From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>,
igt-dev@lists.freedesktop.org
Subject: Re: [PATCH i-g-t 2/2] benchmarks/gem_wsim: Option to list physical engines
Date: Wed, 24 Jan 2024 12:25:55 +0000 [thread overview]
Message-ID: <5925d203-328e-44f0-9371-4de6c837ddf9@linux.intel.com> (raw)
In-Reply-To: <20240115154448.29263-3-marcin.bernatowicz@linux.intel.com>
On 15/01/2024 15:44, Marcin Bernatowicz wrote:
> Added command line option (-l) to list physical engines.
What is the use case and could you paste the example output please (both
drivers if possible)?
Regards,
Tvrtko
> Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
> ---
> benchmarks/gem_wsim.c | 43 ++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 42 insertions(+), 1 deletion(-)
>
> diff --git a/benchmarks/gem_wsim.c b/benchmarks/gem_wsim.c
> index e79d26513..aa70b1770 100644
> --- a/benchmarks/gem_wsim.c
> +++ b/benchmarks/gem_wsim.c
> @@ -2924,6 +2924,7 @@ static void print_help(void)
> " -f <scale> Scale factor for batch durations.\n"
> " -F <scale> Scale factor for delays.\n"
> " -L List GPUs.\n"
> +" -l List physical engines.\n"
> " -D <gpu> One of the GPUs from -L.\n"
> );
> }
> @@ -2983,10 +2984,42 @@ add_workload_arg(struct w_arg *w_args, unsigned int nr_args, char *w_arg,
> return w_args;
> }
>
> +static void list_engines(void)
> +{
> + struct intel_engines *engines = query_engines();
> + int engine_class_count[NUM_ENGINE_CLASSES] = {};
> + unsigned int i;
> +
> + for (i = 0; i < engines->nr_engines; ++i) {
> + igt_assert_lt(engines->engines[i].engine_class, NUM_ENGINE_CLASSES);
> + engine_class_count[engines->engines[i].engine_class]++;
> + }
> +
> + for (i = 0; i < engines->nr_engines; ++i) {
> + if (engine_class_count[engines->engines[i].engine_class] > 1)
> + printf("%s%u",
> + intel_engine_class_string(engines->engines[i].engine_class),
> + engines->engines[i].engine_instance + 1);
> + else
> + printf("%s",
> + intel_engine_class_string(engines->engines[i].engine_class));
> +
> + if (is_xe && engines->engines[i].gt_id)
> + printf("-%u", engines->engines[i].gt_id);
> +
> + if (verbose > 3)
> + printf(" [%d:%d:%d]", engines->engines[i].engine_class,
> + engines->engines[i].engine_instance,
> + engines->engines[i].gt_id);
> + printf("\n");
> + }
> +}
> +
> int main(int argc, char **argv)
> {
> struct igt_device_card card = { };
> bool list_devices_arg = false;
> + bool list_engines_arg = false;
> unsigned int repeat = 1;
> unsigned int clients = 1;
> unsigned int flags = 0;
> @@ -3009,11 +3042,14 @@ int main(int argc, char **argv)
> master_prng = time(NULL);
>
> while ((c = getopt(argc, argv,
> - "LhqvsSdc:r:w:W:a:p:I:f:F:D:")) != -1) {
> + "LlhqvsSdc:r:w:W:a:p:I:f:F:D:")) != -1) {
> switch (c) {
> case 'L':
> list_devices_arg = true;
> break;
> + case 'l':
> + list_engines_arg = true;
> + break;
> case 'D':
> device_arg = strdup(optarg);
> break;
> @@ -3134,6 +3170,11 @@ int main(int argc, char **argv)
> if (is_xe)
> xe_device_get(fd);
>
> + if (list_engines_arg) {
> + list_engines();
> + goto out;
> + }
> +
> if (!nr_w_args) {
> wsim_err("No workload descriptor(s)!\n");
> goto err;
next prev parent reply other threads:[~2024-01-24 12:26 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-15 15:44 [PATCH i-g-t 0/2] benchmarks/gem_wsim: Extend engine selection syntax Marcin Bernatowicz
2024-01-15 15:44 ` [PATCH i-g-t 1/2] " Marcin Bernatowicz
2024-01-24 11:41 ` Laguna, Lukasz
2024-01-24 12:24 ` Tvrtko Ursulin
2024-01-15 15:44 ` [PATCH i-g-t 2/2] benchmarks/gem_wsim: Option to list physical engines Marcin Bernatowicz
2024-01-24 11:41 ` Laguna, Lukasz
2024-01-24 12:25 ` Tvrtko Ursulin [this message]
2024-04-17 8:22 ` Bernatowicz, Marcin
2024-01-15 16:54 ` ✓ Fi.CI.BAT: success for benchmarks/gem_wsim: Extend engine selection syntax Patchwork
2024-01-15 17:06 ` ✓ CI.xeBAT: " Patchwork
2024-01-15 19:10 ` ✗ Fi.CI.IGT: failure " Patchwork
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=5925d203-328e-44f0-9371-4de6c837ddf9@linux.intel.com \
--to=tvrtko.ursulin@linux.intel.com \
--cc=igt-dev@lists.freedesktop.org \
--cc=marcin.bernatowicz@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