongtao New
[1/2] Reimplement packuswb/packusdw with UNSPEC_US_TRUNCATE instead of original us_truncate. [1/2] Reimplement packuswb/packusdw with UNSPEC_US_TRUNCATE instead of original us_truncate. - - - - --- 2023-06-16 Liu, Hongtao New
[x86] Use x instead of v for alternative 2 (v, BH) in mov<mode>_internal. [x86] Use x instead of v for alternative 2 (v, BH) in mov<mode>_internal. - - - - --- 2023-06-14 Liu, Hongtao New
[1/2] Fold _mm{, 256, 512}_abs_{epi8, epi16, epi32, epi64} into gimple ABSU_EXPR + VCE. [1/2] Fold _mm{, 256, 512}_abs_{epi8, epi16, epi32, epi64} into gimple ABSU_EXPR + VCE. - - - - --- 2023-06-06 Liu, Hongtao New
[v2] Explicitly view_convert_expr mask to signed type when folding pblendvb builtins. [v2] Explicitly view_convert_expr mask to signed type when folding pblendvb builtins. - - - - --- 2023-06-06 Liu, Hongtao New
Don't fold _mm{, 256}_blendv_epi8 into (mask < 0 ? src1 : src2) when -funsigned-char. Don't fold _mm{, 256}_blendv_epi8 into (mask < 0 ? src1 : src2) when -funsigned-char. - - - - --- 2023-06-06 Liu, Hongtao New
Fold _mm{, 256, 512}_abs_{epi8, epi16, epi32, epi64} into gimple ABSU_EXPR + VCE. Fold _mm{, 256, 512}_abs_{epi8, epi16, epi32, epi64} into gimple ABSU_EXPR + VCE. - - - - --- 2023-06-06 Liu, Hongtao New
[x86] Add missing vec_pack/unpacks patterns for _Float16 <-> int/float conversion. [x86] Add missing vec_pack/unpacks patterns for _Float16 <-> int/float conversion. - - - - --- 2023-06-05 Liu, Hongtao New
[vect] Use intermiediate integer type for float_expr/fix_trunc_expr when direct optab is not existe… [vect] Use intermiediate integer type for float_expr/fix_trunc_expr when direct optab is not existe… - - - - --- 2023-06-02 Liu, Hongtao New
i386: Add missing vector truncate patterns [PR92658]. i386: Add missing vector truncate patterns [PR92658]. - - - - --- 2023-06-02 Liu, Hongtao New
Don't try bswap + rotate when TYPE_PRECISION(n->type) > n->range. Don't try bswap + rotate when TYPE_PRECISION(n->type) > n->range. - - - - --- 2023-06-01 Liu, Hongtao New
Disable avoid_false_dep_for_bmi for atom and icelake(and later) core processors. Disable avoid_false_dep_for_bmi for atom and icelake(and later) core processors. - - - - --- 2023-05-26 Liu, Hongtao New
[x86] Split notl + pbraodcast + pand to pbroadcast + pandn more modes. [x86] Split notl + pbraodcast + pand to pbroadcast + pandn more modes. - - - - --- 2023-05-26 Liu, Hongtao New
Fold _mm{, 256, 512}_abs_{epi8, epi16, epi32, epi64} into gimple ABS_EXPR. Fold _mm{, 256, 512}_abs_{epi8, epi16, epi32, epi64} into gimple ABS_EXPR. - - - - --- 2023-05-22 Liu, Hongtao New
Only use NO_REGS in cost calculation when !hard_regno_mode_ok for GENERAL_REGS and mode. Only use NO_REGS in cost calculation when !hard_regno_mode_ok for GENERAL_REGS and mode. - - - - --- 2023-05-17 Liu, Hongtao New
[V2] Provide -fcf-protection=branch,return. [V2] Provide -fcf-protection=branch,return. - - - - --- 2023-05-13 Liu, Hongtao New
Provide -fcf-protection=branch,return. Provide -fcf-protection=branch,return. - - - - --- 2023-05-12 Liu, Hongtao New
x86: Add a new option -mdaz-ftz to enable FTZ and DAZ flags in MXCSR. x86: Add a new option -mdaz-ftz to enable FTZ and DAZ flags in MXCSR. - - - - --- 2023-05-10 Liu, Hongtao New
Detect bswap + rotate for byte permutation in pass_bswap. Detect bswap + rotate for byte permutation in pass_bswap. - - - - --- 2023-05-09 Liu, Hongtao New
[V2,vect] Enhance NARROW FLOAT_EXPR vectorization by truncating integer to lower precision. [V2,vect] Enhance NARROW FLOAT_EXPR vectorization by truncating integer to lower precision. - - - - --- 2023-05-08 Liu, Hongtao New
[powerpc] Add a peephole2 to eliminate redundant move from VSX_REGS to GENERAL_REGS when it's from … [powerpc] Add a peephole2 to eliminate redundant move from VSX_REGS to GENERAL_REGS when it's from … - - - - --- 2023-05-04 Liu, Hongtao New
[v2] Canonicalize vec_merge when mask is constant. [v2] Canonicalize vec_merge when mask is constant. - - - - --- 2023-05-04 Liu, Hongtao New
[vect] Enhance NARROW FLOAT_EXPR vectorization by truncating integer to lower precision. [vect] Enhance NARROW FLOAT_EXPR vectorization by truncating integer to lower precision. - - - - --- 2023-04-26 Liu, Hongtao New
Add testcases for ffs/ctz vectorization. Add testcases for ffs/ctz vectorization. - - - - --- 2023-04-23 Liu, Hongtao New
[2/2,i386] def_or_undef __STDCPP_FLOAT16_T__ and __STDCPP_BFLOAT16_T__ for target attribute/pragmas. [1/2,i386] Support type _Float16/__bf16 independent of SSE2. - - - - --- 2023-04-21 Liu, Hongtao New
[1/2,i386] Support type _Float16/__bf16 independent of SSE2. [1/2,i386] Support type _Float16/__bf16 independent of SSE2. - - - - --- 2023-04-21 Liu, Hongtao New
Canonicalize vec_merge when mask is constant. Canonicalize vec_merge when mask is constant. - - - - --- 2023-04-20 Liu, Hongtao New
[2/2] Adjust testcases after better RA decision. [1/2] Use NO_REGS in cost calculation when the preferred register class are not known yet. - - - - --- 2023-04-20 Liu, Hongtao New
[1/2] Use NO_REGS in cost calculation when the preferred register class are not known yet. [1/2] Use NO_REGS in cost calculation when the preferred register class are not known yet. - - - - --- 2023-04-20 Liu, Hongtao New
[i386] Support type _Float16/__bf16 independent of SSE2. [i386] Support type _Float16/__bf16 independent of SSE2. - - - - --- 2023-04-19 Liu, Hongtao New
Check hard_regno_mode_ok before setting lowest memory move cost for the mode with different reg cla… Check hard_regno_mode_ok before setting lowest memory move cost for the mode with different reg cla… - - - - --- 2023-04-04 Liu, Hongtao New
Document signbitm2. Document signbitm2. - - - - --- 2023-03-31 Liu, Hongtao New
Adjust memory_move_cost for MASK_REGS when MODE_SIZE > 8. Adjust memory_move_cost for MASK_REGS when MODE_SIZE > 8. - - - - --- 2023-03-31 Liu, Hongtao New
[V2] Rename ufix_trunc/ufloat* patterns to fixuns_trunc/floatuns* to align with standard pattern na… [V2] Rename ufix_trunc/ufloat* patterns to fixuns_trunc/floatuns* to align with standard pattern na… - - - - --- 2023-03-30 Liu, Hongtao New
Support vector conversion for AVX512 vcvtudq2pd/vcvttps2udq/vcvttpd2udq. Support vector conversion for AVX512 vcvtudq2pd/vcvttps2udq/vcvttpd2udq. - - - - --- 2023-03-30 Liu, Hongtao New
Generate vpblendd instead of vpblendw for V4SI under AVX2. Generate vpblendd instead of vpblendw for V4SI under AVX2. - - - - --- 2023-03-29 Liu, Hongtao New
Remove TARGET_GEN_MEMSET_SCRATCH_RTX since it's not used anymore. Remove TARGET_GEN_MEMSET_SCRATCH_RTX since it's not used anymore. - - - - --- 2023-03-22 Liu, Hongtao New
[vect] Don't peel nonlinear iv(mult or shift) for epilog when vf is not constant. [vect] Don't peel nonlinear iv(mult or shift) for epilog when vf is not constant. - - - - --- 2023-02-02 Liu, Hongtao New
Change AVX512FP16 to AVX512-FP16 which is official name. Change AVX512FP16 to AVX512-FP16 which is official name. - - - - --- 2023-01-29 Liu, Hongtao New
Change AVX512FP16 to AVX512-FP16 in the document. Change AVX512FP16 to AVX512-FP16 in the document. - - - - --- 2023-01-29 Liu, Hongtao New
Don't add crtfastmath.o for -shared. Don't add crtfastmath.o for -shared. - - - - --- 2023-01-13 Liu, Hongtao New
[V2,2/2,x86] x86: Add a new option -mdaz-ftz to enable FTZ and DAZ flags in MXCSR. Untitled series #332816 - - - - --- 2022-12-15 Liu, Hongtao New
[V2,1/2] x86: Don't add crtfastmath.o for -shared - - - - --- 2022-12-15 Liu, Hongtao New
[x86] x86: Don't add crtfastmath.o for -shared and add a new option -mdaz-ftz to enable FTZ and DAZ… [x86] x86: Don't add crtfastmath.o for -shared and add a new option -mdaz-ftz to enable FTZ and DAZ… - - - - --- 2022-12-14 Liu, Hongtao New
[x86] Fix ICE due to condition mismatch between expander and define_insn. [x86] Fix ICE due to condition mismatch between expander and define_insn. - - - - --- 2022-12-06 Liu, Hongtao New
[x86] Improve ix86_expand_fast_convert_bf_to_sf with new extendbfsf2_1. [x86] Improve ix86_expand_fast_convert_bf_to_sf with new extendbfsf2_1. - - - - --- 2022-12-02 Liu, Hongtao New
[x86] Fix ICE due to incorrect insn type. [x86] Fix ICE due to incorrect insn type. - - - - --- 2022-12-01 Liu, Hongtao New
[1/2,V2] Implement hwasan target_hook. [1/2,V2] Implement hwasan target_hook. - - - - --- 2022-11-30 Liu, Hongtao New
[x86] Fix unrecognizable insn due to illegal immediate_operand (const_int 255) of QImode. [x86] Fix unrecognizable insn due to illegal immediate_operand (const_int 255) of QImode. - - - - --- 2022-11-28 Liu, Hongtao New
[V3,x86] Fix incorrect _mm_cvtsbh_ss. [V3,x86] Fix incorrect _mm_cvtsbh_ss. - - - - --- 2022-11-25 Liu, Hongtao New
[v2,x86] Fix incorrect _mm_cvtsbh_ss. [v2,x86] Fix incorrect _mm_cvtsbh_ss. - - - - --- 2022-11-24 Liu, Hongtao New
[x86] Fix incorrect implementation for mm_cvtsbh_ss. [x86] Fix incorrect implementation for mm_cvtsbh_ss. - - - - --- 2022-11-23 Liu, Hongtao New
[x86] Some tidy up for RA related hooks. [x86] Some tidy up for RA related hooks. - - - - --- 2022-11-21 Liu, Hongtao New
[x86] define builtins for "shared" avxneconvert-avx512bf16vl builtins. [x86] define builtins for "shared" avxneconvert-avx512bf16vl builtins. - - - - --- 2022-11-18 Liu, Hongtao New
[2/2] Enable hwasan for x86-64. Support HWASAN with Intel LAM - - - - --- 2022-11-11 Liu, Hongtao New
[1/2] Implement hwasan target_hook. Support HWASAN with Intel LAM - - - - --- 2022-11-11 Liu, Hongtao New
Fix incorrect insn type to avoid ICE in memory attr auto-detection. Fix incorrect insn type to avoid ICE in memory attr auto-detection. - - - - --- 2022-11-08 Liu, Hongtao New
Enable more optimization for 32-bit/64-bit shrd/shld with imm shift count. Enable more optimization for 32-bit/64-bit shrd/shld with imm shift count. - - - - --- 2022-10-31 Liu, Hongtao New
[V2,x86] Fix incorrect digit constraint [V2,x86] Fix incorrect digit constraint - - - - --- 2022-10-31 Liu, Hongtao New
[x86] Fix incorrect digit constraint [x86] Fix incorrect digit constraint - - - - --- 2022-10-27 Liu, Hongtao New
[x86] Enable V4BFmode and V2BFmode. [x86] Enable V4BFmode and V2BFmode. - - - - --- 2022-10-26 Liu, Hongtao New
Canonicalize vec_perm index to make the first index come from the first vector. Canonicalize vec_perm index to make the first index come from the first vector. - - - - --- 2022-10-18 Liu, Hongtao New
[x86] Add define_insn_and_split to support general version of "kxnor". [x86] Add define_insn_and_split to support general version of "kxnor". - - - - --- 2022-10-11 Liu, Hongtao New
[x86] Fix unrecognizable insn of cvtss2si. [x86] Fix unrecognizable insn of cvtss2si. - - - - --- 2022-10-10 Liu, Hongtao New
Check nonlinear iv in vect_can_advance_ivs_p. Check nonlinear iv in vect_can_advance_ivs_p. - - - - --- 2022-09-29 Liu, Hongtao New
[x86] Support 2-instruction vector shuffle for V4SI/V4SF in ix86_expand_vec_perm_const_1. [x86] Support 2-instruction vector shuffle for V4SI/V4SF in ix86_expand_vec_perm_const_1. - - - - --- 2022-09-26 Liu, Hongtao New
[x86] Support 2-instruction vector shuffle for V4SI/V4SF in ix86_expand_vec_perm_const_1. [x86] Support 2-instruction vector shuffle for V4SI/V4SF in ix86_expand_vec_perm_const_1. - - - - --- 2022-09-23 Liu, Hongtao New
[x86] Fix typo in floorv2sf2, should be register_operand for op1, not vector_operand. [x86] Fix typo in floorv2sf2, should be register_operand for op1, not vector_operand. - - - - --- 2022-09-22 Liu, Hongtao New
Don't check can_vec_perm_const_p for nonlinear iv_init when it's constant. Don't check can_vec_perm_const_p for nonlinear iv_init when it's constant. - - - - --- 2022-09-20 Liu, Hongtao New
Fix incorrect handle in vectorizable_induction for mixed induction type. Fix incorrect handle in vectorizable_induction for mixed induction type. - - - - --- 2022-09-20 Liu, Hongtao New
Support 64-bit vectorization for single-precision floating rounding operation. Support 64-bit vectorization for single-precision floating rounding operation. - - - - --- 2022-09-20 Liu, Hongtao New
[x86] Adjust issue_rate for latest Intel processors. [x86] Adjust issue_rate for latest Intel processors. - - - - --- 2022-09-16 Liu, Hongtao New
[x86] Don't optimize cmp mem, 0 to load mem, reg + test reg, reg [x86] Don't optimize cmp mem, 0 to load mem, reg + test reg, reg - - - - --- 2022-09-16 Liu, Hongtao New
Modernize ix86_builtin_vectorized_function with corresponding expanders. Modernize ix86_builtin_vectorized_function with corresponding expanders. - - - - --- 2022-09-16 Liu, Hongtao New
[ICE] Check another epilog variable peeling case in vectorizable_nonlinear_induction. [ICE] Check another epilog variable peeling case in vectorizable_nonlinear_induction. - - - - --- 2022-09-14 Liu, Hongtao New
Fix _mm512_cvt_roundps_ph to generate sae instruction. Fix _mm512_cvt_roundps_ph to generate sae instruction. - - - - --- 2022-09-05 Liu, Hongtao New
[V2] Extend vectorizer to handle nonlinear induction for neg, mul/lshift/rshift with a constant. [V2] Extend vectorizer to handle nonlinear induction for neg, mul/lshift/rshift with a constant. - - - - --- 2022-08-29 Liu, Hongtao New
Don't gimple fold ymm-version vblendvpd/vblendvps/vpblendvb w/o TARGET_AVX2 Don't gimple fold ymm-version vblendvpd/vblendvps/vpblendvb w/o TARGET_AVX2 - - - - --- 2022-08-24 Liu, Hongtao New
[RFC:] Extend vectorizer to handle nonlinear induction for neg, mul/lshift/rshift with a constant. [RFC:] Extend vectorizer to handle nonlinear induction for neg, mul/lshift/rshift with a constant. - - - - --- 2022-08-04 Liu, Hongtao New
Adjust testcase. Adjust testcase. - - - - --- 2022-07-22 Liu, Hongtao New
[V3] Extend 16/32-bit vector bit_op patterns with (m, 0, i) alternative. [V3] Extend 16/32-bit vector bit_op patterns with (m, 0, i) alternative. - - - - --- 2022-07-21 Liu, Hongtao New
Lower complex type move to enable vectorization for complex type load&store. Lower complex type move to enable vectorization for complex type load&store. - - - - --- 2022-07-20 Liu, Hongtao New
Move pass_cse_sincos after vectorizer. Move pass_cse_sincos after vectorizer. - - - - --- 2022-07-20 Liu, Hongtao New
[V2] Extend 16/32-bit vector bit_op patterns with (m, 0, i) alternative. [V2] Extend 16/32-bit vector bit_op patterns with (m, 0, i) alternative. - - - - --- 2022-07-19 Liu, Hongtao New
[V2,RFC] Support vectorization for Complex type. [V2,RFC] Support vectorization for Complex type. - - - - --- 2022-07-18 Liu, Hongtao New
Extend 16/32-bit vector bit_op patterns with (m, 0, i)(vertical) alternative. Extend 16/32-bit vector bit_op patterns with (m, 0, i)(vertical) alternative. - - - - --- 2022-07-18 Liu, Hongtao New
Extend 64-bit vector bit_op patterns with ?r alternative Extend 64-bit vector bit_op patterns with ?r alternative - - - - --- 2022-07-14 Liu, Hongtao New
[RFC] Support vectorization for Complex type. [RFC] Support vectorization for Complex type. - - - - --- 2022-07-11 Liu, Hongtao New
Allocate general register(memory/immediate) for 16/32/64-bit vector bit_op patterns. Allocate general register(memory/immediate) for 16/32/64-bit vector bit_op patterns. - - - - --- 2022-07-11 Liu, Hongtao New
« 1 2 3 4 … 5 6 »