ECE 408 sem project
This commit is contained in:
Aryan Singh committed
1 parent
1d79ccd2e3
commit
fa3efcaf07
139 files changed
+11634
-1
No files matched your search
@@ -0,0 +1,107 @@
|
||||
test-gpt2-kernels - TF32 Mode is turned OFF.
|
||||
test-gpt2 - [State]
|
||||
Batch Size: 4
|
||||
Sequence Length: 64
|
||||
GPT2 - Allocated 221 MiB for activations
|
||||
test-gpt2 - Printing 10 Expected vs Actual Logits:
|
||||
-43.431618, -43.431740
|
||||
-39.836346, -39.836452
|
||||
-43.065910, -43.066021
|
||||
-42.828045, -42.828144
|
||||
-43.529541, -43.529644
|
||||
-44.318398, -44.318497
|
||||
-41.227425, -41.227528
|
||||
-41.270760, -41.270863
|
||||
-42.541393, -42.541523
|
||||
-42.394997, -42.395119
|
||||
---------------- Logits OK! (max err 0.000043, RMSE 0.000002) ----------------
|
||||
_________________________ All tests passed! _________________________
|
||||
Collecting data...
|
||||
Generating '/tmp/nsys-report-e0c8.qdstrm'
|
||||
␍[1/8] [0% ] report4.nsys-rep␍[1/8] [0% ] report4.nsys-rep␍[1/8] [====25% ] report4.nsys-rep␍[1/8] [==========49% ] report4.nsys-rep␍[1/8] [===========50% ] report4.nsys-rep␍[1/8] [=======36% ] report4.nsys-rep␍[1/8] [===========50% ] report4.nsys-rep␍[1/8] [===========51% ] report4.nsys-rep␍[1/8] [===========52% ] report4.nsys-rep␍[1/8] [===========53% ] report4.nsys-rep␍[1/8] [============54% ] report4.nsys-rep␍[1/8] [============55% ] report4.nsys-rep␍[1/8] [============56% ] report4.nsys-rep␍[1/8] [============57% ] report4.nsys-rep␍[1/8] [=============58% ] report4.nsys-rep␍[1/8] [=============59% ] report4.nsys-rep␍[1/8] [=============60% ] report4.nsys-rep␍[1/8] [===================79% ] report4.nsys-rep␍[1/8] [======================90% ] report4.nsys-rep␍[1/8] [========================100%] report4.nsys-rep␍[1/8] [========================100%] report4.nsys-rep
|
||||
[2/8] [0% ] report4.sqlite
[2/8] [1% ] report4.sqlite
[2/8] [2% ] report4.sqlite
[2/8] [3% ] report4.sqlite
[2/8] [4% ] report4.sqlite
[2/8] [5% ] report4.sqlite
[2/8] [6% ] report4.sqlite
[2/8] [7% ] report4.sqlite
[2/8] [8% ] report4.sqlite
[2/8] [9% ] report4.sqlite
[2/8] [10% ] report4.sqlite
[2/8] [11% ] report4.sqlite
[2/8] [12% ] report4.sqlite
[2/8] [13% ] report4.sqlite
[2/8] [14% ] report4.sqlite
[2/8] [=15% ] report4.sqlite
[2/8] [=16% ] report4.sqlite
[2/8] [=17% ] report4.sqlite
[2/8] [==18% ] report4.sqlite
[2/8] [==19% ] report4.sqlite
[2/8] [==20% ] report4.sqlite
[2/8] [==21% ] report4.sqlite
[2/8] [===22% ] report4.sqlite
[2/8] [===23% ] report4.sqlite
[2/8] [===24% ] report4.sqlite
[2/8] [====25% ] report4.sqlite
[2/8] [====26% ] report4.sqlite
[2/8] [====27% ] report4.sqlite
[2/8] [====28% ] report4.sqlite
[2/8] [=====29% ] report4.sqlite
[2/8] [=====30% ] report4.sqlite
[2/8] [=====31% ] report4.sqlite
[2/8] [=====32% ] report4.sqlite
[2/8] [======33% ] report4.sqlite
[2/8] [======34% ] report4.sqlite
[2/8] [======35% ] report4.sqlite
[2/8] [=======36% ] report4.sqlite
[2/8] [=======37% ] report4.sqlite
[2/8] [=======38% ] report4.sqlite
[2/8] [=======39% ] report4.sqlite
[2/8] [========40% ] report4.sqlite
[2/8] [========41% ] report4.sqlite
[2/8] [========42% ] report4.sqlite
[2/8] [=========43% ] report4.sqlite
[2/8] [=========44% ] report4.sqlite
[2/8] [=========45% ] report4.sqlite
[2/8] [=========46% ] report4.sqlite
[2/8] [==========47% ] report4.sqlite
[2/8] [==========48% ] report4.sqlite
[2/8] [==========49% ] report4.sqlite
[2/8] [===========50% ] report4.sqlite
[2/8] [===========51% ] report4.sqlite
[2/8] [===========52% ] report4.sqlite
[2/8] [===========53% ] report4.sqlite
[2/8] [============54% ] report4.sqlite
[2/8] [============55% ] report4.sqlite
[2/8] [============56% ] report4.sqlite
[2/8] [============57% ] report4.sqlite
[2/8] [=============58% ] report4.sqlite
[2/8] [=============59% ] report4.sqlite
[2/8] [=============60% ] report4.sqlite
[2/8] [==============61% ] report4.sqlite
[2/8] [==============62% ] report4.sqlite
[2/8] [==============63% ] report4.sqlite
[2/8] [==============64% ] report4.sqlite
[2/8] [===============65% ] report4.sqlite
[2/8] [===============66% ] report4.sqlite
[2/8] [===============67% ] report4.sqlite
[2/8] [================68% ] report4.sqlite
[2/8] [================69% ] report4.sqlite
[2/8] [================70% ] report4.sqlite
[2/8] [================71% ] report4.sqlite
[2/8] [=================72% ] report4.sqlite
[2/8] [=================73% ] report4.sqlite
[2/8] [=================74% ] report4.sqlite
[2/8] [==================75% ] report4.sqlite
[2/8] [==================76% ] report4.sqlite
[2/8] [==================77% ] report4.sqlite
[2/8] [==================78% ] report4.sqlite
[2/8] [===================79% ] report4.sqlite
[2/8] [===================80% ] report4.sqlite
[2/8] [===================81% ] report4.sqlite
[2/8] [===================82% ] report4.sqlite
[2/8] [====================83% ] report4.sqlite
[2/8] [====================84% ] report4.sqlite
[2/8] [====================85% ] report4.sqlite
[2/8] [=====================86% ] report4.sqlite
[2/8] [=====================87% ] report4.sqlite
[2/8] [=====================88% ] report4.sqlite
[2/8] [=====================89% ] report4.sqlite
[2/8] [======================90% ] report4.sqlite
[2/8] [======================91% ] report4.sqlite
[2/8] [======================92% ] report4.sqlite
[2/8] [=======================93% ] report4.sqlite
[2/8] [=======================94% ] report4.sqlite
[2/8] [=======================95% ] report4.sqlite
[2/8] Line truncated
|
||||
[3/8] Executing 'nvtx_sum' stats report
|
||||
[4/8] Executing 'osrt_sum' stats report
|
||||
|
||||
Time (%) Total Time (ns) Num Calls Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Name
|
||||
-------- --------------- --------- ---------- ---------- -------- --------- ----------- ----------------------
|
||||
63.4 596797662 16 37299853.9 11463331.5 1312 100128054 44505075.2 poll
|
||||
12.3 115657312 38 3043613.5 6326.5 3507 114185851 18517552.8 fopen
|
||||
12.0 112644556 591 190599.9 23554.0 1092 20946538 916359.7 ioctl
|
||||
9.5 89859962 6 14976660.3 107220.5 7223 81799661 32883386.3 fread
|
||||
0.9 8564355 1 8564355.0 8564355.0 8564355 8564355 0.0 pthread_cond_wait
|
||||
0.8 7100598 1 7100598.0 7100598.0 7100598 7100598 0.0 pthread_cond_broadcast
|
||||
0.5 4587263 32 143352.0 2204.5 1333 3746586 671302.8 fclose
|
||||
0.2 2342308 25 93692.3 9026.0 6772 1633214 323364.9 mmap64
|
||||
0.2 2014448 10 201444.8 31454.0 22051 884024 304027.7 write
|
||||
0.1 593932 17 34937.2 8366.0 1873 379470 90751.4 mmap
|
||||
0.0 372607 2 186303.5 186303.5 168375 204232 25354.7 pthread_create
|
||||
0.0 320273 55 5823.1 6021.0 2334 10550 2072.2 open64
|
||||
0.0 170338 1 170338.0 170338.0 170338 170338 0.0 fflush
|
||||
0.0 77535 1 77535.0 77535.0 77535 77535 0.0 fgets
|
||||
0.0 60311 8 7538.9 4633.5 2735 23083 6839.3 munmap
|
||||
0.0 37641 6 6273.5 6372.0 3216 9387 2126.0 open
|
||||
0.0 22875 3 7625.0 9138.0 3808 9929 3329.2 pipe2
|
||||
0.0 17262 9 1918.0 1423.0 1022 3747 993.8 read
|
||||
0.0 16491 2 8245.5 8245.5 5891 10600 3329.8 socket
|
||||
0.0 10971 1 10971.0 10971.0 10971 10971 0.0 connect
|
||||
0.0 6632 1 6632.0 6632.0 6632 6632 0.0 fopen64
|
||||
0.0 6061 1 6061.0 6061.0 6061 6061 0.0 pthread_mutex_trylock
|
||||
0.0 3176 2 1588.0 1588.0 1453 1723 190.9 fwrite
|
||||
0.0 2365 1 2365.0 2365.0 2365 2365 0.0 bind
|
||||
0.0 1042 1 1042.0 1042.0 1042 1042 0.0 fcntl
|
||||
|
||||
[5/8] Executing 'cuda_api_sum' stats report
|
||||
|
||||
Time (%) Total Time (ns) Num Calls Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Name
|
||||
-------- --------------- --------- ---------- ---------- -------- -------- ----------- ---------------------------------
|
||||
87.1 91151498 3 30383832.7 36093633.0 21130 55036735 27948713.1 cudaMemcpy
|
||||
5.1 5373556 12 447796.3 6998.0 200 1853236 632488.6 cudaFree
|
||||
2.3 2415988 1 2415988.0 2415988.0 2415988 2415988 0.0 cudaFreeHost
|
||||
1.7 1811777 1 1811777.0 1811777.0 1811777 1811777 0.0 cudaMallocHost
|
||||
1.4 1447858 1 1447858.0 1447858.0 1447858 1447858 0.0 cudaGetDeviceProperties_v2_v12000
|
||||
1.1 1146304 171 6703.5 2825.0 2715 449320 34539.6 cudaLaunchKernel
|
||||
1.0 1047369 6 174561.5 124498.0 3266 462335 182577.2 cudaMalloc
|
||||
0.1 147859 838 176.4 150.0 80 721 81.0 cuGetProcAddress_v2
|
||||
0.0 46527 1 46527.0 46527.0 46527 46527 0.0 cudaMemset
|
||||
0.0 15610 18 867.2 301.0 250 5870 1417.2 cudaEventCreateWithFlags
|
||||
0.0 13797 4 3449.3 2790.5 1002 7214 2662.6 cudaDeviceSynchronize
|
||||
0.0 7324 18 406.9 270.5 201 2194 468.7 cudaEventDestroy
|
||||
0.0 5211 4 1302.8 1253.0 1242 1463 107.0 cuInit
|
||||
0.0 1252 3 417.3 130.0 110 1012 515.1 cuModuleGetLoadingMode
|
||||
0.0 862 2 431.0 431.0 281 581 212.1 cudaGetDriverEntryPoint_v11030
|
||||
|
||||
[6/8] Executing 'cuda_gpu_kern_sum' stats report
|
||||
|
||||
Time (%) Total Time (ns) Instances Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Name
|
||||
-------- --------------- --------- -------- -------- -------- -------- ----------- ----------------------------------------------------------------------------------------------------
|
||||
88.5 42371434 49 864723.1 794053.0 249378 11507721 1574324.4 matmul_forward_kernel(float *, const float *, const float *, const float *, int, int, int, int)
|
||||
8.5 4090620 25 163624.8 164129.0 158689 166433 2048.2 layernorm_forward_kernel(float *, float *, float *, const float *, const float *, const float *, in…
|
||||
0.6 282529 12 23544.1 23536.0 22944 23968 352.1 attention_v_kernel(float *, float *, float *, int, int, int, int)
|
||||
0.6 278114 12 23176.2 23136.0 22848 23680 232.5 preattention_scores_kernel(float *, float *, int, int, int, int, float *)
|
||||
0.5 226402 12 18866.8 18864.0 18784 18945 50.2 gelu_forward_kernel(float *, const float *, int)
|
||||
0.5 215713 12 17976.1 17968.5 17856 18144 94.6 softmax_forward_kernel(float *, float, const float *, int, int)
|
||||
0.3 145216 24 6050.7 6064.0 5632 6496 364.6 residual_forward_kernel(float *, float *, float *, int)
|
||||
0.2 110113 12 9176.1 9200.0 8928 9472 142.4 permute_kernel(float *, float *, float *, const float *, int, int, int, int)
|
||||
0.2 85280 1 85280.0 85280.0 85280 85280 0.0 encoder_forward_kernel(float *, const int *, const float *, const float *, int, int, int)
|
||||
0.1 70369 12 5864.1 5856.0 5824 5920 27.6 unpermute_kernel(float *, float *, int, int, int, int)
|
||||
|
||||
[7/8] Executing 'cuda_gpu_mem_time_sum' stats report
|
||||
|
||||
Time (%) Total Time (ns) Count Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Operation
|
||||
-------- --------------- ----- ---------- ---------- -------- -------- ----------- ----------------------------
|
||||
81.7 35990437 2 17995218.5 17995218.5 864 35989573 25447860.2 [CUDA memcpy Host-to-Device]
|
||||
17.4 7673713 1 7673713.0 7673713.0 7673713 7673713 0.0 [CUDA memcpy Device-to-Host]
|
||||
0.9 407011 1 407011.0 407011.0 407011 407011 0.0 [CUDA memset]
|
||||
|
||||
[8/8] Executing 'cuda_gpu_mem_size_sum' stats report
|
||||
|
||||
Total (MB) Count Avg (MB) Med (MB) Min (MB) Max (MB) StdDev (MB) Operation
|
||||
---------- ----- -------- -------- -------- -------- ----------- ----------------------------
|
||||
497.905 2 248.952 248.952 0.001 497.904 352.070 [CUDA memcpy Host-to-Device]
|
||||
232.392 1 232.392 232.392 232.392 232.392 0.000 [CUDA memset]
|
||||
51.511 1 51.511 51.511 51.511 51.511 0.000 [CUDA memcpy Device-to-Host]
|
||||
|
||||
Generated:
|
||||
/u/asingh41/sp26_ece408_Temperature1.5/report4.nsys-rep
|
||||
/u/asingh41/sp26_ece408_Temperature1.5/report4.sqlite
|
||||
Reference in new issue
Block a user