Skip to content

Fix some hyperthreading errors. #5295

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions driver/others/init.c
Original file line number Diff line number Diff line change
Expand Up @@ -391,7 +391,15 @@ static void numa_mapping(void) {
core = 0;
for (cpu = 0; cpu < common -> num_procs; cpu ++) {
bitmask_idx = CPUELT(cpu);
/*
* When common->avail[i] = 0x5555555555555555UL (indicating that adjacent logical cores share a physical core),
* using it as a mask may overlap with the local_cpu_map function's role, leading to only half of the real physical cores being detected.
*/
#ifdef ARCH_LOONGARCH64
if (common -> node_info[node][bitmask_idx]) {
#else
if (common -> node_info[node][bitmask_idx] & common -> avail[bitmask_idx] & CPUMASK(cpu)) {
#endif
common -> cpu_info[count] = WRITE_CORE(core) | WRITE_NODE(node) | WRITE_CPU(cpu);
count ++;
core ++;
Expand Down Expand Up @@ -930,8 +938,12 @@ void gotoblas_affinity_init(void) {

if (common -> num_nodes > 1) numa_mapping();

#ifdef ARCH_LOONGARCH64
common -> final_num_procs = common -> num_procs;
#else
common -> final_num_procs = 0;
for(i = 0; i < common -> avail_count; i++) common -> final_num_procs += rcount(common -> avail[i]) + 1; //Make the max cpu number.
#endif

for (cpu = 0; cpu < common -> final_num_procs; cpu ++) common -> cpu_use[cpu] = 0;

Expand Down