[PATCH v2 1/5] tests/exynos: add fimg2d performance analysis

* [PATCH v2 1/5] tests/exynos: add fimg2d performance analysis
@ 2015-03-25 16:48 Tobias Jakobi
  2015-03-25 16:48 ` [PATCH v2 5/5] tests/exynos: add fimg2d event test Tobias Jakobi
  2015-03-26 15:27 ` [PATCH v2 1/5] tests/exynos: add fimg2d performance analysis Emil Velikov
  0 siblings, 2 replies; 3+ messages in thread
From: Tobias Jakobi @ 2015-03-25 16:48 UTC (permalink / raw)
  To: linux-samsung-soc
  Cc: dri-devel, emil.l.velikov, jy0922.shim, m.szyprowski, inki.dae,
	Tobias Jakobi

Currently only fast solid color clear performance is measured.
A large buffer is allocated and solid color clear operations
are executed on it with randomly chosen properties (position
and size of the region, clear color). Execution time is
measured and output together with the amount of pixels
processed.

The 'simple' variant only executes one G2D command buffer at
a time, while the 'multi' variant executes multiple ones. This
can be used to measure setup/exec overhead.

The test also serves a stability check. If clocks/voltages are
too high or low respectively, the test quickly reveals this.

v2: Add GPLv2 header, argument handling and documentation.
    Tool is only installed when requested.

Signed-off-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
---
 tests/exynos/Makefile.am          |  19 ++-
 tests/exynos/exynos_fimg2d_perf.c | 320 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 337 insertions(+), 2 deletions(-)
 create mode 100644 tests/exynos/exynos_fimg2d_perf.c

diff --git a/tests/exynos/Makefile.am b/tests/exynos/Makefile.am
index b21d016..e82d199 100644
--- a/tests/exynos/Makefile.am
+++ b/tests/exynos/Makefile.am
@@ -5,16 +5,31 @@ AM_CFLAGS = \
 	-I $(top_srcdir)/exynos \
 	-I $(top_srcdir)
 
+bin_PROGRAMS =
+noinst_PROGRAMS =
+
 if HAVE_LIBKMS
 if HAVE_INSTALL_TESTS
-bin_PROGRAMS = \
+bin_PROGRAMS += \
 	exynos_fimg2d_test
 else
-noinst_PROGRAMS = \
+noinst_PROGRAMS += \
 	exynos_fimg2d_test
 endif
 endif
 
+if HAVE_INSTALL_TESTS
+bin_PROGRAMS += \
+	exynos_fimg2d_perf
+else
+noinst_PROGRAMS += \
+	exynos_fimg2d_perf
+endif
+
+exynos_fimg2d_perf_LDADD = \
+	$(top_builddir)/libdrm.la \
+	$(top_builddir)/exynos/libdrm_exynos.la
+
 exynos_fimg2d_test_LDADD = \
 	$(top_builddir)/libdrm.la \
 	$(top_builddir)/libkms/libkms.la \
diff --git a/tests/exynos/exynos_fimg2d_perf.c b/tests/exynos/exynos_fimg2d_perf.c
new file mode 100644
index 0000000..e52e0d8
--- /dev/null
+++ b/tests/exynos/exynos_fimg2d_perf.c
@@ -0,0 +1,320 @@
+/*
+ * Copyright (C) 2015 - Tobias Jakobi
+ *
+ * This is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation, either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * It is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ * You should have received a copy of the GNU General Public License
+ * along with it. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <time.h>
+#include <getopt.h>
+
+#include <xf86drm.h>
+
+#include "exynos_drm.h"
+#include "exynos_drmif.h"
+#include "exynos_fimg2d.h"
+
+static int output_mathematica = 0;
+
+static int fimg2d_perf_simple(struct exynos_bo *bo, struct g2d_context *ctx,
+			unsigned buf_width, unsigned buf_height, unsigned iterations)
+{
+	struct timespec tspec = { 0 };
+	struct g2d_image img = { 0 };
+
+	unsigned long long g2d_time;
+	unsigned i;
+	int ret = 0;
+
+	img.width = buf_width;
+	img.height = buf_height;
+	img.stride = buf_width * 4;
+	img.color_mode = G2D_COLOR_FMT_ARGB8888 | G2D_ORDER_AXRGB;
+	img.buf_type = G2D_IMGBUF_GEM;
+	img.bo[0] = bo->handle;
+
+	srand(time(NULL));
+
+	printf("starting simple G2D performance test\n");
+	printf("buffer width = %u, buffer height = %u, iterations = %u\n",
+		buf_width, buf_height, iterations);
+
+	if (output_mathematica)
+		putchar('{');
+
+	for (i = 0; i < iterations; ++i) {
+		unsigned x, y, w, h;
+
+		x = rand() % buf_width;
+		y = rand() % buf_height;
+
+		if (x == (buf_width - 1))
+			x -= 1;
+		if (y == (buf_height - 1))
+			y -= 1;
+
+		w = rand() % (buf_width - x);
+		h = rand() % (buf_height - y);
+
+		if (w == 0) w = 1;
+		if (h == 0) h = 1;
+
+		img.color = rand();
+
+		ret = g2d_solid_fill(ctx, &img, x, y, w, h);
+
+		clock_gettime(CLOCK_MONOTONIC, &tspec);
+
+		if (ret == 0)
+			ret = g2d_exec(ctx);
+
+		if (ret != 0) {
+			fprintf(stderr, "error: iteration %u failed (x = %u, y = %u, w = %u, h = %u)\n",
+				i, x, y, w, h);
+			break;
+		} else {
+			struct timespec end = { 0 };
+			clock_gettime(CLOCK_MONOTONIC, &end);
+
+			g2d_time = (end.tv_sec - tspec.tv_sec) * 1000000000ULL;
+			g2d_time += (end.tv_nsec - tspec.tv_nsec);
+
+			if (output_mathematica) {
+				if (i != 0) putchar(',');
+				printf("{%u,%llu}", w * h, g2d_time);
+			} else {
+				printf("num_pixels = %u, usecs = %llu\n", w * h, g2d_time);
+			}
+		}
+	}
+
+	if (output_mathematica)
+		printf("}\n");
+
+	return ret;
+}
+
+static int fimg2d_perf_multi(struct exynos_bo *bo, struct g2d_context *ctx,
+			unsigned buf_width, unsigned buf_height, unsigned iterations, unsigned batch)
+{
+	struct timespec tspec = { 0 };
+	struct g2d_image *images;
+
+	unsigned long long g2d_time;
+	unsigned i, j;
+	int ret = 0;
+
+	images = calloc(batch, sizeof(struct g2d_image));
+	for (i = 0; i < batch; ++i) {
+		images[i].width = buf_width;
+		images[i].height = buf_height;
+		images[i].stride = buf_width * 4;
+		images[i].color_mode = G2D_COLOR_FMT_ARGB8888 | G2D_ORDER_AXRGB;
+		images[i].buf_type = G2D_IMGBUF_GEM;
+		images[i].bo[0] = bo->handle;
+	}
+
+	srand(time(NULL));
+
+	printf("starting multi G2D performance test (batch size = %u)\n", batch);
+	printf("buffer width = %u, buffer height = %u, iterations = %u\n",
+		buf_width, buf_height, iterations);
+
+	if (output_mathematica)
+		putchar('{');
+
+	for (i = 0; i < iterations; ++i) {
+		unsigned num_pixels = 0;
+
+		for (j = 0; j < batch; ++j) {
+			unsigned x, y, w, h;
+
+			x = rand() % buf_width;
+			y = rand() % buf_height;
+
+			if (x == (buf_width - 1))
+				x -= 1;
+			if (y == (buf_height - 1))
+				y -= 1;
+
+			w = rand() % (buf_width - x);
+			h = rand() % (buf_height - y);
+
+			if (w == 0) w = 1;
+			if (h == 0) h = 1;
+
+			images[j].color = rand();
+
+			num_pixels += w * h;
+
+			ret = g2d_solid_fill(ctx, &images[j], x, y, w, h);
+			if (ret != 0)
+				break;
+		}
+
+		clock_gettime(CLOCK_MONOTONIC, &tspec);
+
+		if (ret == 0)
+			ret = g2d_exec(ctx);
+
+		if (ret != 0) {
+			fprintf(stderr, "error: iteration %u failed (num_pixels = %u)\n", i, num_pixels);
+			break;
+			break;
+		} else {
+			struct timespec end = { 0 };
+			clock_gettime(CLOCK_MONOTONIC, &end);
+
+			g2d_time = (end.tv_sec - tspec.tv_sec) * 1000000000ULL;
+			g2d_time += (end.tv_nsec - tspec.tv_nsec);
+
+			if (output_mathematica) {
+				if (i != 0) putchar(',');
+				printf("{%u,%llu}", num_pixels, g2d_time);
+			} else {
+				printf("num_pixels = %u, usecs = %llu\n", num_pixels, g2d_time);
+			}
+		}
+	}
+
+	if (output_mathematica)
+		printf("}\n");
+
+	return ret;
+}
+
+static void usage(const char *name)
+{
+	fprintf(stderr, "usage: %s [-ibwh]\n\n", name);
+
+	fprintf(stderr, "\t-i <number of iterations>\n");
+	fprintf(stderr, "\t-b <size of a batch> (default = 3)\n\n");
+
+	fprintf(stderr, "\t-w <buffer width> (default = 4096)\n");
+	fprintf(stderr, "\t-h <buffer height> (default = 4096)\n\n");
+
+	fprintf(stderr, "\t-M <enable Mathematica styled output>\n");
+
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	int fd, ret, c, parsefail;
+
+	struct exynos_device *dev;
+	struct g2d_context *ctx;
+	struct exynos_bo *bo;
+
+	unsigned int iters = 0, batch = 3;
+	unsigned int bufw = 4096, bufh = 4096;
+
+	ret = 0;
+	parsefail = 0;
+
+	while ((c = getopt(argc, argv, "i:b:w:h:M")) != -1) {
+		switch (c) {
+		case 'i':
+			if (sscanf(optarg, "%u", &iters) != 1)
+				parsefail = 1;
+			break;
+		case 'b':
+			if (sscanf(optarg, "%u", &batch) != 1)
+				parsefail = 1;
+			break;
+		case 'w':
+			if (sscanf(optarg, "%u", &bufw) != 1)
+				parsefail = 1;
+			break;
+		case 'h':
+			if (sscanf(optarg, "%u", &bufh) != 1)
+				parsefail = 1;
+			break;
+		case 'M':
+			output_mathematica = 1;
+			break;
+		default:
+			parsefail = 1;
+			break;
+		}
+	}
+
+	if (parsefail || (argc == 1) || (iters == 0))
+		usage(argv[0]);
+
+	if (bufw > 4096 || bufh > 4096) {
+		fprintf(stderr, "error: buffer width/height should be less than 4096.\n");
+		ret = -1;
+
+		goto out;
+	}
+
+	if (bufw == 0 || bufh == 0) {
+		fprintf(stderr, "error: buffer width/height should be non-zero.\n");
+		ret = -1;
+
+		goto out;
+	}
+
+	fd = drmOpen("exynos", NULL);
+	if (fd < 0) {
+		fprintf(stderr, "error: failed to open drm\n");
+		ret = -1;
+
+		goto out;
+	}
+
+	dev = exynos_device_create(fd);
+	if (dev == NULL) {
+		fprintf(stderr, "error: failed to create device\n");
+		ret = -2;
+
+		goto fail;
+	}
+
+	ctx = g2d_init(fd);
+	if (ctx == NULL) {
+		fprintf(stderr, "error: failed to init G2D\n");
+		ret = -3;
+
+		goto g2d_fail;
+	}
+
+	bo = exynos_bo_create(dev, bufw * bufh * 4, 0);
+	if (bo == NULL) {
+		fprintf(stderr, "error: failed to create bo\n");
+		ret = -4;
+
+		goto bo_fail;
+	}
+
+	ret = fimg2d_perf_simple(bo, ctx, bufw, bufh, iters);
+
+	if (ret == 0)
+		ret = fimg2d_perf_multi(bo, ctx, bufw, bufh, iters, batch);
+
+	exynos_bo_destroy(bo);
+
+bo_fail:
+	g2d_fini(ctx);
+
+g2d_fail:
+	exynos_device_destroy(dev);
+
+fail:
+	drmClose(fd);
+
+out:
+	return ret;
+}
-- 
2.0.5

^ permalink raw reply related	[flat|nested] 3+ messages in thread