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
i386: Add BDESC2 for ix86_isa_flags2 and refine all related. i386: Add BDESC2 for ix86_isa_flags2 and refine all related. - - - - --- 2019-01-22 Hongtao Liu New
Add missing avx512dqintrin.h _mm_mask_fpclass_s[sd]_mask (PR target/897803) Add missing avx512dqintrin.h _mm_mask_fpclass_s[sd]_mask (PR target/897803) - - - - --- 2019-03-24 Hongtao Liu New
Fix ix86_expand_sse_comi_round (PR Target/89750, PR Target/86444) Fix ix86_expand_sse_comi_round (PR Target/89750, PR Target/86444) - - - - --- 2019-05-07 Hongtao Liu New
Add GCC support to ENQCMD. Add GCC support to ENQCMD. - - - - --- 2019-05-24 Hongtao Liu New
Add missing avx512dqintrin.h _mm_mask_fpclass_s[sd]_mask (PR target/89803) Add missing avx512dqintrin.h _mm_mask_fpclass_s[sd]_mask (PR target/89803) - - - - --- 2019-06-03 Hongtao Liu New
Enable memory operand for vfpclass[p,s][s,d] patterns. Enable memory operand for vfpclass[p,s][s,d] patterns. - - - - --- 2019-06-05 Hongtao Liu New
Enable GCC support for AVX512_VP2INTERSECT. Enable GCC support for AVX512_VP2INTERSECT. - - - - --- 2019-06-06 Hongtao Liu New
[target/87007] Extend rpad to handle AVX512F vcvtusi2ss/vcvtusi2sd [target/87007] Extend rpad to handle AVX512F vcvtusi2ss/vcvtusi2sd - - - - --- 2019-09-18 Hongtao Liu New
[target/92035] Add missing avx512f intrinsics [target/92035] Add missing avx512f intrinsics - - - - --- 2019-10-12 Hongtao Liu New
[target/89071] Fix false dependence of scalar operations vrcp/vsqrt/vrsqrt/vrndscale [target/89071] Fix false dependence of scalar operations vrcp/vsqrt/vrsqrt/vrndscale - - - - --- 2019-10-23 Hongtao Liu New
[target/92295] Fix inefficient vector constructor [target/92295] Fix inefficient vector constructor - - - - --- 2019-11-01 Hongtao Liu New
Set AVX128_OPTIMAL for all avx targets. Set AVX128_OPTIMAL for all avx targets. - - - - --- 2019-11-12 Hongtao Liu New
Split X86_TUNE_AVX128_OPTIMAL into X86_TUNE_AVX256_SPLIT_REGS and X86_TUNE_AVX128_OPTIMAL Split X86_TUNE_AVX128_OPTIMAL into X86_TUNE_AVX256_SPLIT_REGS and X86_TUNE_AVX128_OPTIMAL - - - - --- 2019-11-12 Hongtao Liu New
Fix TYPO of avx512f_maskcmp<mode>3. Fix TYPO of avx512f_maskcmp<mode>3. - - - - --- 2019-11-27 Hongtao Liu New
Enable mask operation for 128/256-bit vector VCOND_EXPR under avx512f (PR92686) Enable mask operation for 128/256-bit vector VCOND_EXPR under avx512f (PR92686) - - - - --- 2019-12-04 Hongtao Liu New
Use OPTION_MASK_ISA2_$target_[SET, UNSET, ] to indicate those for x_ix86_isa_flags2 Use OPTION_MASK_ISA2_$target_[SET, UNSET, ] to indicate those for x_ix86_isa_flags2 - - - - --- 2019-12-09 Hongtao Liu New
Fix unrecognizable insn of pr92865 Fix unrecognizable insn of pr92865 - - - - --- 2019-12-10 Hongtao Liu New
Add tune option for integer mask cmov, enable this tune for m_CORE_AVX512 Add tune option for integer mask cmov, enable this tune for m_CORE_AVX512 - - - - --- 2019-12-11 Hongtao Liu New
Fix redundant load missed by fre [tree-optimization 92980] Fix redundant load missed by fre [tree-optimization 92980] - - - - --- 2019-12-18 Hongtao Liu New
Add enqcmd,avx512bf16,avx512vp2intersect to funcspec-56.inc Add enqcmd,avx512bf16,avx512vp2intersect to funcspec-56.inc - - - - --- 2020-05-06 Hongtao Liu New
[PR94118] ] Update documentation for x86 operand modifier. [PR94118] ] Update documentation for x86 operand modifier. - - - - --- 2020-05-12 Hongtao Liu New
[PR92658] Add missing vector truncmn2 expanders for avx512f [PR92658] Add missing vector truncmn2 expanders for avx512f - - - - --- 2020-05-20 Hongtao Liu New
Fix nonconforming memory_operand for vpmov instructions which has memory operand narrow than 128 bi… Fix nonconforming memory_operand for vpmov instructions which has memory operand narrow than 128 bi… - - - - --- 2020-05-25 Hongtao Liu New
Fix typo in expander trunc<mode><pmov_dst_3>2 [AVX512] Fix typo in expander trunc<mode><pmov_dst_3>2 [AVX512] - - - - --- 2020-06-04 Hongtao Liu New
[AVX512,PR87767] Optimize memory broadcast for constant vector under AVX512 [AVX512,PR87767] Optimize memory broadcast for constant vector under AVX512 - - - - --- 2020-07-09 Hongtao Liu New
[AVX512] For vector compare to mask register, UNSPEC is needed instead of comparison operator [PR96… [AVX512] For vector compare to mask register, UNSPEC is needed instead of comparison operator [PR96… - - - - --- 2020-07-20 Hongtao Liu New
[AVX512,PR96246] Merge two define_insn: <avx512>_blendm<mode>, <avx512>_load<mode>_mask. [AVX512,PR96246] Merge two define_insn: <avx512>_blendm<mode>, <avx512>_load<mode>_mask. - - - - --- 2020-07-22 Hongtao Liu New
Using gen_int_mode instead of GEN_INT to avoid ICE caused by type promotion. Using gen_int_mode instead of GEN_INT to avoid ICE caused by type promotion. - - - - --- 2020-07-22 Hongtao Liu New
[PR,target/96350] Force ENDBR immediate into memory to avoid fake ENDBR opcode. [PR,target/96350] Force ENDBR immediate into memory to avoid fake ENDBR opcode. - - - - --- 2020-08-11 Hongtao Liu New
Don't use pinsr for struct initialization. Don't use pinsr for struct initialization. - - - - --- 2020-08-14 Hongtao Liu New
[1/4,PR,target/88808] Enable bitwise operator for AVX512 masks. [1/4,PR,target/88808] Enable bitwise operator for AVX512 masks. - - - - --- 2020-08-14 Hongtao Liu New
[2/4,PR,target/88808] Enable bitwise operator for AVX512 masks. [1/4,PR,target/88808] Enable bitwise operator for AVX512 masks. - - - - --- 2020-08-14 Hongtao Liu New
[3/4,PR,target/88808] Enable bitwise operator for AVX512 masks. [1/4,PR,target/88808] Enable bitwise operator for AVX512 masks. - - - - --- 2020-08-14 Hongtao Liu New
[4/4,PR,target/88808] Enable bitwise operator for AVX512 masks. [1/4,PR,target/88808] Enable bitwise operator for AVX512 masks. - - - - --- 2020-08-14 Hongtao Liu New
Adjust testcase gcc.target/i386/pr92865-1.c Adjust testcase gcc.target/i386/pr92865-1.c - - - - --- 2020-08-17 Hongtao Liu New
Adjust testcase. Adjust testcase. - - - - --- 2020-08-18 Hongtao Liu New
Adjust testcase Adjust testcase - - - - --- 2020-08-31 Hongtao Liu New
[AVX512] Lower AVX512 vector compare to AVX version when dest is vector [AVX512] Lower AVX512 vector compare to AVX version when dest is vector - - - - --- 2020-09-02 Hongtao Liu New
Implement __builtin_thread_pointer for x86 TLS Implement __builtin_thread_pointer for x86 TLS - - - - --- 2020-09-08 Hongtao Liu New
Return mask <-> integer cost for non-AVX512 micro-architecture. Return mask <-> integer cost for non-AVX512 micro-architecture. - - - - --- 2020-09-15 Hongtao Liu New
Increase rtx_cost of sse_to_integer in skylake_cost. Increase rtx_cost of sse_to_integer in skylake_cost. - - - - --- 2020-09-16 Hongtao Liu New
-mno-xsave should imply -mno-avx since -mavx implies -mxsave -mno-xsave should imply -mno-avx since -mavx implies -mxsave - - - - --- 2020-09-16 Hongtao Liu New
[PR,rtl-optimization/97249] Simplify vec_select of paradoxical subreg. [PR,rtl-optimization/97249] Simplify vec_select of paradoxical subreg. - - - - --- 2020-10-13 Hongtao Liu New
[PR,target/97194,AVX2] Support variable index vec_set. [PR,target/97194,AVX2] Support variable index vec_set. - - - - --- 2020-10-19 Hongtao Liu New
[PR,97506] Simplify trivial vcond_expr in expander. [PR,97506] Simplify trivial vcond_expr in expander. - - - - --- 2020-10-21 Hongtao Liu New
[PR,target/97642] Fix incorrect replacement of vmovdqu32 with vpblendd. [PR,target/97642] Fix incorrect replacement of vmovdqu32 with vpblendd. - - - - --- 2020-11-04 Hongtao Liu New
[wwwdocs] gcc-11/changes: Mention Intel AVX-VNNI [wwwdocs] gcc-11/changes: Mention Intel AVX-VNNI - - - - --- 2020-11-11 Hongtao Liu New
[X86] Delete Deadcode. [X86] Delete Deadcode. - - - - --- 2020-11-26 Hongtao Liu New
i386: Optimize vpsubusw compared to 0 into vpcmpleuw or vpcmpnltuw[PR96906] i386: Optimize vpsubusw compared to 0 into vpcmpleuw or vpcmpnltuw[PR96906] - - - - --- 2020-11-30 Hongtao Liu New
[Refactor,AVX512] Combine VI12_AVX512VL with VI48_AVX512VL into VI_AVX512VLBW [Refactor,AVX512] Combine VI12_AVX512VL with VI48_AVX512VL into VI_AVX512VLBW - - - - --- 2020-12-01 Hongtao Liu New
[X86] Fold more shuffle builtins to VEC_PERM_EXPR. [X86] Fold more shuffle builtins to VEC_PERM_EXPR. - - - - --- 2020-12-15 Hongtao Liu New
i386: Optimize pmovskb on zero_extend of subreg HI of the result [PR98461] i386: Optimize pmovskb on zero_extend of subreg HI of the result [PR98461] - - - - --- 2021-01-04 Hongtao Liu New
[x86] Delete dead code in ix86_expand_sse_comi.[PR98612] [x86] Delete dead code in ix86_expand_sse_comi.[PR98612] - - - - --- 2021-01-11 Hongtao Liu New
[PR,rtl/optimization/98694] Fix incorrect optimization by cprop_hardreg. [PR,rtl/optimization/98694] Fix incorrect optimization by cprop_hardreg. - - - - --- 2021-01-18 Hongtao Liu New
[GCC-9] backport -march=tigerlake to GCC9 [PR target/100009] [GCC-9] backport -march=tigerlake to GCC9 [PR target/100009] - - - - --- 2021-04-13 Hongtao Liu New
[i386] Fix a small performance regression. [PR98348] [i386] Fix a small performance regression. [PR98348] - - - - --- 2021-04-19 Hongtao Liu New
[i386] MASK_AVX256_SPLIT_UNALIGNED_STORE/LOAD should be cleared in opts->x_target_flags when X86_TU… [i386] MASK_AVX256_SPLIT_UNALIGNED_STORE/LOAD should be cleared in opts->x_target_flags when X86_TU… - - - - --- 2021-04-22 Hongtao Liu New
[i386] Optimize __builtin_shuffle when it's used to zero the upper bits of the dest. [PR target/946… [i386] Optimize __builtin_shuffle when it's used to zero the upper bits of the dest. [PR target/946… - - - - --- 2021-04-23 Hongtao Liu New
Add folding and remove expanders for x86 *pcmp{et,gt}* builtins [PR target/98911] Add folding and remove expanders for x86 *pcmp{et,gt}* builtins [PR target/98911] - - - - --- 2021-04-23 Hongtao Liu New
i386: Optimize vpblendvb on inverted mask register to vpblendvb on swapping the order of operand 1 … i386: Optimize vpblendvb on inverted mask register to vpblendvb on swapping the order of operand 1 … - - - - --- 2021-04-27 Hongtao Liu New
[AVX512] Fix ICE for vpexpand*. [AVX512] Fix ICE for vpexpand*. - - - - --- 2021-04-30 Hongtao Liu New
[AVX512] Optimize vpexpand* to mask mov when mask have all ones in it's lower part (including 0 and… [AVX512] Optimize vpexpand* to mask mov when mask have all ones in it's lower part (including 0 and… - - - - --- 2021-04-30 Hongtao Liu New
[i386] Fix ICE [PR target/100549] [i386] Fix ICE [PR target/100549] - - - - --- 2021-05-13 Hongtao Liu New
[i386] Fix _mm256_zeroupper to notify LRA that vzeroupper will kill sse registers. [PR target/82735] [i386] Fix _mm256_zeroupper to notify LRA that vzeroupper will kill sse registers. [PR target/82735] - - - - --- 2021-05-13 Hongtao Liu New
[i386] Fix ICE when lhs is NULL [PR target/100660] [i386] Fix ICE when lhs is NULL [PR target/100660] - - - - --- 2021-05-20 Hongtao Liu New
[1/2,i386] Fold blendv builtins into gimple. [1/2,i386] Fold blendv builtins into gimple. - - - - --- 2021-05-24 Hongtao Liu New
[i386] Support avx512 vector shift with vector [PR98434] [i386] Support avx512 vector shift with vector [PR98434] - - - - --- 2021-05-24 Hongtao Liu New
Extend is_cond_scalar_reduction to handle nop_expr after/before scalar reduction.[PR98365] Extend is_cond_scalar_reduction to handle nop_expr after/before scalar reduction.[PR98365] - - - - --- 2021-05-24 Hongtao Liu New
[i386] Split not+broadcast+pand to broadcast+pandn. [i386] Split not+broadcast+pand to broadcast+pandn. - - - - --- 2021-05-25 Hongtao Liu New
Simplify (view_convert ~a) < 0 to (view_convert a) >= 0 [PR middle-end/100738] Simplify (view_convert ~a) < 0 to (view_convert a) >= 0 [PR middle-end/100738] - - - - --- 2021-06-01 Hongtao Liu New
Canonicalize (vec_duplicate (not A)) to (not (vec_duplicate A)). Canonicalize (vec_duplicate (not A)) to (not (vec_duplicate A)). - - - - --- 2021-06-02 Liu, Hongtao New
Canonicalize (vec_duplicate (not A)) to (not (vec_duplicate A)). Canonicalize (vec_duplicate (not A)) to (not (vec_duplicate A)). - - - - --- 2021-06-02 Liu, Hongtao New
[1/2] CALL_INSN may not be a real function call. [1/2] CALL_INSN may not be a real function call. - - - - --- 2021-06-03 Liu, Hongtao New
[2/2] Fix _mm256_zeroupper by representing the instructions as call_insns in which the call has a s… [1/2] CALL_INSN may not be a real function call. - - - - --- 2021-06-03 Liu, Hongtao New
[i386] Fix ICE of insn does not satisfy its constraints. [i386] Fix ICE of insn does not satisfy its constraints. - - - - --- 2021-06-03 Liu, Hongtao New
Add vect_recog_popcount_pattern to handle mismatch between the vectorized popcount IFN and scalar p… Add vect_recog_popcount_pattern to handle mismatch between the vectorized popcount IFN and scalar p… - - - - --- 2021-06-17 Liu, Hongtao New
Disparage slightly the mask register alternative for bitwise operations. [PR target/101142] Disparage slightly the mask register alternative for bitwise operations. [PR target/101142] - - - - --- 2021-06-21 Liu, Hongtao New
MAINTAINERS: Add myself as maintainer of the i386 vector extensions. MAINTAINERS: Add myself as maintainer of the i386 vector extensions. - - - - --- 2021-06-21 Liu, Hongtao New
Remove my Write After Approval entry. Remove my Write After Approval entry. - - - - --- 2021-06-22 Liu, Hongtao New
[i386] Revert x86_order_regs_for_local_alloc changes in r12-1669. [i386] Revert x86_order_regs_for_local_alloc changes in r12-1669. - - - - --- 2021-06-24 Liu, Hongtao New
The upper bits of FIXUPIMMS{S, D} should come from src1 not dest. The upper bits of FIXUPIMMS{S, D} should come from src1 not dest. - - - - --- 2021-06-29 Liu, Hongtao New
[01/62] AVX512FP16: Support vector init/broadcast for FP16. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[02/62] AVX512FP16: Add testcase for vector init and broadcast intrinsics. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[03/62] AVX512FP16: Fix HF vector passing in variable arguments. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[04/62] AVX512FP16: Add ABI tests for xmm. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[05/62] AVX512FP16: Add ABI test for ymm. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[06/62] AVX512FP16: Add abi test for zmm Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[07/62] AVX512FP16: Add vaddph/vsubph/vdivph/vmulph. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[08/62] AVX512FP16: Add testcase for vaddph/vsubph/vmulph/vdivph. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[09/62] AVX512FP16: Enable _Float16 autovectorization Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[10/62] AVX512FP16: Add vaddsh/vsubsh/vmulsh/vdivsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[11/62] AVX512FP16: Add testcase for vaddsh/vsubsh/vmulsh/vdivsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[12/62] AVX512FP16: Add vmaxph/vminph/vmaxsh/vminsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[13/62] AVX512FP16: Add testcase for vmaxph/vmaxsh/vminph/vminsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[14/62] AVX512FP16: Add vcmpph/vcmpsh/vcomish/vucomish. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[15/62] AVX512FP16: Add testcase for vcmpph/vcmpsh/vcomish/vucomish. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[16/62] AVX512FP16: Add vsqrtph/vrsqrtph/vsqrtsh/vrsqrtsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[17/62] AVX512FP16: Add testcase for vsqrtph/vsqrtsh/vrsqrtph/vrsqrtsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[18/62] AVX512FP16: Add vrcpph/vrcpsh/vscalefph/vscalefsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
[19/62] AVX512FP16: Add testcase for vrcpph/vrcpsh/vscalefph/vscalefsh. Support all AVX512FP16 intrinsics. - - - - --- 2021-07-01 Liu, Hongtao New
« 1 2 3 4 … 5 6 »