Add and fix H100 NCU counter mappings #2
Merged
+9
−9
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
When profiling on H100, 9 counters in counters.py produced warnings due
to empty or incorrect NCU metric mappings:
[WARNING] The report doesn't has this counter: pipe_fp16 -> sm__inst_executed_pipe_fp16...
[WARNING] The report doesn't has this counter: dram_util ->
[WARNING] The report doesn't has this counter: shared_ld_requests ->
...
Fixed 2 broken mappings:
- pipe_fp16: H100 renamed the fp16 pipe metric to fma_type_fp16
- kernel_name: "Kernel Name" is not a valid NCU metric, use launch__kernel_name
Filled 7 previously empty mappings by matching against available H100
NCU profile metrics:
- dram_util -> dram__cycles_active.avg.pct_of_peak_sustained_elapsed
- dram_throughput -> dram__throughput.avg.pct_of_peak_sustained_elapsed
- imc_hitrate -> smsp__imc_request_hit_rate.pct
- shared_ld_requests -> l1tex__t_requests_pipe_lsu_mem_dshared_op_ld.sum
- shared_st_requests -> l1tex__t_requests_pipe_lsu_mem_dshared_op_st.sum
- gnic_lg_read_requests_precoalescing -> l1tex__t_requests_pipe_lsu_mem_global_op_ld.sum
- gnic_lg_read_requests_postcoalescing -> l1tex__t_output_wavefronts_pipe_lsu_mem_global_op_ld.sum
jhdavis8
approved these changes
Feb 2, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
9 counters in
counters.pyhad empty or incorrect NCU metric mappings, causing warnings when profiling on H100.Fixed 2 broken mappings:
pipe_fp16: H100 renamed the fp16 pipe metric tofma_type_fp16kernel_name:"Kernel Name"is not a valid NCU metric, replaced withlaunch__kernel_nameFilled 7 previously empty mappings:
dram_util,dram_throughput,imc_hitrate,shared_ld_requests,shared_st_requests,gnic_lg_read_requests_precoalescing,gnic_lg_read_requests_postcoalescingWarnings observed
Mappings were determined by matching semantically against available metrics in H100
.ncu-repprofiles.