]> git.ipfire.org Git - thirdparty/gcc.git/history - gcc/config/i386/sse.md
x86: allow memory operand for AVX2 splitter for PR target/100711
[thirdparty/gcc.git] / gcc / config / i386 / sse.md
2023-07-05  Jan Beulichx86: allow memory operand for AVX2 splitter for PR...
2023-07-05  Jan Beulichx86: use VPTERNLOG also for certain andnot forms
2023-07-05  Jan Beulichx86: use VPTERNLOG for further bitwise two-vector opera...
2023-06-27  liuhongtRefine maskstore patterns with UNSPEC_MASKMOV.
2023-06-25  liuhongtRefine maskloadmn pattern with UNSPEC_MASKLOAD.
2023-06-22  Roger Saylei386: Convert ptestz of pandn into ptestc.
2023-06-21  Jan Beulichx86: make VPTERNLOG* usable on less than 512-bit operan...
2023-06-20  Jan Beulichx86: correct and improve "*vec_dupv2di"
2023-06-19  liuhongtRefined 256/512-bit vpacksswb/vpackssdw patterns.
2023-06-19  liuhongtReimplement packuswb/packusdw with UNSPEC_US_TRUNCATE...
2023-06-15  Jan Beulichx86/AVX512: use VMOVDDUP for broadcast to V2DF
2023-06-14  liuhongtUse x instead of v for alternative 2 (v, BH) in mov...
2023-06-12  liuhongtAdd missing vec_pack/unpacks patterns for _Float16...
2023-06-01  Roger SaylePR target/109973: CCZmode and CCCmode variants of ...
2023-05-27  liuhongtSplit notl + pbraodcast + pand to pbroadcast + pandn...
2023-05-24  Uros Bizjaki386: Add v<any_shift:insn>v4qi3 expander
2023-05-18  Uros Bizjaki386: Add infrastructure for QImode partial vector...
2023-04-20  Haochen Jiangi386: Share AES xmm intrin with VAES
2023-04-20  Haochen Jiangi386: Add PCLMUL dependency for VPCLMULQDQ
2023-04-20  Haochen Jiangi386: Fix vpblendm{b,w} intrins and insns
2023-04-20  Haochen Jiangi386: Add AVX512BW dependency to AVX512VBMI2
2023-04-20  Haochen Jiangi386: Add AVX512BW dependency to AVX512BITALG
2023-04-20  Hu, Lin1Optimize vshuf{i,f}{32x4,64x2} ymm and vperm{i,f}128 ymm
2023-04-18  Uros Bizjaki386: Improve permutations with INSERTPS instruction...
2023-03-31  liuhongtRename ufix_trunc/ufloat* patterns to fixuns_trunc...
2023-01-16  Jakub JelinekUpdate copyright years.
2022-12-25  Roger SayleUse movss/movsd to implement V4SI/V2DI VEC_PERM on...
2022-11-09  liuhongtFix incorrect insn type to avoid ICE in memory attr...
2022-11-08  Jakub Jelineki386: Improve vector [GL]E{,U} comparison against vecto...
2022-11-01  liuhongtFix incorrect digit constraint
2022-10-31  konglin1Support Intel AVX-NE-CONVERT
2022-10-31  konglin1i386:: using __bf16 for AVX512BF16 intrinsics
2022-10-21  Haochen Jiangi386: Auto vectorize sdot_prod, udot_prod with VNNIINT8...
2022-10-21  Kong LinglingSupport Intel AVX-VNNI-INT8
2022-10-21  Hongyu WangSupport Intel AVX-IFMA
2022-09-28  H.J. Lui386: Mark XMM4-XMM6 as clobbered by encodekey128/encod...
2022-09-23  Hu, Lin1i386: Optimize code generation of __mm256_zextsi128_si2...
2022-09-16  liuhongtModernize ix86_builtin_vectorized_function with corresp...
2022-09-06  liuhongtFix _mm512_cvt_roundps_ph to generate sae instruction.
2022-09-05  konglin1x86: Handle V8BF in expand_vec_perm_broadcast_1
2022-08-29  H.J. Lux86: Handle V16BF in ix86_avx256_split_vector_move_misalign
2022-08-24  Jakub Jelineki386: Fix up mode iterators that weren't expanded ...
2022-08-18  konglin1x86: Support vector __bf16 type
2022-08-13  Roger SayleMove V1TI shift/rotate lowering from expand to pre...
2022-08-09  Roger SayleUse PTEST to perform AND in TImode STV of (A & B) ...
2022-07-18  Roger SayleAdd UNSPEC_MASKOP to kupck<mode> instructions in sse...
2022-07-08  Haochen Jiangi386: Handle memory operand for direct call to cvtps2pd...
2022-07-05  Roger SayleUNSPEC_PALIGNR optimizations and clean-ups on x86.
2022-07-04  Haochen Jiangi386: Extend cvtps2pd to memory
2022-06-30  Antoni Bouchertarget: Fix asm generation for AVX builtins when using...
2022-06-23  liuhongtReplace REGNO with reg_or_subregno in pre_reload splitter.
2022-06-17  Uros Bizjaki386: Fix VPMOV splitter [PR105993]
2022-06-15  liuhongtFix ICE in extract_insn, at recog.cc:2791
2022-06-08  liuhongtDisparages SSE_REGS alternatives sligntly with ?v inste...
2022-06-07  liuhongtFix insn does not satisfy its constraints: sse2_lshrv1ti3
2022-06-07  Roger SayleRecognize vpcmov in combine with -mxop on x86.
2022-06-03  Jan Beulichx86: {,v}psadbw have commutative source operands
2022-06-02  Roger SaylePR target/105791: Add V1TI to V_128_256 for xop_pcmov_v...
2022-05-30  Roger SaylePR target/70321: Split double word equality/inequality...
2022-05-30  Uros Bizjaki386: Remove constraints when used with constant intege...
2022-05-24  Prathamesh KulkarniAdd new parameter to vec_perm_const hook for specifying...
2022-05-24  Roger SaylePR tree-optimization/105668: Provide vcond_mask_v1tiv1t...
2022-05-17  Uros Bizjaki386: Fix ICE in final_scan_insn_1 [PR105624]
2022-05-17  Jakub Jelineki386: Fix up V2DI and V1TI inequality comparisons ...
2022-05-17  liuhongtOptimize vpermtiw/b to vpunpcklqdq for certain cases.
2022-05-15  Uros Bizjaki386: Remove constraints when used with constant intege...
2022-05-13  Roger SayleImproved V1TI (and V2DI) mode equality/inequality on...
2022-05-12  Haochen Jiangi386: Add combine splitter to transform pxor/pcmpeqb...
2022-05-11  liuhongtOptimize movzwl + vmovd/vmovq to vmovw.
2022-05-09  liuhongtOptimize vec_setv8{hi,hf}_0 + pmovzxbq to pmovzxbq.
2022-05-03  Uros Bizjaki386: Optimize _mm_storeu_si16 w/o SSE4 [PR105079]
2022-04-07  liuhongtRefine and/ior/xor/andn masked patterns for V*HFmode.
2022-04-06  Roger SayleSupport pandn for V1TI mode (i.e. *andnotv1ti3).
2022-03-28  H.J. Lux86: Also use Yw in *ssse3_pshufbv8qi3 clobber
2022-03-28  liuhongtFix typo in vec_setv8hi_0.
2022-03-27  H.J. Lux86: Use Yw constraint on *ssse3_pshufbv8qi3
2022-03-26  H.J. Lux86: Use x constraint on KL patterns
2022-03-26  H.J. Lux86: Use x constraint on SSSE3 patterns with MMX operands
2022-03-23  liuhongtFix ICE caused by NULL_RTX returned by lowpart_subreg.
2022-03-22  Hongyu WangAVX512FP16: Fix wrong code for _mm_mask_f[c]madd.*sch...
2022-03-21  Hongyu WangAVX512FP16: Fix masm=intel output for vfc?(madd|mul...
2022-03-16  Roger SayleFix strange binary corruption with last commit.
2022-03-16  Roger SaylePR target/94680: Clear upper bits of V2DF using movq...
2022-03-08  liuhongtOptimize v4si broadcast for noavx512vl.
2022-03-07  Jakub Jelineki386: Fix up cond_{and,ior,xor,mul}* [PR104779]
2022-02-24  liuhongtFix typo in <code>v1ti3.
2022-02-10  Uros Bizjaki386: Fix vec_unpacks_float_lo_v4si operand constraint...
2022-02-09  liuhongtICE: QImode(not SImode) operand should be passed to...
2022-01-19  Jakub Jelineki386: Fix *aes<aeswideklvariant>u8
2022-01-19  Jakub Jelineki386: Fix GLC tuning with -masm=intel [PR104104]
2022-01-17  Martin LiskaChange references of .c files to .cc files
2022-01-16  wwwhhhyyy[i386] GLC tuning: Break false dependency for dest...
2022-01-15  Uros Bizjaki386: Improve and optimize ix86_expand_sse_movcc
2022-01-11  Haochen JiangExtend predicate of operands[1] from register_operand...
2022-01-07  liuhongtSupport commutative alternative for AVX512 vpcmpeq...
2022-01-07  liuhongtOptimize V16HF vector insert to element 0 for AVX2.
2022-01-04  liuhongtForce_reg operand 1.
2022-01-03  Jakub JelinekUpdate copyright years.
2021-12-29  Uros Bizjaki386: Robustify some expanders w.r.t. paradoxical SUBREGs
2021-12-23  liuhongtCombine vpcmpuw + zero_extend to vpcmpuw.
next