Age | Commit message (Expand) | Author | Files | Lines |
37 hours | SVE intrinsics: Add fold_active_lanes_to method to refactor svmul and svdiv. | Jennifer Schmitz | 14 | -72/+342 |
42 hours | AArch64: support encoding integer immediates using floating point moves | Tamar Christina | 1 | -0/+87 |
42 hours | AArch64: update testsuite to account for new zero moves | Tamar Christina | 52 | -412/+410 |
5 days | SVE intrinsics: Fold svmul with constant power-of-2 operand to svlsl | Jennifer Schmitz | 9 | -242/+2577 |
6 days | simplify-rtx: Fix incorrect folding of shift and AND [PR117012] | Tamar Christina | 1 | -0/+16 |
6 days | AArch64: rename the SVE2 psel intrinsics to psel_lane [PR116371] | Tamar Christina | 16 | -694/+694 |
6 days | aarch64: Fix folding of degenerate svwhilele case [PR117045] | Richard Sandiford | 3 | -1/+66 |
9 days | aarch64: Add codegen support for SVE2 faminmax | Saurabh Jha | 2 | -0/+104 |
9 days | aarch64: Add SVE2 faminmax intrinsics | Saurabh Jha | 6 | -0/+2586 |
9 days | aarch64: Alter pr116258.c test to correct for big endian. | Richard Ball | 1 | -1/+2 |
11 days | aarch64: Fix SVE ACLE gimple folds for C++ LTO [PR116629] | Richard Sandiford | 1 | -0/+381 |
11 days | tree-optimization/116024 - simplify some cases of X +- C1 cmp C2 | Artemiy Volkov | 1 | -1/+1 |
12 days | aarch64: Expand CTZ to RBIT + CLZ for SVE [PR109498] | Soumya AR | 1 | -0/+49 |
13 days | gcc: Remove executable permissions of testcases and *.md files | Jakub Jelinek | 6 | -0/+0 |
13 days | aarch64: Fix general permutes of svbfloat16_ts | Richard Sandiford | 1 | -0/+10 |
13 days | aarch64: Handle SVE modes in aarch64_evpc_reencode [PR116583] | Richard Sandiford | 4 | -0/+587 |
2024-10-04 | aarch64: Fix bug with max/min (PR116934) | Saurabh Jha | 1 | -0/+13 |
2024-10-01 | aarch64: Add fp8 scalar types | Claudio Bantaloukas | 2 | -0/+490 |
2024-09-30 | autovectorizer: Test autovectorization of different dot-prod modes. | Victor Do Nascimento | 1 | -0/+66 |
2024-09-30 | aarch64: Fix aarch64 backend-use of (u|s|us)dot_prod patterns | Victor Do Nascimento | 1 | -0/+26 |
2024-09-23 | aarch64: Add codegen support for AdvSIMD faminmax | Saurabh Jha | 3 | -0/+681 |
2024-09-23 | aarch64: Add AdvSIMD faminmax intrinsics | Saurabh Jha | 2 | -0/+125 |
2024-09-22 | aarch64: Take into account when VF is higher than known scalar iters | Tamar Christina | 9 | -29/+66 |
2024-09-19 | SVE intrinsics: Fold svmul with all-zero operands to zero vector | Jennifer Schmitz | 2 | -2/+367 |
2024-09-17 | SVE intrinsics: Fold svdiv with all-zero operands to zero vector | Jennifer Schmitz | 2 | -8/+373 |
2024-09-16 | aarch64: Improve vector constant generation using SVE INDEX instruction [PR11... | Pengxuan Zheng | 5 | -8/+103 |
2024-09-16 | aarch64: Emit ADD X, Y, Y instead of SHL X, Y, #1 for SVE instructions. | Soumya AR | 34 | -93/+136 |
2024-09-09 | middle-end: also optimized `popcount(a) <= 1` [PR90693] | Andrew Pinski | 3 | -0/+91 |
2024-09-05 | [AARCH64] adjust gcc.target/aarch64/sve/mask_gather_load_7.c | Richard Biener | 1 | -4/+4 |
2024-09-03 | aarch64: Fix testcase vec-init-22-speed.c [PR116589] | Andrew Pinski | 1 | -1/+1 |
2024-09-03 | SVE intrinsics: Fold constant operands for svmul. | Jennifer Schmitz | 1 | -0/+302 |
2024-09-03 | SVE intrinsics: Fold constant operands for svdiv. | Jennifer Schmitz | 1 | -0/+358 |
2024-08-31 | phiopt: Ignore some nop statements in heursics [PR116098] | Andrew Pinski | 1 | -0/+28 |
2024-08-29 | expand: Allow widdening optab when expanding popcount==1 [PR116508] | Andrew Pinski | 1 | -0/+45 |
2024-08-28 | aarch64: Add a test for zeroing <64bits>x2_t structures | Richard Sandiford | 1 | -0/+21 |
2024-08-23 | ifcvt: disallow call instructions in noce_convert_multiple_sets [PR116358] | Manolis Tsamis | 1 | -0/+15 |
2024-08-22 | PR target/116365: Add user-friendly arguments to --param aarch64-autovec-pref... | Jennifer Schmitz | 14 | -9/+29 |
2024-08-22 | PR tree-optimization/101390: Vectorize modulo operator | Jennifer Schmitz | 1 | -0/+28 |
2024-08-21 | aarch64: Fix caller saves of VNx2QI [PR116238] | Richard Sandiford | 1 | -0/+13 |
2024-08-21 | aarch64: Implement popcountti2 pattern [PR113042] | Andrew Pinski | 2 | -0/+50 |
2024-08-19 | aarch64: Fix ls64 intrinsic availability | Andrew Carlotti | 4 | -0/+38 |
2024-08-19 | aarch64: Fix memtag intrinsic availability | Andrew Carlotti | 4 | -0/+38 |
2024-08-19 | aarch64: Fix tme intrinsic availability | Andrew Carlotti | 4 | -0/+38 |
2024-08-15 | aarch64: Improve popcount for bytes [PR113042] | Andrew Pinski | 4 | -0/+74 |
2024-08-15 | aarch64: Rename svpext to svpext_lane [PR116371] | Richard Sandiford | 16 | -416/+416 |
2024-08-12 | ifcvt: Handle multiple rewired regs and refactor noce_convert_multiple_sets | Manolis Tsamis | 1 | -0/+20 |
2024-08-12 | ifcvt: Allow more operations in multiple set if conversion | Manolis Tsamis | 1 | -0/+79 |
2024-08-12 | aarch64: Emit ADD X, Y, Y instead of SHL X, Y, #1 for Advanced SIMD | Kyrylo Tkachov | 1 | -0/+64 |
2024-08-08 | aarch64/testsuite: Fix if-compare_2.c for removing vcond{,u,eq} patterns [PR1... | Andrew Pinski | 1 | -2/+7 |
2024-08-08 | AArch64: Fix signbit mask creation after late combine [PR116229] | Tamar Christina | 1 | -0/+20 |