HoneyPatouceul
HoneyPatouceul
You may have to increase STATS_BUFFER_SIZE in file gtop.hh, for example: `const int STATS_BUFFER_SIZE = 512; ` Also note that the test for which Jetson relying on tegrastats output length...
Added support for TX1 R28.1. [gtop.cc.txt](https://github.com/martinkersner/gtop/files/1737522/gtop.cc.txt)
I have added support for R28.1, but you're running a very old R23.1 version. You would have to create indexes for R23.1 such as : ``` static const std::map TX1cpuIdxMap...
Increasing the buffer size is required from R28.2 that logs almost double information with temperatures. For TX1 on R28.1, cpu index should be 5 and gpu index 7. Note that...
Replied at: https://devtalk.nvidia.com/default/topic/1005519/jetson-tx1/tegrastats-visualization/post/5256193/#5256193
Further testing on TX2 with R28.2-DP and cuda9, using cuda-memcheck with AF-3.6.0 debug build (with some jit traces and skipping patch from #2037, but similar without these) I see: ```...
@9prady9 With R28.1 on my TX1 (I think it's cuda 8.0.84), I see memory faults as reported in my second post in #2036. Interestingly, the test passes. But running it...
@9prady9 Just tried cuda.8.0.84 on my TX2 with L4T R28.2-DP for an arrayfire debug build (configured and built with cuda 8). It shows mmu faults when running (and test fails),...