Hi Kamil,
Hi Nirmoy, On 2024-06-18 at 19:32:47 +0200, Nirmoy Das wrote: [PATCH i-g-t v2] tests/intel/xe_exec_store: Add basic_inst_benchmark -----------------------------------------------------^ You should use '-', also your subtest has 'store', so: [PATCH i-g-t v2] tests/intel/xe_exec_store: Add basic-store-benchmark
Will do that
Add basic_inst_benchmark to benchmark this basic operation for BO sizes to get basic understanding how long it takes bind a BO and run simple GPU command on it. This not a CI test but rather for developer to identify various bottleneck/regression in BO binding. Signed-off-by: Nirmoy Das <nirmoy.das@intel.com> --- tests/intel/xe_exec_store.c | 110 ++++++++++++++++++++++++++++++------ 1 file changed, 92 insertions(+), 18 deletions(-)This didn't work on my ATS-M machine: sudo build/tests/xe_exec_store --r basic-store-benchmark IGT-Version: 1.28-g64414e4da (x86_64) (Linux: 6.9.0-rc6-xe-public-513ea833c201+ x86_64) Using IGT_SRANDOM=1718890917 for randomisation Opened device: /dev/dri/card0 Starting subtest: basic-store-benchmark Starting dynamic subtest: WC Dynamic subtest WC: SUCCESS (0.000s) (xe_exec_store:15881) xe/xe_ioctl-CRITICAL: Test assertion failure function xe_bo_create_caching, file ../lib/xe/xe_ioctl.c:311: (xe_exec_store:15881) xe/xe_ioctl-CRITICAL: Failed assertion: __xe_bo_create_caching(fd, vm, size, placement, flags, cpu_caching, &handle) == 0 (xe_exec_store:15881) xe/xe_ioctl-CRITICAL: Last errno: 22, Invalid argument (xe_exec_store:15881) xe/xe_ioctl-CRITICAL: error: -1 != 0
I guess WC cache is not allowed on dGFX, dmesg should let us know. I will check and fix it. Thanks for trying it out.
It should something like:Also, where are benchmarks? Do you print them only after WC and WB runs?
sudo ~/igt-gpu-tools/build/tests/xe_exec_store --run basic-store-benchmark
IGT-Version: 1.28-g2ed908c0b (x86_64) (Linux: 6.10.0-rc2-xe+ x86_64)
Using IGT_SRANDOM=1718739607 for randomisation
Opened device: /dev/dri/card0
Starting subtest: basic-store-benchmark
Starting dynamic subtest: WC
Dynamic subtest WC: SUCCESS (0.000s)
Time taken for size SZ_4K: 8 ms
Time taken for size SZ_2M: 7 ms
Time taken for size SZ_64M: 15 ms
Time taken for size SZ_128M: 16 ms
Time taken for size SZ_256M: 33 ms
Time taken for size SZ_1G: 110 ms
Starting dynamic subtest: WB
Dynamic subtest WB: SUCCESS (0.000s)
Time taken for size SZ_4K: 4 ms
Time taken for size SZ_2M: 5 ms
Time taken for size SZ_64M: 16 ms
Time taken for size SZ_128M: 29 ms
Time taken for size SZ_256M: 49 ms
Time taken for size SZ_1G: 176 ms
Btw I realized --dyn doesn't work, the test executes
WC always even with --dyn :/ any ideas ?
See also one nit below.diff --git a/tests/intel/xe_exec_store.c b/tests/intel/xe_exec_store.c index c872c22d5..4b1c619e0 100644 --- a/tests/intel/xe_exec_store.c +++ b/tests/intel/xe_exec_store.c @@ -93,15 +93,10 @@ static void persistance_batch(struct data *data, uint64_t addr) data->addr = batch_addr; } -/** - * SUBTEST: basic-store - * Description: Basic test to verify store dword. - * SUBTEST: basic-cond-batch - * Description: Basic test to verify cond batch end instruction. - * SUBTEST: basic-all - * Description: Test to verify store dword on all available engines. - */ -static void basic_inst(int fd, int inst_type, struct drm_xe_engine_class_instance *eci) + +static void basic_inst_size(int fd, int inst_type, + struct drm_xe_engine_class_instance *eci, + uint16_t cpu_caching, size_t bo_size) { struct drm_xe_sync sync[2] = { { .type = DRM_XE_SYNC_TYPE_SYNCOBJ, .flags = DRM_XE_SYNC_FLAG_SIGNAL, }, @@ -117,7 +112,6 @@ static void basic_inst(int fd, int inst_type, struct drm_xe_engine_class_instanc uint32_t exec_queue; uint32_t bind_engine; uint32_t syncobj; - size_t bo_size; int value = 0x123456; uint64_t addr = 0x100000; uint32_t bo = 0; @@ -127,12 +121,16 @@ static void basic_inst(int fd, int inst_type, struct drm_xe_engine_class_instanc sync[1].handle = syncobj; vm = xe_vm_create(fd, 0, 0); - bo_size = sizeof(*data); - bo_size = xe_bb_size(fd, bo_size); - bo = xe_bo_create(fd, vm, bo_size, - vram_if_possible(fd, eci->gt_id), - DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM); + if (cpu_caching) + bo = xe_bo_create_caching(fd, vm, bo_size, + vram_if_possible(fd, eci->gt_id), + DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM, + cpu_caching); + else + bo = xe_bo_create(fd, vm, bo_size, + vram_if_possible(fd, eci->gt_id), + DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM); exec_queue = xe_exec_queue_create(fd, vm, eci, 0); bind_engine = xe_bind_exec_queue_create(fd, vm, 0); @@ -167,6 +165,66 @@ static void basic_inst(int fd, int inst_type, struct drm_xe_engine_class_instanc xe_vm_destroy(fd, vm); } +Remove extra line.
Will remove it.
Thanks!
Nirmoy
Regards, Kamil+/** + * SUBTEST: basic-store + * Description: Basic test to verify store dword. + * SUBTEST: basic-cond-batch + * Description: Basic test to verify cond batch end instruction. + * SUBTEST: basic-all + * Description: Test to verify store dword on all available engines. + */ +static void basic_inst(int fd, int inst_type, + struct drm_xe_engine_class_instance *eci, + uint16_t cpu_caching) +{ + size_t bo_size; + + bo_size = sizeof(struct data); + bo_size = xe_bb_size(fd, bo_size); + + basic_inst_size(fd, inst_type, eci, cpu_caching, bo_size); +} + +/** + * SUBTEST: basic-store-benchmark + * Description: Basic test to verify time taken for doing store dword with various size. + */ +static void basic_inst_benchmark(int fd, int inst_type, + struct drm_xe_engine_class_instance *eci, + uint16_t cpu_caching) +{ + struct { + size_t size; + const char *name; + } sizes[] = { + {SZ_4K, "SZ_4K"}, + {SZ_2M, "SZ_2M"}, + {SZ_64M, "SZ_64M"}, + {SZ_128M, "SZ_128M"}, + {SZ_256M, "SZ_256M"}, + {SZ_1G, "SZ_1G"} + }; + + struct timeval start, end; + long seconds, useconds, mtime; + + for (size_t i = 0; i < ARRAY_SIZE(sizes); ++i) { + size_t bo_size = sizes[i].size; + const char *size_name = sizes[i].name; + + gettimeofday(&start, NULL); + basic_inst_size(fd, inst_type, eci, cpu_caching, bo_size); + gettimeofday(&end, NULL); + + seconds = end.tv_sec - start.tv_sec; + useconds = end.tv_usec - start.tv_usec; + mtime = ((seconds) * 1000 + useconds / 1000.0) + 0.5; + + igt_info("Time taken for size %s: %ld ms\n", size_name, mtime); + } +} + #define PAGES 1 #define NCACHELINES (4096/64) /** @@ -342,12 +400,28 @@ igt_main igt_subtest("basic-store") { engine = xe_engine(fd, 1); - basic_inst(fd, STORE, &engine->instance); + basic_inst(fd, COND_BATCH, &engine->instance, 0); + } + + igt_subtest_with_dynamic("basic-store-benchmark") { + struct dyn { + const char *name; + int cache; + } tests[] = { + {"WC", DRM_XE_GEM_CPU_CACHING_WC}, + {"WB", DRM_XE_GEM_CPU_CACHING_WB} + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) { + igt_dynamic_f("%s", tests[i].name); + engine = xe_engine(fd, 1); + basic_inst_benchmark(fd, STORE, &engine->instance, tests[i].cache); + } } igt_subtest("basic-cond-batch") { engine = xe_engine(fd, 1); - basic_inst(fd, COND_BATCH, &engine->instance); + basic_inst(fd, COND_BATCH, &engine->instance, 0); } igt_subtest_with_dynamic("basic-all") { @@ -356,7 +430,7 @@ igt_main xe_engine_class_string(hwe->engine_class), hwe->engine_instance, hwe->gt_id); - basic_inst(fd, STORE, hwe); + basic_inst(fd, STORE, hwe, 0); } } -- 2.42.0