aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/radeon_benchmark.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/radeon/radeon_benchmark.c')
-rw-r--r--drivers/gpu/drm/radeon/radeon_benchmark.c245
1 files changed, 171 insertions, 74 deletions
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 10191d9..441de38 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -26,21 +26,81 @@
#include "radeon_reg.h"
#include "radeon.h"
-void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
- unsigned sdomain, unsigned ddomain)
+#define RADEON_BENCHMARK_COPY_BLIT 1
+#define RADEON_BENCHMARK_COPY_DMA 0
+
+#define RADEON_BENCHMARK_ITERATIONS 1024
+#define RADEON_BENCHMARK_COMMON_MODES_N 17
+
+static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
+ uint64_t saddr, uint64_t daddr,
+ int flag, int n)
+{
+ unsigned long start_jiffies;
+ unsigned long end_jiffies;
+ struct radeon_fence *fence = NULL;
+ int i, r;
+
+ start_jiffies = jiffies;
+ for (i = 0; i < n; i++) {
+ r = radeon_fence_create(rdev, &fence);
+ if (r)
+ return r;
+
+ switch (flag) {
+ case RADEON_BENCHMARK_COPY_DMA:
+ r = radeon_copy_dma(rdev, saddr, daddr,
+ size / RADEON_GPU_PAGE_SIZE,
+ fence);
+ break;
+ case RADEON_BENCHMARK_COPY_BLIT:
+ r = radeon_copy_blit(rdev, saddr, daddr,
+ size / RADEON_GPU_PAGE_SIZE,
+ fence);
+ break;
+ default:
+ DRM_ERROR("Unknown copy method\n");
+ r = -EINVAL;
+ }
+ if (r)
+ goto exit_do_move;
+ r = radeon_fence_wait(fence, false);
+ if (r)
+ goto exit_do_move;
+ radeon_fence_unref(&fence);
+ }
+ end_jiffies = jiffies;
+ r = jiffies_to_msecs(end_jiffies - start_jiffies);
+
+exit_do_move:
+ if (fence)
+ radeon_fence_unref(&fence);
+ return r;
+}
+
+
+static void radeon_benchmark_log_results(int n, unsigned size,
+ unsigned int time,
+ unsigned sdomain, unsigned ddomain,
+ char *kind)
+{
+ unsigned int throughput = (n * (size >> 10)) / time;
+ DRM_INFO("radeon: %s %u bo moves of %u kB from"
+ " %d to %d in %u ms, throughput: %u Mb/s or %u MB/s\n",
+ kind, n, size >> 10, sdomain, ddomain, time,
+ throughput * 8, throughput);
+}
+
+static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
+ unsigned sdomain, unsigned ddomain)
{
struct radeon_bo *dobj = NULL;
struct radeon_bo *sobj = NULL;
- struct radeon_fence *fence = NULL;
uint64_t saddr, daddr;
- unsigned long start_jiffies;
- unsigned long end_jiffies;
- unsigned long time;
- unsigned i, n, size;
- int r;
+ int r, n;
+ int time;
- size = bsize;
- n = 1024;
+ n = RADEON_BENCHMARK_ITERATIONS;
r = radeon_bo_create(rdev, size, PAGE_SIZE, true, sdomain, &sobj);
if (r) {
goto out_cleanup;
@@ -67,65 +127,28 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
}
/* r100 doesn't have dma engine so skip the test */
- if (rdev->asic->copy_dma) {
-
- start_jiffies = jiffies;
- for (i = 0; i < n; i++) {
- r = radeon_fence_create(rdev, &fence);
- if (r) {
- goto out_cleanup;
- }
-
- r = radeon_copy_dma(rdev, saddr, daddr,
- size / RADEON_GPU_PAGE_SIZE, fence);
-
- if (r) {
- goto out_cleanup;
- }
- r = radeon_fence_wait(fence, false);
- if (r) {
- goto out_cleanup;
- }
- radeon_fence_unref(&fence);
- }
- end_jiffies = jiffies;
- time = end_jiffies - start_jiffies;
- time = jiffies_to_msecs(time);
- if (time > 0) {
- i = ((n * size) >> 10) / time;
- printk(KERN_INFO "radeon: dma %u bo moves of %ukb from"
- " %d to %d in %lums (%ukb/ms %ukb/s %uM/s)\n",
- n, size >> 10,
- sdomain, ddomain, time,
- i, i * 1000, (i * 1000) / 1024);
- }
+ /* also, VRAM-to-VRAM test doesn't make much sense for DMA */
+ /* skip it as well if domains are the same */
+ if ((rdev->asic->copy_dma) && (sdomain != ddomain)) {
+ time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
+ RADEON_BENCHMARK_COPY_DMA, n);
+ if (time < 0)
+ goto out_cleanup;
+ if (time > 0)
+ radeon_benchmark_log_results(n, size, time,
+ sdomain, ddomain, "dma");
}
- start_jiffies = jiffies;
- for (i = 0; i < n; i++) {
- r = radeon_fence_create(rdev, &fence);
- if (r) {
- goto out_cleanup;
- }
- r = radeon_copy_blit(rdev, saddr, daddr, size / RADEON_GPU_PAGE_SIZE, fence);
- if (r) {
- goto out_cleanup;
- }
- r = radeon_fence_wait(fence, false);
- if (r) {
+ if (rdev->asic->copy_blit) {
+ time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
+ RADEON_BENCHMARK_COPY_BLIT, n);
+ if (time < 0)
goto out_cleanup;
- }
- radeon_fence_unref(&fence);
- }
- end_jiffies = jiffies;
- time = end_jiffies - start_jiffies;
- time = jiffies_to_msecs(time);
- if (time > 0) {
- i = ((n * size) >> 10) / time;
- printk(KERN_INFO "radeon: blit %u bo moves of %ukb from %d to %d"
- " in %lums (%ukb/ms %ukb/s %uM/s)\n", n, size >> 10,
- sdomain, ddomain, time, i, i * 1000, (i * 1000) / 1024);
+ if (time > 0)
+ radeon_benchmark_log_results(n, size, time,
+ sdomain, ddomain, "blit");
}
+
out_cleanup:
if (sobj) {
r = radeon_bo_reserve(sobj, false);
@@ -143,18 +166,92 @@ out_cleanup:
}
radeon_bo_unref(&dobj);
}
- if (fence) {
- radeon_fence_unref(&fence);
- }
+
if (r) {
- printk(KERN_WARNING "Error while benchmarking BO move.\n");
+ DRM_ERROR("Error while benchmarking BO move.\n");
}
}
-void radeon_benchmark(struct radeon_device *rdev)
+void radeon_benchmark(struct radeon_device *rdev, int test_number)
{
- radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_GTT,
- RADEON_GEM_DOMAIN_VRAM);
- radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_VRAM,
- RADEON_GEM_DOMAIN_GTT);
+ int i;
+ int common_modes[RADEON_BENCHMARK_COMMON_MODES_N] = {
+ 640 * 480 * 4,
+ 720 * 480 * 4,
+ 800 * 600 * 4,
+ 848 * 480 * 4,
+ 1024 * 768 * 4,
+ 1152 * 768 * 4,
+ 1280 * 720 * 4,
+ 1280 * 800 * 4,
+ 1280 * 854 * 4,
+ 1280 * 960 * 4,
+ 1280 * 1024 * 4,
+ 1440 * 900 * 4,
+ 1400 * 1050 * 4,
+ 1680 * 1050 * 4,
+ 1600 * 1200 * 4,
+ 1920 * 1080 * 4,
+ 1920 * 1200 * 4
+ };
+
+ switch (test_number) {
+ case 1:
+ /* simple test, VRAM to GTT and GTT to VRAM */
+ radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_GTT,
+ RADEON_GEM_DOMAIN_VRAM);
+ radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_VRAM,
+ RADEON_GEM_DOMAIN_GTT);
+ break;
+ case 2:
+ /* simple test, VRAM to VRAM */
+ radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_VRAM,
+ RADEON_GEM_DOMAIN_VRAM);
+ break;
+ case 3:
+ /* GTT to VRAM, buffer size sweep, powers of 2 */
+ for (i = 1; i <= 65536; i <<= 1)
+ radeon_benchmark_move(rdev, i*1024,
+ RADEON_GEM_DOMAIN_GTT,
+ RADEON_GEM_DOMAIN_VRAM);
+ break;
+ case 4:
+ /* VRAM to GTT, buffer size sweep, powers of 2 */
+ for (i = 1; i <= 65536; i <<= 1)
+ radeon_benchmark_move(rdev, i*1024,
+ RADEON_GEM_DOMAIN_VRAM,
+ RADEON_GEM_DOMAIN_GTT);
+ break;
+ case 5:
+ /* VRAM to VRAM, buffer size sweep, powers of 2 */
+ for (i = 1; i <= 65536; i <<= 1)
+ radeon_benchmark_move(rdev, i*1024,
+ RADEON_GEM_DOMAIN_VRAM,
+ RADEON_GEM_DOMAIN_VRAM);
+ break;
+ case 6:
+ /* GTT to VRAM, buffer size sweep, common modes */
+ for (i = 1; i < RADEON_BENCHMARK_COMMON_MODES_N; i++)
+ radeon_benchmark_move(rdev, common_modes[i],
+ RADEON_GEM_DOMAIN_GTT,
+ RADEON_GEM_DOMAIN_VRAM);
+ break;
+ case 7:
+ /* VRAM to GTT, buffer size sweep, common modes */
+ for (i = 1; i < RADEON_BENCHMARK_COMMON_MODES_N; i++)
+ radeon_benchmark_move(rdev, common_modes[i],
+ RADEON_GEM_DOMAIN_VRAM,
+ RADEON_GEM_DOMAIN_GTT);
+ break;
+ case 8:
+ /* VRAM to VRAM, buffer size sweep, common modes */
+ for (i = 1; i < RADEON_BENCHMARK_COMMON_MODES_N; i++)
+ radeon_benchmark_move(rdev, common_modes[i],
+ RADEON_GEM_DOMAIN_VRAM,
+ RADEON_GEM_DOMAIN_VRAM);
+ break;
+
+ default:
+ DRM_ERROR("Unknown benchmark\n");
+ }
}
generated by cgit v1.1 at 2024-04-19 04:48:37 +0000