MemoryUB (UB Read/Write Bandwidth Rate)
MemoryUB.csv stores the collected MTE/Vector/Scalar UB read/write bandwidth rate data. For details, see the field description in the following table.
|
Field |
Description |
|---|---|
|
block_id |
Number of running task blocks, which corresponds to the number of cores configured during task running. |
|
sub_block_id |
Name and sequence number of each block used for task running. |
|
aic_time(us) |
Execution time (μs) on each AI Cube Core compute unit after the task is allocated to each AI Cube Core compute unit. |
|
aic_total_cycles |
Total number of cycles executed on each AI Cube Core compute unit after the task is allocated to each AI Cube Core compute unit. |
|
aiv_time(us) |
Execution time of each AI Vector Core compute unit after the task is allocated to the unit, in μs. |
|
aiv_total_cycles |
Total number of cycles executed on each AI Vector Core compute unit after the task is allocated to the unit. |
|
aiv_ub_read_bw_vector(GB/s) |
Bandwidth read from UB by Vector (GB/s) |
|
aiv_ub_write_bw_vector(GB/s) |
Bandwidth written to UB by Vector (GB/s) |
|
aiv_ub_read_bw_scalar(GB/s) |
Bandwidth read from UB by Scalar (GB/s) |
|
aiv_ub_write_bw_scalar(GB/s) |
Bandwidth written to UB by Scalar (GB/s) |
|
Field |
Description |
|---|---|
|
aic_time(us) |
Execution time of each AI Core compute unit after the task is allocated to the unit, in μs. |
|
aic_total_cycles |
Total number of cycles executed on each AI Core compute unit after the task is allocated to the unit. |
|
aic_ub_read_bw_vector(GB/s) |
Bandwidth read from UB by Vector (GB/s) |
|
aic_ub_write_bw_vector(GB/s) |
Bandwidth written to UB by Vector (GB/s) |
|
aic_ub_read_bw_scalar(GB/s) |
Bandwidth read from UB by Scalar (GB/s) |
|
aic_ub_write_bw_scalar(GB/s) |
Bandwidth written to UB by Scalar (GB/s) |