2 * Copyright 2009 Jerome Glisse.
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
17 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
18 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
19 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
20 * OTHER DEALINGS IN THE SOFTWARE.
22 * Authors: Jerome Glisse
25 #include <drm/amdgpu_drm.h>
28 #define AMDGPU_BENCHMARK_ITERATIONS 1024
29 #define AMDGPU_BENCHMARK_COMMON_MODES_N 17
31 static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
32 uint64_t saddr, uint64_t daddr, int n)
34 unsigned long start_jiffies;
35 unsigned long end_jiffies;
36 struct dma_fence *fence;
39 start_jiffies = jiffies;
40 for (i = 0; i < n; i++) {
41 struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
42 r = amdgpu_copy_buffer(ring, saddr, daddr, size, NULL, &fence,
46 r = dma_fence_wait(fence, false);
51 end_jiffies = jiffies;
52 r = jiffies_to_msecs(end_jiffies - start_jiffies);
59 static void amdgpu_benchmark_log_results(int n, unsigned size,
61 unsigned sdomain, unsigned ddomain,
64 unsigned int throughput = (n * (size >> 10)) / time;
65 DRM_INFO("amdgpu: %s %u bo moves of %u kB from"
66 " %d to %d in %u ms, throughput: %u Mb/s or %u MB/s\n",
67 kind, n, size >> 10, sdomain, ddomain, time,
68 throughput * 8, throughput);
71 static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
72 unsigned sdomain, unsigned ddomain)
74 struct amdgpu_bo *dobj = NULL;
75 struct amdgpu_bo *sobj = NULL;
76 struct amdgpu_bo_param bp;
77 uint64_t saddr, daddr;
81 memset(&bp, 0, sizeof(bp));
83 bp.byte_align = PAGE_SIZE;
86 bp.type = ttm_bo_type_kernel;
88 bp.bo_ptr_size = sizeof(struct amdgpu_bo);
90 n = AMDGPU_BENCHMARK_ITERATIONS;
91 r = amdgpu_bo_create(adev, &bp, &sobj);
95 r = amdgpu_bo_reserve(sobj, false);
98 r = amdgpu_bo_pin(sobj, sdomain);
100 amdgpu_bo_unreserve(sobj);
103 r = amdgpu_ttm_alloc_gart(&sobj->tbo);
104 amdgpu_bo_unreserve(sobj);
108 saddr = amdgpu_bo_gpu_offset(sobj);
110 r = amdgpu_bo_create(adev, &bp, &dobj);
114 r = amdgpu_bo_reserve(dobj, false);
115 if (unlikely(r != 0))
117 r = amdgpu_bo_pin(dobj, ddomain);
119 amdgpu_bo_unreserve(sobj);
122 r = amdgpu_ttm_alloc_gart(&dobj->tbo);
123 amdgpu_bo_unreserve(dobj);
127 daddr = amdgpu_bo_gpu_offset(dobj);
129 if (adev->mman.buffer_funcs) {
130 time = amdgpu_benchmark_do_move(adev, size, saddr, daddr, n);
134 amdgpu_benchmark_log_results(n, size, time,
135 sdomain, ddomain, "dma");
139 /* Check error value now. The value can be overwritten when clean up.*/
141 DRM_ERROR("Error while benchmarking BO move.\n");
145 r = amdgpu_bo_reserve(sobj, true);
146 if (likely(r == 0)) {
147 amdgpu_bo_unpin(sobj);
148 amdgpu_bo_unreserve(sobj);
150 amdgpu_bo_unref(&sobj);
153 r = amdgpu_bo_reserve(dobj, true);
154 if (likely(r == 0)) {
155 amdgpu_bo_unpin(dobj);
156 amdgpu_bo_unreserve(dobj);
158 amdgpu_bo_unref(&dobj);
162 void amdgpu_benchmark(struct amdgpu_device *adev, int test_number)
165 static const int common_modes[AMDGPU_BENCHMARK_COMMON_MODES_N] = {
185 switch (test_number) {
187 /* simple test, VRAM to GTT and GTT to VRAM */
188 amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_GTT,
189 AMDGPU_GEM_DOMAIN_VRAM);
190 amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_VRAM,
191 AMDGPU_GEM_DOMAIN_GTT);
194 /* simple test, VRAM to VRAM */
195 amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_VRAM,
196 AMDGPU_GEM_DOMAIN_VRAM);
199 /* GTT to VRAM, buffer size sweep, powers of 2 */
200 for (i = 1; i <= 16384; i <<= 1)
201 amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
202 AMDGPU_GEM_DOMAIN_GTT,
203 AMDGPU_GEM_DOMAIN_VRAM);
206 /* VRAM to GTT, buffer size sweep, powers of 2 */
207 for (i = 1; i <= 16384; i <<= 1)
208 amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
209 AMDGPU_GEM_DOMAIN_VRAM,
210 AMDGPU_GEM_DOMAIN_GTT);
213 /* VRAM to VRAM, buffer size sweep, powers of 2 */
214 for (i = 1; i <= 16384; i <<= 1)
215 amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
216 AMDGPU_GEM_DOMAIN_VRAM,
217 AMDGPU_GEM_DOMAIN_VRAM);
220 /* GTT to VRAM, buffer size sweep, common modes */
221 for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++)
222 amdgpu_benchmark_move(adev, common_modes[i],
223 AMDGPU_GEM_DOMAIN_GTT,
224 AMDGPU_GEM_DOMAIN_VRAM);
227 /* VRAM to GTT, buffer size sweep, common modes */
228 for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++)
229 amdgpu_benchmark_move(adev, common_modes[i],
230 AMDGPU_GEM_DOMAIN_VRAM,
231 AMDGPU_GEM_DOMAIN_GTT);
234 /* VRAM to VRAM, buffer size sweep, common modes */
235 for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++)
236 amdgpu_benchmark_move(adev, common_modes[i],
237 AMDGPU_GEM_DOMAIN_VRAM,
238 AMDGPU_GEM_DOMAIN_VRAM);
242 DRM_ERROR("Unknown benchmark\n");