diff options
| author | Tom de Vries <tdevries@suse.de> | 2020-10-08 08:22:39 +0200 |
|---|---|---|
| committer | Tom de Vries <tdevries@suse.de> | 2020-10-08 11:03:29 +0200 |
| commit | 7345ef6c2a197d0a2581c67838b7ba1650dfad30 (patch) | |
| tree | 567612353abd9396dafae46f8565935709794b88 | |
| parent | c1c62aec6751678e958ab5c61b2d903a09d7efd9 (diff) | |
| download | gcc-7345ef6c2a197d0a2581c67838b7ba1650dfad30.zip gcc-7345ef6c2a197d0a2581c67838b7ba1650dfad30.tar.gz gcc-7345ef6c2a197d0a2581c67838b7ba1650dfad30.tar.bz2 | |
[libgomp, nvptx] Report launch dimensions in GOMP_OFFLOAD_run
Using this patch, when using GOMP_DEBUG=1 and launching a kernel in
GOMP_OFFLOAD_run (used by the omp implementation), we see the kernel launch
dimensions:
...
GOMP_OFFLOAD_run: kernel main$_omp_fn$0: \
launch [(teams: 1), 1, 1] [(lanes: 32), (threads: 1), 1]
...
Build on x86_64-linux with nvptx accelerator, tested libgomp.
libgomp/ChangeLog:
2020-10-08 Tom de Vries <tdevries@suse.de>
PR libgomp/81802
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_run): Report launch
dimensions.
| -rw-r--r-- | libgomp/plugin/plugin-nvptx.c | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c index a63dd1a..11d4cee 100644 --- a/libgomp/plugin/plugin-nvptx.c +++ b/libgomp/plugin/plugin-nvptx.c @@ -1891,7 +1891,11 @@ nvptx_stacks_free (void *p, int num) void GOMP_OFFLOAD_run (int ord, void *tgt_fn, void *tgt_vars, void **args) { - CUfunction function = ((struct targ_fn_descriptor *) tgt_fn)->fn; + struct targ_fn_descriptor *tgt_fn_desc + = (struct targ_fn_descriptor *) tgt_fn; + CUfunction function = tgt_fn_desc->fn; + const struct targ_fn_launch *launch = tgt_fn_desc->launch; + const char *fn_name = launch->fn; CUresult r; struct ptx_device *ptx_dev = ptx_devices[ord]; const char *maybe_abort_msg = "(perhaps abort was called)"; @@ -1926,6 +1930,9 @@ GOMP_OFFLOAD_run (int ord, void *tgt_fn, void *tgt_vars, void **args) CU_LAUNCH_PARAM_BUFFER_SIZE, &fn_args_size, CU_LAUNCH_PARAM_END }; + GOMP_PLUGIN_debug (0, " %s: kernel %s: launch" + " [(teams: %u), 1, 1] [(lanes: 32), (threads: %u), 1]\n", + __FUNCTION__, fn_name, teams, threads); r = CUDA_CALL_NOCHECK (cuLaunchKernel, function, teams, 1, 1, 32, threads, 1, 0, NULL, NULL, config); if (r != CUDA_SUCCESS) |