aboutsummaryrefslogtreecommitdiff
path: root/gcc/config/gcn
AgeCommit message (Expand)AuthorFilesLines
2023-11-27GCN: Remove 'last_arg' spec functionThomas Schwinge3-43/+1
2023-11-27GCN: Tag '-march=[...]', '-mtune=[...]' as 'Negative' of themselves [PR112669]Thomas Schwinge1-2/+2
2023-11-27amdgcn: Disallow TImode vector permuteAndrew Stubbs1-1/+3
2023-11-22amdgcn: Fix vector TImode reload loopAndrew Stubbs1-4/+4
2023-11-15amdgcn: Add Accelerator VGPR registersAndrew Stubbs7-191/+533
2023-11-15amdgcn: simplify secondary reload patternsAndrew Stubbs2-90/+4
2023-11-10amdgcn: Fix v_add constraints (pr112308)Andrew Stubbs1-50/+68
2023-11-10amdgcn: Fix vector min/max ICEAndrew Stubbs1-1/+9
2023-11-07openmp: Add support for the 'indirect' clause in C/C++Kwok Cheung Yeung1-2/+27
2023-10-27amdgcn: Fix bug in gfx1030 support patchAndrew Stubbs1-4/+2
2023-10-27amdgcn: silence warningsAndrew Stubbs2-3/+5
2023-10-20amdgcn: add -march=gfx1030 EXPERIMENTALAndrew Stubbs9-87/+183
2023-10-19amdgcn: deprecate Fiji device and multilibAndrew Stubbs1-2/+6
2023-10-06amdgcn: switch mov insns to compact syntaxAndrew Stubbs2-130/+108
2023-10-06amdgcn: silence warningAndrew Stubbs1-1/+1
2023-08-09targhooks: Extend legitimate_address_p with code_helper [PR110248]Kewen Lin1-1/+1
2023-06-19amdgcn: implement vector div and mod libfuncsAndrew Stubbs1-0/+244
2023-06-19amdgcn: minimal V64TImode vector supportAndrew Stubbs3-130/+299
2023-06-14driver: Forward '-lgfortran', '-lm' to offloading compilationThomas Schwinge1-0/+12
2023-05-26amdgcn: Change -m(no-)xnack to -mxnack=(on,off,any)Tobias Burnus5-29/+47
2023-05-18gcc/config/*: use _P() defines from tree.hBernhard Reutner-Fischer2-3/+3
2023-05-05GCN: Silence unused-variable warningTobias Burnus1-2/+0
2023-04-27amdgcn: Fix addsub bugAndrew Stubbs1-8/+15
2023-04-20amdgcn: bug fix ldexp insnAndrew Stubbs1-16/+9
2023-04-18amdgcn: HardFP divideAndrew Stubbs3-96/+144
2023-04-04amdgcn: Add 64-bit vector notAndrew Stubbs1-0/+17
2023-03-23amdgcn: Fix register size bugAndrew Stubbs1-0/+13
2023-03-23amdgcn: vec_extract no-op insnsAndrew Stubbs4-9/+78
2023-03-22amdgcn: Add instruction patterns for complex number operations.Andrew Jenner4-0/+348
2023-03-13gcn/mkoffload.cc: Pass -save-temps on for the hsaco stepTobias Burnus1-0/+3
2023-03-06amdgcn: Add instruction patterns for conditional min/max operationsPaul-Antoine Arras2-2/+137
2023-03-02amdgcn: Enable SIMD vectorization of math functionsKwok Cheung Yeung1-0/+110
2023-02-06amdgcn: Pass -mstack-size through to runtimeAndrew Stubbs1-0/+18
2023-02-02amdgcn: Add instruction pattern for conditional shift operationsPaul-Antoine Arras1-0/+23
2023-02-02amdgcn, libgomp: Manually allocated stacksAndrew Stubbs4-111/+147
2023-01-16Update copyright years.Jakub Jelinek18-18/+18
2022-12-01amdgcn: Add preprocessor builtins for every processor typePaul-Antoine Arras2-14/+32
2022-11-30amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectorsPaul-Antoine Arras2-2/+2
2022-11-28gcn: Fix __builtin_gcn_first_call_this_thread_pTobias Burnus2-21/+8
2022-11-25OpenMP: Generate SIMD clones for functions with "declare target"Sandra Loosemore1-4/+6
2022-11-22gcn: Add __builtin_gcn_{get_stack_limit,first_call_this_thread_p}Tobias Burnus3-2/+87
2022-11-16gcn: Add __builtin_gcn_kernarg_ptrTobias Burnus2-4/+24
2022-11-08amdgcn: Fix expansion of GCN_BUILTIN_LDEXPV builtinKwok Cheung Yeung1-1/+1
2022-11-08amdgcn: Add builtins for vectorized native versions of abs, floorf and floorKwok Cheung Yeung2-0/+48
2022-11-03amdgcn: Fix instruction generation for exp2 and log2 operationsKwok Cheung Yeung1-6/+14
2022-11-03amdgcn: Fix duplicate conditionals [PR107510]Andrew Stubbs1-2/+0
2022-10-31amdgcn: add fmin/fmax patternsAndrew Stubbs2-0/+32
2022-10-31amdgcn: multi-size vector reductionsAndrew Stubbs3-94/+45
2022-10-31amdgcn: Silence unused parameter warningAndrew Stubbs1-1/+1
2022-10-20amdgcn: Use FLAT addressing for all functions with pointer arguments [PR105421]Julian Brown1-6/+9
generated by cgit v1.1 at 2025-01-10 06:32:19 +0000