Navigation :

GPU Kernel Information Aggregated by Layer

Search:

layer_index	layer_name	layer_type	layer_duration (us)	layer_gpu_duration (us)	layer_cpu_duration (us)	layer_flops	layer_dram_read_bytes	layer_dram_write_bytes	layer_achieved_occupancy (%)	layer_arithmetic_intensity (flops/byte)	layer_arithmetic_throughput (GFlops)	layer_memory_bound

layer_index	layer_name	layer_type	layer_duration (us)	layer_gpu_duration (us)	layer_cpu_duration (us)	layer_memory_bound
1	vgg4_relu0_fwd	Activation	585.00	49.00	536.00	true
2	vgg4_conv1_fwd	Convolution	241222.67	301.33	240921.33	true
3	vgg4_relu1_fwd	Activation	588.33	49.00	539.33	true
4	vgg4_pool0_fwd	Pooling	6438.67	33.33	6405.33	true
5	vgg4_conv2_fwd	Convolution	100122.00	159.67	99962.33	true
6	vgg4_relu2_fwd	Activation	301.67	19.67	282.00	true
7	vgg4_conv3_fwd	Convolution	199591.33	260.00	199331.33	true
8	vgg4_relu3_fwd	Activation	291.67	20.00	271.67	true
9	vgg4_pool1_fwd	Pooling	3542.67	12.67	3530.00	true
10	vgg4_conv4_fwd	Convolution	91360.00	170.67	91189.33	true
11	vgg4_relu4_fwd	Activation	148.33	6.00	142.33	true
12	vgg4_conv5_fwd	Convolution	186162.33	307.33	185855.00	true
13	vgg4_relu5_fwd	Activation	152.33	6.00	146.33	true
14	vgg4_conv6_fwd	Convolution	183749.00	306.00	183443.00	true
15	vgg4_relu6_fwd	Activation	152.33	6.00	146.33	true
16	vgg4_pool2_fwd	Pooling	1802.67	6.33	1796.33	true
17	vgg4_conv7_fwd	Convolution	87487.00	177.67	87309.33	true
18	vgg4_relu7_fwd	Activation	79.33	4.00	75.33	true
19	vgg4_conv8_fwd	Convolution	177488.33	332.33	177156.00	true
20	vgg4_relu8_fwd	Activation	81.33	4.33	77.00	true
21	vgg4_conv9_fwd	Convolution	178904.67	332.00	178572.67	true
22	vgg4_relu9_fwd	Activation	80.00	4.00	76.00	true
23	vgg4_pool3_fwd	Pooling	890.33	4.00	886.33	true
24	vgg4_conv10_fwd	Convolution	46756.67	178.33	46578.33	true
25	vgg4_relu10_fwd	Activation	25.00	2.33	22.67	true
26	vgg4_conv11_fwd	Convolution	46984.67	175.00	46809.67	true
27	vgg4_relu11_fwd	Activation	27.00	3.00	24.00	true
28	vgg4_conv12_fwd	Convolution	46893.33	175.00	46718.33	true
29	vgg4_relu12_fwd	Activation	23.00	2.67	20.33	true
30	vgg4_pool4_fwd	Pooling	286.67	4.00	282.67	true
31	vgg4_dense0_fwd	FullyConnected	147936.67	705.67	147231.00	true
32	vgg4_dense0_relu_fwd	Activation	14.67	2.00	12.67	true
33	vgg4_dropout0_fwd	Dropout	7.67	2.00	5.67	true
34	vgg4_dense1_fwd	FullyConnected	25785.33	120.67	25664.67	true
35	vgg4_dense1_relu_fwd	Activation	11.00	2.67	8.33	true
36	vgg4_dropout1_fwd	Dropout	7.00	2.00	5.00	true
37	vgg4_dense2_fwd	FullyConnected	6593.33	34.67	6558.67	true

Showing 1 to 37 of 37 entries

Download as CSV