[gcc r15-635] MAINTAINERS: Add myself to write after approval

https://gcc.gnu.org/g:6daed961542a9d5e83f9b94a3ee91f918f4268a5 commit r15-635-g6daed961542a9d5e83f9b94a3ee91f918f4268a5 Author: Levy Hsu Date: Sat May 18 02:20:18 2024 +0800 MAINTAINERS: Add myself to write after approval ChangeLog: * MAINTAINERS: Add myself. Dif

[gcc r15-3391] i386: Support partial vectorized V2BF/V4BF plus/minus/mult/div/sqrt

https://gcc.gnu.org/g:8e16f26ca9fad685b9b723da7112ffcc99e81593 commit r15-3391-g8e16f26ca9fad685b9b723da7112ffcc99e81593 Author: Levy Hsu Date: Mon Aug 26 10:46:30 2024 +0930 i386: Support partial vectorized V2BF/V4BF plus/minus/mult/div/sqrt This patch introduces new mode iterato

[gcc r15-3392] i386: Support partial vectorized V2BF/V4BF smaxmin

https://gcc.gnu.org/g:62df24e50039ae04aa3b940e680cffd9041ef5bf commit r15-3392-g62df24e50039ae04aa3b940e680cffd9041ef5bf Author: Levy Hsu Date: Tue Aug 27 14:22:20 2024 +0930 i386: Support partial vectorized V2BF/V4BF smaxmin This patch supports sminmax for partial vectorized V2BF

[gcc r15-3461] i386: Integrate BFmode for Enhanced Vectorization in ix86_preferred_simd_mode

https://gcc.gnu.org/g:b851bce473d8e573b1b586c71d47e71067b4fa66 commit r15-3461-gb851bce473d8e573b1b586c71d47e71067b4fa66 Author: Levy Hsu Date: Tue Sep 3 15:44:06 2024 +0930 i386: Integrate BFmode for Enhanced Vectorization in ix86_preferred_simd_mode This change adds BFmode supp

[gcc r15-3462] i386: Support partial signbit/xorsign/copysign/abs/neg/and/xor/ior/andn for V2BF/V4BF

https://gcc.gnu.org/g:d0c86be1ce7131aeca2cf3304a8d65a00da4f12a commit r15-3462-gd0c86be1ce7131aeca2cf3304a8d65a00da4f12a Author: Levy Hsu Date: Mon Sep 2 13:27:46 2024 +0930 i386: Support partial signbit/xorsign/copysign/abs/neg/and/xor/ior/andn for V2BF/V4BF This patch adds supp

[gcc r15-3464] i386: Support partial vectorized FMA for V2BF/V4BF

https://gcc.gnu.org/g:f9ca3fd1fe30f3ee6725bfe4a612e9a1234c11ac commit r15-3464-gf9ca3fd1fe30f3ee6725bfe4a612e9a1234c11ac Author: Levy Hsu Date: Mon Sep 2 13:52:38 2024 +0800 i386: Support partial vectorized FMA for V2BF/V4BF This patch introduces support for vectorized FMA operati

[gcc r15-3561] x86: Refine V4BF/V2BF FMA Testcase

https://gcc.gnu.org/g:3d031cc4465a32bbc82c96e3e07894eb6dc4d3ec commit r15-3561-g3d031cc4465a32bbc82c96e3e07894eb6dc4d3ec Author: Levy Hsu Date: Tue Sep 10 15:12:09 2024 +0930 x86: Refine V4BF/V2BF FMA Testcase gcc/testsuite/ChangeLog: * gcc.target/i386/avx10_2-par

[gcc r15-3596] i386: Enable V2BF/V4BF vec_cmp with AVX10.2 vcmppbf16

https://gcc.gnu.org/g:89d50c45048e5d7230ddde9afc8fbc83143e34cb commit r15-3596-g89d50c45048e5d7230ddde9afc8fbc83143e34cb Author: Levy Hsu Date: Wed Sep 4 16:34:04 2024 +0930 i386: Enable V2BF/V4BF vec_cmp with AVX10.2 vcmppbf16 gcc/ChangeLog: * config/i386/i386.cc

[gcc r15-1896] x86: Support bitwise and/andnot/abs/neg/copysign/xorsign op for V8BF/V16BF/V32BF

https://gcc.gnu.org/g:f3f9e4ee7642e5131f2d6607f764267df7d233d4 commit r15-1896-gf3f9e4ee7642e5131f2d6607f764267df7d233d4 Author: Levy Hsu Date: Mon Jul 8 14:59:35 2024 + x86: Support bitwise and/andnot/abs/neg/copysign/xorsign op for V8BF/V16BF/V32BF This patch extends suppor

[gcc r15-841] x86: Fix Logical Shift Issue in expand_vec_perm_psrlw_psllw_por [PR115146]

https://gcc.gnu.org/g:0022064649d0ec40e97df24279c48842e278fedc commit r15-841-g0022064649d0ec40e97df24279c48842e278fedc Author: Levy Hsu Date: Tue May 21 12:47:21 2024 +0930 x86: Fix Logical Shift Issue in expand_vec_perm_psrlw_psllw_por [PR115146] Replaced arithmetic shifts with

[gcc r15-1368] x86: Emit cvtne2ps2bf16 for odd increasing perm in __builtin_shufflevector

https://gcc.gnu.org/g:6d0b7b69d143025f271d0041cfa29cf26e6c343b commit r15-1368-g6d0b7b69d143025f271d0041cfa29cf26e6c343b Author: Levy Hsu Date: Thu Jun 13 15:20:04 2024 +0930 x86: Emit cvtne2ps2bf16 for odd increasing perm in __builtin_shufflevector This patch updates the GCC x86

[gcc r15-4232] x86: Implement Fast-Math Float Truncation to BF16 via PSRLD Instruction

https://gcc.gnu.org/g:8718727509b2d038d00afa3bd5ef8e0df216a287 commit r15-4232-g8718727509b2d038d00afa3bd5ef8e0df216a287 Author: Levy Hsu Date: Wed Sep 25 14:32:35 2024 +1100 x86: Implement Fast-Math Float Truncation to BF16 via PSRLD Instruction gcc/ChangeLog: *

[gcc r15-3886] x86: Extend AVX512 Vectorization for Popcount in Various Modes

https://gcc.gnu.org/g:85910e650a61de6da37e3d67a7ac208904dd3c0d commit r15-3886-g85910e650a61de6da37e3d67a7ac208904dd3c0d Author: Levy Hsu Date: Wed Sep 11 14:19:02 2024 +0930 x86: Extend AVX512 Vectorization for Popcount in Various Modes This patch enables vectorization of the pop