|
218 | 218 | ######################################################################
|
219 | 219 | # The resulting table output (omitting some columns):
|
220 | 220 | #
|
221 |
| -# =========================================================== ============ ============ ============ ============ ============ |
222 |
| -# Name Self XPU Self XPU % XPU total XPU time avg # of Calls |
223 |
| -# =========================================================== ============ ============ ============ ============ ============ |
224 |
| -# model_inference 0.000us 0.00% 2.567ms 2.567ms 1 |
225 |
| -# aten::conv2d 0.000us 0.00% 1.871ms 93.560us 20 |
226 |
| -# aten::convolution 0.000us 0.00% 1.871ms 93.560us 20 |
227 |
| -# aten::_convolution 0.000us 0.00% 1.871ms 93.560us 20 |
228 |
| -# aten::convolution_overrideable 1.871ms 72.89% 1.871ms 93.560us 20 |
229 |
| -# gen_conv 1.484ms 57.82% 1.484ms 74.216us 20 |
230 |
| -# aten::batch_norm 0.000us 0.00% 432.640us 21.632us 20 |
231 |
| -# aten::_batch_norm_impl_index 0.000us 0.00% 432.640us 21.632us 20 |
232 |
| -# aten::native_batch_norm 432.640us 16.85% 432.640us 21.632us 20 |
233 |
| -# conv_reorder 386.880us 15.07% 386.880us 6.448us 60 |
234 |
| -# ----------------------------------------------------------- ------------------------------------------------------ ------------ |
| 221 | + |
| 222 | +###################################################################### |
| 223 | +# --------------------------------- ------------ ------------ ------------ ------------ ------------ |
| 224 | +# Name Self XPU Self XPU % XPU total XPU time avg # of Calls |
| 225 | +# --------------------------------- ------------ ------------ ------------ ------------ ------------ |
| 226 | +# model_inference 0.000us 0.00% 2.567ms 2.567ms 1 |
| 227 | +# aten::conv2d 0.000us 0.00% 1.871ms 93.560us 20 |
| 228 | +# aten::convolution 0.000us 0.00% 1.871ms 93.560us 20 |
| 229 | +# aten::_convolution 0.000us 0.00% 1.871ms 93.560us 20 |
| 230 | +# aten::convolution_overrideable 1.871ms 72.89% 1.871ms 93.560us 20 |
| 231 | +# gen_conv 1.484ms 57.82% 1.484ms 74.216us 20 |
| 232 | +# aten::batch_norm 0.000us 0.00% 432.640us 21.632us 20 |
| 233 | +# aten::_batch_norm_impl_index 0.000us 0.00% 432.640us 21.632us 20 |
| 234 | +# aten::native_batch_norm 432.640us 16.85% 432.640us 21.632us 20 |
| 235 | +# conv_reorder 386.880us 15.07% 386.880us 6.448us 60 |
| 236 | +# --------------------------------- ------------ ------------ ------------ ------------ ------------ |
235 | 237 | # Self CPU time total: 712.486ms
|
236 | 238 | # Self XPU time total: 2.567ms
|
237 |
| -# =========================================================== ============ ============ ============ ============ ============ |
238 |
| -# |
239 |
| - |
240 | 239 |
|
241 | 240 | ######################################################################
|
242 | 241 | # Note the occurrence of on-device kernels in the output (e.g. ``sgemm_32x32x32_NN``).
|
|
0 commit comments