Skip to content

add violation metrics 1.8 version changes adding partition level violation stats #33

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.

Sign up for GitHub

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

Merged
sarat-k merged 1 commit into from
Nov 7, 2025
Merged

add violation metrics 1.8 version changes adding partition level violation stats #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
26 changes: 26 additions & 0 deletions sw/nic/gpuagent/api/include/aga_gpu.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,6 +576,32 @@ typedef struct aga_gpu_violation_stats_s {
uint64_t vr_thermal_residency_accumulated;
/// High Bandwidth Memory (HBM) thermal residency accumulated
uint64_t hbm_thermal_residency_accumulated;
/// processor hot residency percentage
uint64_t processor_hot_residency_percentage;
/// Package Power Tracking (PPT) residency percentage
uint64_t ppt_residency_percentage;
/// socket thermal residency percentage
uint64_t socket_thermal_residency_percentage;
/// Voltage Rail (VR) thermal residency percentage
uint64_t vr_thermal_residency_percentage;
/// High Bandwidth Memory (HBM) thermal residency percentage
uint64_t hbm_thermal_residency_percentage;
/// gfx clock below host limit power accumulated per XCC
uint64_t gfx_clk_below_host_limit_power_accumulated[AGA_GPU_MAX_XCC];
/// gfx clock below host limit thermal accumulated per XCC
uint64_t gfx_clk_below_host_limit_thermal_accumulated[AGA_GPU_MAX_XCC];
/// gfx low utilization accumulated per XCC
uint64_t gfx_low_utilization_accumulated[AGA_GPU_MAX_XCC];
/// gfx clock below host limit total accumulated per XCC
uint64_t gfx_clk_below_host_limit_total_accumulated[AGA_GPU_MAX_XCC];
/// gfx clock below host limit power percentage per XCC
uint64_t gfx_clk_below_host_limit_power_percentage[AGA_GPU_MAX_XCC];
/// gfx clock below host limit thermal percentage per XCC
uint64_t gfx_clk_below_host_limit_thermal_percentage[AGA_GPU_MAX_XCC];
/// gfx low utilization percentage per XCC
uint64_t gfx_low_utilization_percentage[AGA_GPU_MAX_XCC];
/// gfx clock below host limit total percentage per XCC
uint64_t gfx_clk_below_host_limit_total_percentage[AGA_GPU_MAX_XCC];
} aga_gpu_violation_stats_t;

/// \brief GPU statistics
Expand Down
Loading