aboutsummaryrefslogtreecommitdiff
path: root/libgomp/plugin
AgeCommit message (Expand)AuthorFilesLines
2020-06-17amdgcn: Switch to HSACO v3 binary formatAndrew Stubbs1-230/+5
2020-04-23amdgcn: Check HSA return codes [PR94629]Andrew Stubbs1-0/+8
2020-02-13openmp: ignore nowait if async execution is unsupported [PR93481]Frederik Harwath1-6/+1
2020-02-03Remove gfx801 "carrizo" supportAndrew Stubbs1-9/+0
2020-01-31[amdgcn] Scale number of threads/workers with VGPR usageKwok Cheung Yeung1-0/+23
2020-01-30Skip plugin-{gcn,hsa} for (-m)x32 (PR bootstrap/93409)Tobias Burnus1-2/+2
2020-01-29Add OpenACC acc_get_property support for AMD GCNFrederik Harwath1-10/+63
2020-01-23Fix libgomp plugin-gcn bugAndrew Stubbs1-1/+2
2020-01-21Add runtime ISA check for amdgcn offloadingFrederik Harwath1-4/+127
2020-01-10OpenACC 'acc_get_property' cleanupThomas Schwinge3-105/+81
2020-01-01Update copyright years.Jakub Jelinek7-7/+7
2019-12-28re PR bootstrap/93074 (build FAIL with --enable-offload-targets=nvptx-none)Jakub Jelinek1-0/+6
2019-12-22Add OpenACC 2.6 `acc_get_property' supportMaciej W. Rozycki4-1/+127
2019-12-11libgomp – spelling fixes, incl. omp_lib.h.inTobias Burnus1-3/+3
2019-11-20AMD GCN libgomp plugin queue-full condition locking fixJulian Brown1-13/+10
2019-11-20Fix host-to-device copies from rodata for AMD GCNJulian Brown1-4/+34
2019-11-13GCN Libgomp PluginAndrew Stubbs3-0/+4034
2019-11-13Add device number to GOMP_OFFLOAD_openacc_async_constructAndrew Stubbs1-1/+1
2019-10-01configure.ac: Remove GCC_HEADER_STDINT(gstdint.h).Jakub Jelinek2-2/+1
2019-09-13libgomp plugin - init stringTobias Burnus1-3/+3
2019-05-24re PR libgomp/90585 (libgomp hsa plugin ftbfs in the x32 multilib variant)Jakub Jelinek2-9/+20
2019-05-17OpenACC Profiling Interface (incomplete)Thomas Schwinge1-6/+190
2019-05-132019-05-13 Chung-Lin Tang <cltang@codesourcery.com>Chung-Lin Tang3-1023/+317
2019-02-22[libgomp] In OpenACC testing, cycle though all offload targetsThomas Schwinge1-0/+5
2019-02-22[libgomp] Clarify difference between offload target, offload plugin, and Open...Thomas Schwinge1-17/+19
2019-01-24[nvptx, libgomp] Fix memleak in GOMP_OFFLOAD_fini_deviceTom de Vries1-0/+6
2019-01-23[nvptx, libgomp] Fix cuMemAlloc with size zeroTom de Vries1-20/+28
2019-01-23[nvptx, libgomp] Fix assert (!s->map->active) in map_finiTom de Vries1-2/+25
2019-01-23[nvptx, libgomp] Fix map_pushTom de Vries1-18/+29
2019-01-12[nvptx] Enable setting vector length using -fopenacc-dimTom de Vries1-1/+1
2019-01-12[nvptx] Update insufficient launch message for variable vector_lengthTom de Vries1-8/+10
2019-01-11[nvptx] Don't allow vector_length 64 with num_workers 16Tom de Vries1-0/+22
2019-01-09[nvptx, libgomp] Don't launch with num_workers == 0Tom de Vries1-0/+1
2019-01-01Update copyright years.Jakub Jelinek6-6/+6
2018-12-14[PR88495] An OpenACC async queue is always synchronized with itselfThomas Schwinge1-1/+2
2018-12-14[PR88407] [OpenACC] Correctly handle unseen async-argumentsThomas Schwinge1-7/+6
2018-12-14[PR88370] acc_get_cuda_stream/acc_set_cuda_stream: acc_async_sync, acc_async_...Thomas Schwinge1-2/+8
2018-09-18[nvptx] Remove use of CUDA unified memory in libgompCesar Philippidis1-79/+91
2018-08-13[nvptx] Use CUDA driver API to select default runtime launch geometryCesar Philippidis3-12/+75
2018-08-08[libgomp, nvptx] Fall back to cuLinkAddData/cuLinkCreate if _v2 not foundTom de Vries2-4/+26
2018-08-08[libgomp, nvptx] Allow cuGetErrorString to be NULLTom de Vries2-4/+8
2018-08-08[libgomp, nvptx] Remove hard-coded const in nvptx_open_deviceTom de Vries1-2/+5
2018-08-08[libgomp, nvptx] Note that cuGetErrorString is in CUDA_VERSION >= 6000Tom de Vries1-5/+4
2018-08-06[libgomp, nvptx] Handle CUDA_ONE_CALL_MAYBE_NULLTom de Vries1-3/+20
2018-08-06[libgomp, nvptx] Minimize lifetime of CUDA_ONE_CALL definesTom de Vries1-5/+9
2018-08-04[libgomp, nvptx, --without-cuda-driver] Don't use system cuda driverTom de Vries1-22/+33
2018-08-01[PATCH] Remove use of 'struct map' from plugin (nvptx)Cesar Philippidis1-27/+6
2018-08-01[libgomp, nvptx] Add cuda-lib.defTom de Vries2-49/+48
2018-07-30[libgomp, nvptx] Handle per-function max-threads-per-block in default dimsTom de Vries1-4/+25
2018-07-30[libgomp, nvptx] Calculate default dims per deviceTom de Vries1-7/+21