add gfx12 for counter collection tests (#108)

* add gfx12 for counter def.

* Update continuous_integration.yml

* Update counter_defs.yaml

* commenting logging.

* Update ioctl.cpp

* add gfx12 to tests

* Update ioctl.cpp

* Add description to GFX12 GL2C_EA_RDREQ counter

* Updates from editor

---------

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
Co-authored-by: Kuricheti, Mythreya <Mythreya.Kuricheti@amd.com>

[ROCm/rocprofiler-sdk commit: 121901c321]

projects/rocprofiler-sdk/.github/workflows/continuous_integration.yml

@@ -21,7 +21,7 @@ concurrency:
 env:
   # TODO(jrmadsen): replace LD_RUNPATH_FLAG, GPU_TARGETS, etc. with internal handling in cmake
   ROCM_PATH: "/opt/rocm"
-  GPU_TARGETS: "gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1100 gfx1101 gfx1102"
+  GPU_TARGETS: "gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1100 gfx1101 gfx1102 gfx1201"
   PATH: "/usr/bin:$PATH"
   navi3_EXCLUDE_TESTS_REGEX: "^(test-page-migration-(execute|validate))$"
   vega20_EXCLUDE_TESTS_REGEX: "^(test-page-migration-(execute|validate))$"
@@ -44,7 +44,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        runner: ['vega20', 'mi300a']
+        runner: ['navi4', 'mi300a']
         os: ['ubuntu-22.04']
         build-type: ['RelWithDebInfo']
         ci-flags: ['--linter clang-tidy']

projects/rocprofiler-sdk/source/lib/rocprofiler-sdk/counters/tests/core.cpp

@@ -755,7 +755,7 @@ TEST(core, check_load_counter_def_append)
     const std::string test_yaml = R"(
 TEST_YAML_LOAD:
   architectures:
-    gfx942/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx908/gfx90a/gfx9:
+    gfx942/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx908/gfx90a/gfx9/gfx12/gfx1200/gfx1201:
       expression: reduce(GRBM_GUI_ACTIVE,max)*CU_NUM
   description: 'Unit: cycles'
     )";
@@ -782,13 +782,13 @@ TEST(core, check_load_counter_def)
     const std::string test_yaml = R"(
 GRBM_GUI_ACTIVE:
   architectures:
-    gfx942/gfx941/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx940/gfx908/gfx900/gfx90a/gfx9:
+    gfx942/gfx941/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx940/gfx908/gfx900/gfx90a/gfx9/gfx12/gfx1200/gfx1201:
       block: GRBM
       event: 2
   description: The GUI is Active
 TEST_YAML_LOAD:
   architectures:
-    gfx942/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx908/gfx90a/gfx9:
+    gfx942/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx908/gfx90a/gfx9/gfx12/gfx1200/gfx1201:
       expression: reduce(GRBM_GUI_ACTIVE,max)
   description: cycles
     )";

projects/rocprofiler-sdk/source/lib/rocprofiler-sdk/counters/yaml/counter_defs.yaml

@@ -134,7 +134,7 @@ CP_UTIL:
     blocks are busy
 CU_NUM:
   architectures:
-    gfx942/gfx941/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx940/gfx908/gfx900/gfx90a/gfx9:
+    gfx942/gfx941/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx940/gfx908/gfx900/gfx90a/gfx9/gfx12/gfx1200/gfx1201:
       expression: simd_count/simd_per_cu
   description: CU_NUM
 SIMD_NUM:
@@ -263,6 +263,7 @@ GL2C_EA_RDREQ:
     gfx12/gfx1200/gfx1201:
       block: GL2C
       event: 140
+  description: Number of GL2C/EA read requests (either 32-byte or 64-byte or 128-byte) for all clients.
 GL2C_EA_RDREQ_sum:
   architectures:
     gfx12/gfx1200/gfx1201:
@@ -327,6 +328,7 @@ GL2C_EA_WRREQ:
     gfx12/gfx1200/gfx1201:
       block: GL2C
       event: 108
+  description: Number of transactions (all sizes) going over the GL2C_EA_WRREQ interface for all clients. This does not include probe commands.
 GL2C_EA_WRREQ_sum:
   architectures:
     gfx12/gfx1200/gfx1201:
@@ -338,6 +340,7 @@ GL2C_EA_WRREQ_STALL:
     gfx12/gfx1200/gfx1201:
       block: GL2C
       event: 122
+  description: Number of cycles a write request was stalled.
 GL2C_EA_WRREQ_STALL_max:
   architectures:
     gfx12/gfx1200/gfx1201:
@@ -2122,7 +2125,7 @@ SQ_WAVES_SAVED:
     space). Returns one value per-SE (aggregates of SIMD values).
 SQ_WAVES_sum:
   architectures:
-    gfx942/gfx941/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx940/gfx908/gfx90a/gfx9/gfx900:
+    gfx942/gfx941/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx940/gfx908/gfx90a/gfx9/gfx900/gfx12/gfx1200/gfx1201:
       expression: reduce(SQ_WAVES,sum)
   description: Gives the total number of waves currently enqueued by the application during the collection
     timeframe (for dispatch profiling this is the timeframe of kernel execution, for agent profiling it

projects/rocprofiler-sdk/tests/rocprofv3/counter-collection/extra_counters/extra_counters.yaml

@@ -1,5 +1,5 @@
 TEST_YAML_LOAD:
   architectures:
-    gfx942/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx908/gfx90a/gfx9:
+    gfx942/gfx10/gfx1010/gfx1030/gfx1031/gfx11/gfx1032/gfx1102/gfx906/gfx1100/gfx1101/gfx908/gfx90a/gfx9/gfx12/gfx1200/gfx1201:
       expression: reduce(GRBM_GUI_ACTIVE,max)*CU_NUM
   description: 'Unit: cycles'