[rocprof-compute] Wrap negative values in L2 - Fabric interface detailed metrics (#833)
* update gfx942 soc_config 1700 * add MAX wrapper for Write and Atomic (32B) * removed trailing whitespace and EA* fix * added to CHANGELOG.md * edited changelog
Αυτή η υποβολή περιλαμβάνεται σε:
υποβλήθηκε από
GitHub
γονέας
4ebc4ff5ba
υποβολή
62843ed900
@@ -143,6 +143,9 @@ Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.
|
||||
|
||||
### Known issues
|
||||
|
||||
* MI300A/X L2-Fabric 64B read counter may display negative values - The rocprof-compute metric 17.6.1 (Read 64B) can report negative values due to incorrect calculation when TCC_BUBBLE_sum + TCC_EA0_RDREQ_32B_sum exceeds TCC_EA0_RDREQ_sum.
|
||||
* A workaround has been implemented using max(0, calculated_value) to prevent negative display values while the root cause is under investigation.
|
||||
|
||||
### Upcoming changes
|
||||
|
||||
## ROCm Compute Profiler 3.2.3 for ROCm 7.0.0
|
||||
|
||||
+3
-3
@@ -529,9 +529,9 @@ Panel Config:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
+3
-3
@@ -529,9 +529,9 @@ Panel Config:
|
||||
max: MAX((MAX((TCC_EA_RDREQ_sum - TCC_EA_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
+3
-3
@@ -529,9 +529,9 @@ Panel Config:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
+3
-3
@@ -529,9 +529,9 @@ Panel Config:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
+9
-9
@@ -513,12 +513,12 @@ Panel Config:
|
||||
max: MAX((TCC_EA0_RDREQ_32B_sum / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Read (64B):
|
||||
avg: AVG(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum) /
|
||||
$denom))
|
||||
min: MIN(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum) /
|
||||
$denom))
|
||||
max: MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum) /
|
||||
$denom))
|
||||
avg: AVG(MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum)
|
||||
/ $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum)
|
||||
/ $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum)
|
||||
/ $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Read (128B):
|
||||
avg: AVG(((TCC_BUBBLE_sum) / $denom))
|
||||
@@ -541,9 +541,9 @@ Panel Config:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
+3
-3
@@ -668,9 +668,9 @@ Panel Config:
|
||||
max: MAX(TCC_EA0_RDREQ_DRAM_32B_sum * 32/ (End_Timestamp - Start_Timestamp))
|
||||
unit: Gbps
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
@@ -89,12 +89,12 @@ src/rocprof_compute_soc/analysis_configs/gfx940/1600_vector_l1_data_cache.yaml:
|
||||
src/rocprof_compute_soc/analysis_configs/gfx941/1600_vector_l1_data_cache.yaml: 37c061bc9751828621a72aa6576596262b684fca7b764adbb991cd7eef58987d
|
||||
src/rocprof_compute_soc/analysis_configs/gfx942/1600_vector_l1_data_cache.yaml: 37c061bc9751828621a72aa6576596262b684fca7b764adbb991cd7eef58987d
|
||||
src/rocprof_compute_soc/analysis_configs/gfx950/1600_vector_l1_data_cache.yaml: ae0388f43813302969f51a80ac58678614b993f5163083a69e1c99811d730064
|
||||
src/rocprof_compute_soc/analysis_configs/gfx908/1700_l2_cache.yaml: 54ff1df4ee08206d0aa4ff9cd9f0b20cbaa3866aecb9b40a0ac5969e9e25ed20
|
||||
src/rocprof_compute_soc/analysis_configs/gfx90a/1700_l2_cache.yaml: ee87b5b6cdaca98de6e5cb0d06e2e092470e0e25aac1498f8abcfc8421932ae6
|
||||
src/rocprof_compute_soc/analysis_configs/gfx940/1700_l2_cache.yaml: 78f9fee5dafc83d311da1c801200c1820e16a0678dd0548fafa8a966ec6a94d5
|
||||
src/rocprof_compute_soc/analysis_configs/gfx941/1700_l2_cache.yaml: 51fe6e3888975b805594c2ab2b3147e717ae5e015468ee592cbcddc389c689bc
|
||||
src/rocprof_compute_soc/analysis_configs/gfx942/1700_l2_cache.yaml: dc2dc9ff61b1747e492c28ef5ac76764fd75c18fd0827834130bc583f2afc619
|
||||
src/rocprof_compute_soc/analysis_configs/gfx950/1700_l2_cache.yaml: d181f753c3fff608c72b8015d1af30bfd8cf8cdfbc0a17c505f717ddaa3b1efc
|
||||
src/rocprof_compute_soc/analysis_configs/gfx908/1700_l2_cache.yaml: 1991d3ec4bf1d534d32f35ffea23ebce3fe30d6114b48171acb5a8bc4446828f
|
||||
src/rocprof_compute_soc/analysis_configs/gfx90a/1700_l2_cache.yaml: d95bc3ecf5405a3687202c3ce29230838fa872bb3df04ff4e45d8e67822409af
|
||||
src/rocprof_compute_soc/analysis_configs/gfx940/1700_l2_cache.yaml: 89501317ffae421ce2ef272894c798274488fef68d12657143415dd8514be383
|
||||
src/rocprof_compute_soc/analysis_configs/gfx941/1700_l2_cache.yaml: ad882ce0748402eb6080528c583046014665e9a4436c7a26784fb11961320b02
|
||||
src/rocprof_compute_soc/analysis_configs/gfx942/1700_l2_cache.yaml: 8544fefbaf4a6885feecc43557e8efb31c2f79b9c5e7fd2d1e6be59951cd51dc
|
||||
src/rocprof_compute_soc/analysis_configs/gfx950/1700_l2_cache.yaml: b8d83bd17c09939240c01d598cd2f8961a6e3f3545663725737b2566d6544735
|
||||
src/rocprof_compute_soc/analysis_configs/gfx908/1800_l2_cache_per_channel.yaml: f5db15673a4be8b92f05a380738c5a10f68ca78ca2b1a9c31c19acae13d17f7b
|
||||
src/rocprof_compute_soc/analysis_configs/gfx90a/1800_l2_cache_per_channel.yaml: a0c53202fe9f68d5e1fa689ce0643c471ced7d47e007d8ccc68fba294f7f6a05
|
||||
src/rocprof_compute_soc/analysis_configs/gfx940/1800_l2_cache_per_channel.yaml: e184e3692eb0d641fb2e37fada0e58a6c4958553931d7c038b884e1e6986093f
|
||||
|
||||
@@ -15559,9 +15559,9 @@ panels:
|
||||
max: MAX((MAX((TCC_EA_RDREQ_sum - TCC_EA_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA_WRREQ_sum - TCC_EA_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA_WR_UNCACHED_32B_sum / $denom))
|
||||
@@ -15615,9 +15615,9 @@ panels:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
@@ -15671,9 +15671,9 @@ panels:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
@@ -15707,12 +15707,12 @@ panels:
|
||||
max: MAX((TCC_EA0_RDREQ_32B_sum / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Read (64B):
|
||||
avg: AVG(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum)
|
||||
/ $denom))
|
||||
min: MIN(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum)
|
||||
/ $denom))
|
||||
max: MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum)
|
||||
/ $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum) /
|
||||
$denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum) /
|
||||
$denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_RDREQ_sum - TCC_BUBBLE_sum - TCC_EA0_RDREQ_32B_sum) /
|
||||
$denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Read (128B):
|
||||
avg: AVG(((TCC_BUBBLE_sum) / $denom))
|
||||
@@ -15735,9 +15735,9 @@ panels:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
@@ -15811,9 +15811,9 @@ panels:
|
||||
max: MAX(TCC_EA0_RDREQ_DRAM_32B_sum * 32/ (End_Timestamp - Start_Timestamp))
|
||||
unit: Gbps
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
@@ -15902,9 +15902,9 @@ panels:
|
||||
max: MAX((MAX((TCC_EA0_RDREQ_sum - TCC_EA0_RDREQ_DRAM_sum), 0) / $denom))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (32B):
|
||||
avg: AVG(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
min: MIN(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
max: MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom))
|
||||
avg: AVG(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
min: MIN(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
max: MAX(MAX(((TCC_EA0_WRREQ_sum - TCC_EA0_WRREQ_64B_sum) / $denom), 0))
|
||||
unit: (Req + $normUnit)
|
||||
Write and Atomic (Uncached):
|
||||
avg: AVG((TCC_EA0_WR_UNCACHED_32B_sum / $denom))
|
||||
|
||||
Αναφορά σε νέο ζήτημα
Block a user