gem_wsim: Command line switch for specifying low slice count workloads

A new command line switch ('-s') is added which toggles the low slice
count mode for workloads following on the command line.

This enables easy benchmarking of the effect of running the existing media
workloads in parallel against another client. For example:

  ./gem_wsim -n ... -v -r 600 -W master.wsim -s -w media_nn480.wsim

Adding or removing the '-s' switch before the second workload enables
analyzing the cost of dynamic SSEU switching impacted to the first
(master) workload.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

1 files changed, 40 insertions, 4 deletions

diff --git a/benchmarks/gem_wsim.c b/benchmarks/gem_wsim.c
index 47a1ddaf..8dd887a5 100644
--- a/benchmarks/gem_wsim.c
+++ b/benchmarks/gem_wsim.c
@@ -100,6 +100,7 @@ struct w_arg {
 	char *filename;
 	char *desc;
 	int prio;
+	bool sseu;
 };
 
 struct bond {
@@ -179,6 +180,7 @@ struct workload
 	unsigned int nr_steps;
 	struct w_step *steps;
 	int prio;
+	bool sseu;
 
 	pthread_t thread;
 	bool run;
@@ -251,6 +253,7 @@ static int fd;
 #define GLOBAL_BALANCE	(1<<8)
 #define DEPSYNC		(1<<9)
 #define I915		(1<<10)
+#define SSEU		(1<<11)
 
 #define SEQNO_IDX(engine) ((engine) * 16)
 #define SEQNO_OFFSET(engine) (SEQNO_IDX(engine) * sizeof(uint32_t))
@@ -726,6 +729,7 @@ add_step:
 	wrk->nr_steps = nr_steps;
 	wrk->steps = steps;
 	wrk->prio = arg->prio;
+	wrk->sseu = arg->sseu;
 
 	free(desc);
 
@@ -771,6 +775,7 @@ clone_workload(struct workload *_wrk)
 	memset(wrk, 0, sizeof(*wrk));
 
 	wrk->prio = _wrk->prio;
+	wrk->sseu = _wrk->sseu;
 	wrk->nr_steps = _wrk->nr_steps;
 	wrk->steps = calloc(wrk->nr_steps, sizeof(struct w_step));
 	igt_assert(wrk->steps);
@@ -1136,6 +1141,26 @@ find_engine(struct i915_engine_class_instance *ci, unsigned int count,
 	return 0;
 }
 
+static void
+set_ctx_sseu(uint32_t ctx)
+{
+	struct drm_i915_gem_context_param_sseu sseu = { };
+	struct drm_i915_gem_context_param param = { };
+
+	sseu.class = I915_ENGINE_CLASS_RENDER;
+	sseu.instance = 0;
+
+	param.ctx_id = ctx;
+	param.param = I915_CONTEXT_PARAM_SSEU;
+	param.value = (uintptr_t)&sseu;
+
+	gem_context_get_param(fd, &param);
+
+	sseu.slice_mask = 1;
+
+	gem_context_set_param(fd, &param);
+}
+
 static int
 prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 {
@@ -1487,6 +1512,9 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 			gem_context_set_param(fd, &param);
 		}
 
+		if (wrk->sseu)
+			set_ctx_sseu(arg.ctx_id);
+
 		if (share_vm)
 			vm_destroy(fd, share_vm);
 	}
@@ -2661,6 +2689,8 @@ static void print_help(void)
 "  -R              Round-robin initial VCS assignment per client.\n"
 "  -H              Send heartbeat on synchronisation points with seqno based\n"
 "                  balancers. Gives better engine busyness view in some cases.\n"
+"  -s              Turn on small SSEU config for the next workload on the\n"
+"                  command line. Subsequent -s switches it off.\n"
 "  -S              Synchronize the sequence of random batch durations between\n"
 "                  clients.\n"
 "  -G              Global load balancing - a single load balancer will be shared\n"
@@ -2703,11 +2733,12 @@ static char *load_workload_descriptor(char *filename)
 }
 
 static struct w_arg *
-add_workload_arg(struct w_arg *w_args, unsigned int nr_args, char *w_arg, int prio)
+add_workload_arg(struct w_arg *w_args, unsigned int nr_args, char *w_arg,
+		 int prio, bool sseu)
 {
 	w_args = realloc(w_args, sizeof(*w_args) * nr_args);
 	igt_assert(w_args);
-	w_args[nr_args - 1] = (struct w_arg) { w_arg, NULL, prio };
+	w_args[nr_args - 1] = (struct w_arg) { w_arg, NULL, prio, sseu };
 
 	return w_args;
 }
@@ -2800,7 +2831,8 @@ int main(int argc, char **argv)
 
 	init_clocks();
 
-	while ((c = getopt(argc, argv, "hqv2RSHxGdc:n:r:w:W:a:t:b:p:")) != -1) {
+	while ((c = getopt(argc, argv,
+			   "hqv2RsSHxGdc:n:r:w:W:a:t:b:p:")) != -1) {
 		switch (c) {
 		case 'W':
 			if (master_workload >= 0) {
@@ -2810,7 +2842,8 @@ int main(int argc, char **argv)
 			master_workload = nr_w_args;
 			/* Fall through */
 		case 'w':
-			w_args = add_workload_arg(w_args, ++nr_w_args, optarg, prio);
+			w_args = add_workload_arg(w_args, ++nr_w_args, optarg,
+						  prio, flags & SSEU);
 			break;
 		case 'p':
 			prio = atoi(optarg);
@@ -2852,6 +2885,9 @@ int main(int argc, char **argv)
 		case 'S':
 			flags |= SYNCEDCLIENTS;
 			break;
+		case 's':
+			flags ^= SSEU;
+			break;
 		case 'H':
 			flags |= HEARTBEAT;
 			break;