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 +1,114 @@
|
||||
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, -43.431801
|
||||
-39.836346, -39.836525
|
||||
-43.065910, -43.066086
|
||||
-42.828045, -42.828217
|
||||
-43.529541, -43.529724
|
||||
-44.318398, -44.318581
|
||||
-41.227425, -41.227596
|
||||
-41.270760, -41.270927
|
||||
-42.541393, -42.541595
|
||||
-42.394997, -42.395184
|
||||
---------------- Logits OK! (max err 0.000069, RMSE 0.000002) ----------------
|
||||
_________________________ All tests passed! _________________________
|
||||
Collecting data...
|
||||
Generating '/tmp/nsys-report-e25f.qdstrm'
|
||||
␍[1/8] [0% ] report7.nsys-rep␍[1/8] [0% ] report7.nsys-rep␍[1/8] [=16% ] report7.nsys-rep␍[1/8] [=====31% ] report7.nsys-rep␍[1/8] [=====32% ] report7.nsys-rep␍[1/8] [====25% ] report7.nsys-rep␍[1/8] [======35% ] report7.nsys-rep␍[1/8] [=======36% ] report7.nsys-rep␍[1/8] [=======37% ] report7.nsys-rep␍[1/8] [=======38% ] report7.nsys-rep␍[1/8] [=======39% ] report7.nsys-rep␍[1/8] [========40% ] report7.nsys-rep␍[1/8] [========41% ] report7.nsys-rep␍[1/8] [========42% ] report7.nsys-rep␍[1/8] [==================78% ] report7.nsys-rep␍[1/8] [=====================86% ] report7.nsys-rep␍[1/8] [========================100%] report7.nsys-rep␍[1/8] [========================100%] report7.nsys-rep
|
||||
[2/8] [0% ] report7.sqlite
[2/8] [1% ] report7.sqlite
[2/8] [2% ] report7.sqlite
[2/8] [3% ] report7.sqlite
[2/8] [4% ] report7.sqlite
[2/8] [5% ] report7.sqlite
[2/8] [6% ] report7.sqlite
[2/8] [7% ] report7.sqlite
[2/8] [8% ] report7.sqlite
[2/8] [9% ] report7.sqlite
[2/8] [10% ] report7.sqlite
[2/8] [11% ] report7.sqlite
[2/8] [12% ] report7.sqlite
[2/8] [13% ] report7.sqlite
[2/8] [14% ] report7.sqlite
[2/8] [=15% ] report7.sqlite
[2/8] [=16% ] report7.sqlite
[2/8] [=17% ] report7.sqlite
[2/8] [==18% ] report7.sqlite
[2/8] [==19% ] report7.sqlite
[2/8] [==20% ] report7.sqlite
[2/8] [==21% ] report7.sqlite
[2/8] [===22% ] report7.sqlite
[2/8] [===23% ] report7.sqlite
[2/8] [===24% ] report7.sqlite
[2/8] [====25% ] report7.sqlite
[2/8] [====26% ] report7.sqlite
[2/8] [====27% ] report7.sqlite
[2/8] [====28% ] report7.sqlite
[2/8] [=====29% ] report7.sqlite
[2/8] [=====30% ] report7.sqlite
[2/8] [=====31% ] report7.sqlite
[2/8] [=====32% ] report7.sqlite
[2/8] [======33% ] report7.sqlite
[2/8] [======34% ] report7.sqlite
[2/8] [======35% ] report7.sqlite
[2/8] [=======36% ] report7.sqlite
[2/8] [=======37% ] report7.sqlite
[2/8] [=======38% ] report7.sqlite
[2/8] [=======39% ] report7.sqlite
[2/8] [========40% ] report7.sqlite
[2/8] [========41% ] report7.sqlite
[2/8] [========42% ] report7.sqlite
[2/8] [=========43% ] report7.sqlite
[2/8] [=========44% ] report7.sqlite
[2/8] [=========45% ] report7.sqlite
[2/8] [=========46% ] report7.sqlite
[2/8] [==========47% ] report7.sqlite
[2/8] [==========48% ] report7.sqlite
[2/8] [==========49% ] report7.sqlite
[2/8] [===========50% ] report7.sqlite
[2/8] [===========51% ] report7.sqlite
[2/8] [===========52% ] report7.sqlite
[2/8] [===========53% ] report7.sqlite
[2/8] [============54% ] report7.sqlite
[2/8] [============55% ] report7.sqlite
[2/8] [============56% ] report7.sqlite
[2/8] [============57% ] report7.sqlite
[2/8] [=============58% ] report7.sqlite
[2/8] [=============59% ] report7.sqlite
[2/8] [=============60% ] report7.sqlite
[2/8] [==============61% ] report7.sqlite
[2/8] [==============62% ] report7.sqlite
[2/8] [==============63% ] report7.sqlite
[2/8] [==============64% ] report7.sqlite
[2/8] [===============65% ] report7.sqlite
[2/8] [===============66% ] report7.sqlite
[2/8] [===============67% ] report7.sqlite
[2/8] [================68% ] report7.sqlite
[2/8] [================69% ] report7.sqlite
[2/8] [================70% ] report7.sqlite
[2/8] [================71% ] report7.sqlite
[2/8] [=================72% ] report7.sqlite
[2/8] [=================73% ] report7.sqlite
[2/8] [=================74% ] report7.sqlite
[2/8] [==================75% ] report7.sqlite
[2/8] [==================76% ] report7.sqlite
[2/8] [==================77% ] report7.sqlite
[2/8] [==================78% ] report7.sqlite
[2/8] [===================79% ] report7.sqlite
[2/8] [===================80% ] report7.sqlite
[2/8] [===================81% ] report7.sqlite
[2/8] [===================82% ] report7.sqlite
[2/8] [====================83% ] report7.sqlite
[2/8] [====================84% ] report7.sqlite
[2/8] [====================85% ] report7.sqlite
[2/8] [=====================86% ] report7.sqlite
[2/8] [=====================87% ] report7.sqlite
[2/8] [=====================88% ] report7.sqlite
[2/8] [=====================89% ] report7.sqlite
[2/8] [======================90% ] report7.sqlite
[2/8] [======================91% ] report7.sqlite
[2/8] [======================92% ] report7.sqlite
[2/8] [=======================93% ] report7.sqlite
[2/8] [=======================94% ] report7.sqlite
[2/8] [=======================95% ] report7.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
|
||||
-------- --------------- --------- ---------- ---------- -------- --------- ----------- ----------------------
|
||||
62.0 680717261 17 40042191.8 10065417.0 1532 100136863 44760103.1 poll
|
||||
14.8 162110818 38 4266074.2 6131.0 3496 161029552 26117864.7 fopen
|
||||
11.0 120373004 6 20062167.3 89457.5 6833 95159843 38120924.5 fread
|
||||
10.4 114685549 591 194053.4 23404.0 1032 22556281 980200.7 ioctl
|
||||
0.8 9116342 1 9116342.0 9116342.0 9116342 9116342 0.0 pthread_cond_broadcast
|
||||
0.4 3892842 32 121651.3 2144.0 1353 3504445 619781.4 fclose
|
||||
0.2 2358791 25 94351.6 8787.0 6392 1637323 324262.9 mmap64
|
||||
0.2 1996705 1 1996705.0 1996705.0 1996705 1996705 0.0 pthread_cond_wait
|
||||
0.2 1950609 10 195060.9 27181.0 22051 798313 285177.5 write
|
||||
0.1 591677 17 34804.5 5981.0 1893 395630 94748.6 mmap
|
||||
0.0 362288 2 181144.0 181144.0 171561 190727 13552.4 pthread_create
|
||||
0.0 322858 55 5870.1 5861.0 2314 14327 2395.2 open64
|
||||
0.0 76734 1 76734.0 76734.0 76734 76734 0.0 fgets
|
||||
0.0 62457 1 62457.0 62457.0 62457 62457 0.0 fflush
|
||||
0.0 40205 6 6700.8 6922.5 3527 9608 2269.3 open
|
||||
0.0 38922 8 4865.3 5074.5 2765 7153 1707.3 munmap
|
||||
0.0 19787 3 6595.7 7844.0 3657 8286 2554.5 pipe2
|
||||
0.0 18904 10 1890.4 1623.0 1012 3516 882.0 read
|
||||
0.0 15960 2 7980.0 7980.0 5100 10860 4072.9 socket
|
||||
0.0 11101 1 11101.0 11101.0 11101 11101 0.0 connect
|
||||
0.0 6472 1 6472.0 6472.0 6472 6472 0.0 fopen64
|
||||
0.0 3417 2 1708.5 1708.5 1393 2024 446.2 fwrite
|
||||
0.0 1593 1 1593.0 1593.0 1593 1593 0.0 bind
|
||||
|
||||
[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
|
||||
-------- --------------- --------- ---------- ---------- -------- -------- ----------- ---------------------------------
|
||||
61.4 51907511 3 17302503.7 15637119.0 21119 36249273 18171403.8 cudaMemcpy
|
||||
18.9 15960434 4 3990108.5 3249843.5 1031059 8429688 3147630.5 cuLibraryLoadData
|
||||
6.1 5177442 12 431453.5 6161.5 191 1837587 621479.2 cudaFree
|
||||
5.7 4819182 1347 3577.7 3086.0 2835 335788 9243.6 cudaLaunchKernel
|
||||
2.9 2489386 1 2489386.0 2489386.0 2489386 2489386 0.0 cudaFreeHost
|
||||
1.7 1448309 1 1448309.0 1448309.0 1448309 1448309 0.0 cudaGetDeviceProperties_v2_v12000
|
||||
1.6 1383518 1 1383518.0 1383518.0 1383518 1383518 0.0 cudaMallocHost
|
||||
0.9 766724 6 127787.3 123215.5 3447 318305 118859.5 cudaMalloc
|
||||
0.2 160077 838 191.0 151.0 70 6683 242.2 cuGetProcAddress_v2
|
||||
0.2 139420 48 2904.6 2500.0 2184 13164 1581.6 cudaMemsetAsync
|
||||
0.2 137165 48 2857.6 2690.0 1974 12383 1519.2 cudaEventRecord
|
||||
0.0 35015 1 35015.0 35015.0 35015 35015 0.0 cudaMemset
|
||||
0.0 30347 4 7586.8 7734.0 6913 7966 469.4 cuLibraryGetKernel
|
||||
0.0 27345 240 113.9 90.0 69 1262 81.3 cuStreamGetCaptureInfo_v2
|
||||
0.0 17219 18 956.6 300.0 260 7834 1819.2 cudaEventCreateWithFlags
|
||||
0.0 12852 4 3213.0 2549.5 991 6762 2485.5 cudaDeviceSynchronize
|
||||
0.0 8116 18 450.9 301.0 211 2675 566.0 cudaEventDestroy
|
||||
0.0 5371 4 1342.8 1343.0 1172 1513 139.5 cuInit
|
||||
0.0 3317 1 3317.0 3317.0 3317 3317 0.0 cudaEventQuery
|
||||
0.0 1322 3 440.7 180.0 130 1012 495.4 cuModuleGetLoadingMode
|
||||
0.0 872 2 436.0 436.0 211 661 318.2 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
|
||||
-------- --------------- --------- -------- -------- -------- -------- ----------- ----------------------------------------------------------------------------------------------------
|
||||
25.6 4083613 25 163344.5 163744.0 158464 166208 2004.3 layernorm_forward_kernel(float *, float *, float *, const float *, const float *, const float *, in…
|
||||
22.8 3644222 576 6326.8 6336.0 6144 6592 79.1 ampere_sgemm_32x128_nn
|
||||
16.8 2675550 25 107022.0 78560.0 60384 1000383 186333.0 ampere_sgemm_128x64_tn
|
||||
15.9 2535902 576 4402.6 4384.0 4352 4864 60.7 ampere_sgemm_32x32_sliced1x4_tn
|
||||
10.0 1591582 12 132631.8 133168.0 129568 134783 1430.5 ampere_sgemm_64x64_tn
|
||||
2.4 390976 12 32581.3 32528.0 32384 32928 170.9 ampere_sgemm_64x32_sliced1x4_tn
|
||||
1.4 223072 12 18589.3 18560.0 18528 18848 90.0 gelu_forward_kernel(float *, const float *, int)
|
||||
1.4 219968 48 4582.7 4288.0 2848 7616 1622.8 bias_add_kernel(float *, const float *, int, int)
|
||||
1.4 217344 12 18112.0 18000.0 17920 19200 353.5 softmax_forward_kernel(float *, float, const float *, int, int)
|
||||
0.9 142080 24 5920.0 5952.0 5632 6240 265.2 residual_forward_kernel(float *, float *, float *, int)
|
||||
0.6 89376 1 89376.0 89376.0 89376 89376 0.0 encoder_forward_kernel(float *, const int *, const float *, const float *, int, int, int)
|
||||
0.5 84511 12 7042.6 7008.0 6976 7392 112.9 permute_kernel(float *, float *, float *, const float *, int, int, int, int)
|
||||
0.4 70944 12 5912.0 5888.0 5824 6016 62.7 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
|
||||
-------- --------------- ----- ---------- ---------- -------- -------- ----------- ----------------------------
|
||||
81.3 36158470 2 18079235.0 18079235.0 832 36157638 25566722.7 [CUDA memcpy Host-to-Device]
|
||||
17.6 7821051 1 7821051.0 7821051.0 7821051 7821051 0.0 [CUDA memcpy Device-to-Host]
|
||||
1.1 473504 49 9663.3 1184.0 480 407616 58036.0 [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]
|
||||
232.407 49 4.743 0.000 0.000 232.392 33.199 [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/report7.nsys-rep
|
||||
/u/asingh41/sp26_ece408_Temperature1.5/report7.sqlite
|
||||
Reference in new issue
Block a user