Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Nirmoy Das <nirmoy.das@intel.com>
To: Kamil Konieczny <kamil.konieczny@linux.intel.com>,
	<igt-dev@lists.freedesktop.org>
Subject: Re: [PATCH i-g-t v2] tests/intel/xe_exec_store: Add basic_inst_benchmark
Date: Thu, 20 Jun 2024 16:44:44 +0200	[thread overview]
Message-ID: <1da8d3f3-38d6-484b-857a-61a13a5bf56a@intel.com> (raw)
In-Reply-To: <20240620142007.ywhmpjokrnnpbhnv@kamilkon-DESK.igk.intel.com>

[-- Attachment #1: Type: text/plain, Size: 8241 bytes --]

Hi Kamil,

On 6/20/2024 4:20 PM, Kamil Konieczny wrote:
> 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.


>
> Also, where are benchmarks? Do you print them only after
> WC and WB runs?
It should something like:

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
>>

[-- Attachment #2: Type: text/html, Size: 11579 bytes --]

      reply	other threads:[~2024-06-20 14:44 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-18 17:32 [PATCH i-g-t v2] tests/intel/xe_exec_store: Add basic_inst_benchmark Nirmoy Das
2024-06-18 19:10 ` ✓ CI.xeBAT: success for tests/intel/xe_exec_store: Add basic_inst_benchmark (rev2) Patchwork
2024-06-18 19:20 ` ✗ Fi.CI.BAT: failure " Patchwork
2024-06-19  9:04 ` ✗ CI.xeFULL: " Patchwork
2024-06-20 14:20 ` [PATCH i-g-t v2] tests/intel/xe_exec_store: Add basic_inst_benchmark Kamil Konieczny
2024-06-20 14:44   ` Nirmoy Das [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1da8d3f3-38d6-484b-857a-61a13a5bf56a@intel.com \
    --to=nirmoy.das@intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=kamil.konieczny@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox