Brice Goglin
Brice Goglin
Also, according to https://patchwork.freedesktop.org/patch/125069/ reading the config file from sysfs may wake up the device, which could be very slow. So basically we should either do everything from sysfs when...
Hello Look for cuda_runtime_api.h in config.log to find out the entire compile line that failed. In theory, your CFLAGS isn't needed (it's only for compiler flags), only CPPFLAGS should contain...
If pgcc doesn't support cuda_runtime_api.h, then some parts of hwloc itself won't build with pgcc (at least topology-cuda.c and tests/hwloc/cuda*.c), and you would need to use CC=pg++ for building hwloc.
Hello @chingking and @YuhaoYHH Does this problem still occur?
Could be related to #232
@NicolasDenoyelle can you rebase/squash these commits to ease review?
Note to open pull requests: some things changed in the CI yesterday, you'll need to rebase on top of master to avoid total CI failure.
Could be related to #208
Hello. I wondered the same when testing the gcc farm yesterday. Linux is showing a single core with 4 threads. I saw some possibly related patched on the Linux kernel...
Reported the issue to RISC-V developers at https://lkml.org/lkml/2022/7/5/1568 and there are now kernel patches at https://lore.kernel.org/linux-riscv/[email protected]/ which should fix the issue.