Cuda Component Refactor

src/components/cuda/README_internal.md

@@ -0,0 +1,38 @@
+# Cuda Component Native Events in PAPI
+
+At current the Cuda component uses bits to create an Event identifier. The following internal README will be used to breakdown the encoding format.
+
+
+# Event Identifier Encoding Format
+
+## Unused bits
+As of 04/30/24, there are a total of 34 unused bits. These bits can be used to create a new qualifier or can be used to extended the number of bits for an existing qualifier.
+
+## Device
+7 bits are allocated for the device which accounts for 128 total devices on a node (e.g. [0 - 127 devices]).
+
+## Qlmask
+2 bits are allocated for the qualifier mask. 
+
+## Nameid
+21 bits are allocated for the nameid which will roughly account for greater than 2 million Cuda native events per device on a node.
+
+## Calculations for Bit Masks and Shifts
+| #DEFINE    | Bits |
+| -------- | ------- |
+| EVENTS_WIDTH  | `(sizeof(uint64_t) * 8)`    |
+| DEVICE_WIDTH | `( 7)`   |
+| QLMASK_WIDTH    | `( 2)`   |
+| NAMEID_WIDTH  | `(21)`    |
+| DEVICE_WIDTH | `( 7)`   |
+| UNUSED_WIDTH   | `(EVENTS_WIDTH - DEVICE_WIDTH - QLMASK_WIDTH - NAMEID_WIDTH)`   |
+| DEVICE_SHIFT  | `(EVENTS_WIDTH - UNUSED_WIDTH - DEVICE_WIDTH)`    |
+| QLMASK_SHIFT | `(DEVICE_SHIFT - QLMASK_WIDTH)`   |
+| NAMEID_SHIFT    | `(QLMASK_SHIFT - NAMEID_WIDTH)`   |
+| DEVICE_MASK  | `((0xFFFFFFFFFFFFFFFF >> (EVENTS_WIDTH - DEVICE_WIDTH)) << DEVICE_SHIFT)`    |
+| QLMASK_MASK | `((0xFFFFFFFFFFFFFFFF >> (EVENTS_WIDTH - QLMASK_WIDTH)) << QLMASK_SHIFT)`   |
+| NAMEID_MASK   | `((0xFFFFFFFFFFFFFFFF >> (EVENTS_WIDTH - NAMEID_WIDTH)) << NAMEID_SHIFT)`   |
+| DEVICE_FLAG  | `DEVICE_FLAG  (0x2)`   |
+
+
+**NOTE**: If adding a new qualifier, you must add it to the above [Calculations for Bit Masks and Shifts](#calculations-for-bit-masks-and-shifts) section and account for this addition within `cupti_profiler.c`. 

src/components/cuda/cupti_common.c

@@ -656,3 +656,30 @@ int cuptic_device_release(cuptiu_event_table_t *evt_table)
     _papi_hwi_unlock(_cuda_lock);
     return PAPI_OK;
 }
+
+/** @class cuptiu_dev_set
+  * @brief For a Cuda native event, set the device ID.
+  *
+  * @param *bitmap
+  *   Device map.
+  * @param i
+  *   Device ID.
+*/
+int cuptiu_dev_set(cuptiu_bitmap_t *bitmap, int i)
+{
+    *bitmap |= (1ULL << i);
+    return PAPI_OK;
+}
+
+/** @class cuptiu_dev_check
+  * @brief For a Cuda native event, check for a valid device ID.
+  *
+  * @param *bitmap
+  *   Device map.
+  * @param i
+  *   Device ID.
+*/
+int cuptiu_dev_check(cuptiu_bitmap_t bitmap, int i)
+{
+    return (bitmap & (1ULL << i));
+}

src/components/cuda/cupti_common.h

@@ -107,4 +107,8 @@ int cuptic_ctxarr_destroy(cuptic_info_t *pinfo);
 int cuptic_device_acquire(cuptiu_event_table_t *evt_table);
 int cuptic_device_release(cuptiu_event_table_t *evt_table);
 
+/* functions to handle device qualifiers */
+int cuptiu_dev_set(cuptiu_bitmap_t *bitmap, int i);
+int cuptiu_dev_check(cuptiu_bitmap_t bitmap, int i);
+
 #endif /* __CUPTI_COMMON_H__ */

src/components/cuda/cupti_dispatch.c

@@ -201,42 +201,59 @@ int cuptid_control_reset(cuptid_ctl_t cupti_ctl)
     return PAPI_ECMP;
 }
 
-int cuptid_event_enum(cuptiu_event_table_t *all_evt_names)
+int cuptid_evt_enum(uint64_t *event_code, int modifier)
 {
     if (cuptic_is_runtime_perfworks_api()) {
 
 #if defined(API_PERFWORKS)
-        return cuptip_event_enum(all_evt_names);
+        return cuptip_evt_enum(event_code, modifier);
 #endif
 
     } else if (cuptic_is_runtime_events_api()) {
 
 #if defined(API_EVENTS)
-        return cuptie_event_enum(all_evt_names);
+        return cuptie_evt_enum(event_code, modifier);
 #endif
 
     }
     return PAPI_ECMP;
 }
 
-int cuptid_event_name_to_descr(char *evt_name, char *descr)
+int cuptid_evt_code_to_descr(uint64_t event_code, char *descr, int len)
 {
     if (cuptic_is_runtime_perfworks_api()) {
-
 #if defined(API_PERFWORKS)
-        return cuptip_event_name_to_descr(evt_name, descr);
+        return cuptip_evt_code_to_descr(event_code, descr, len);
 #endif
-
-    } else if (cuptic_is_runtime_events_api()) {
-
+    } 
+    else if (cuptic_is_runtime_events_api()) {
 #if defined(API_EVENTS)
-        return cuptie_event_name_to_descr(evt_name, descr);
+        return cuptie_event_code_to_descr(event_code, descr, len);
 #endif
-
     }
     return PAPI_ECMP;
 }
 
+int cuptid_evt_code_to_info(uint64_t event_code, PAPI_event_info_t *info)
+{
+    return cuptip_evt_code_to_info(event_code, info);
+}
+
+int cuptid_evt_code_to_name(uint64_t event_code, char *name, int len)
+{
+    return cuptip_evt_code_to_name(event_code, name, len);
+}
+
+int cuptid_evt_name_to_code(const char *name, uint64_t *event_code)
+{
+    return cuptip_evt_name_to_code(name, event_code);
+}
+
+int cuptid_get_num_qualified_evts(int *count, uint64_t event_code)
+{
+    return cuptip_get_num_qualified_evts(count, event_code);
+}
+
 void cuptid_event_table_destroy(ntv_event_table_t *evt_table)
 {
     cuptiu_event_table_destroy(evt_table);

src/components/cuda/cupti_dispatch.h

@@ -27,8 +27,12 @@ int cuptid_control_start(cuptid_ctl_t ctl);
 int cuptid_control_stop(cuptid_ctl_t ctl);
 int cuptid_control_read(cuptid_ctl_t ctl, long long *values);
 int cuptid_control_reset(cuptid_ctl_t ctl);
-int cuptid_event_enum(ntv_event_table_t all_evt_names);
-int cuptid_event_name_to_descr(char *evt_name, char *descr);
+
+int cuptid_evt_enum(uint64_t *event_code, int modifier);
+int cuptid_evt_code_to_descr(uint64_t event_code, char *descr, int len);
+int cuptid_evt_code_to_info(uint64_t event_code, PAPI_event_info_t *info);
+int cuptid_evt_code_to_name(uint64_t event_code, char *name, int len);
+int cuptid_evt_name_to_code(const char *name, uint64_t *event_code);
 
 void cuptid_event_table_destroy(ntv_event_table_t *evt_table);
 int cuptid_event_table_create(ntv_event_table_t *evt_table);
@@ -37,4 +41,5 @@ int cuptid_event_table_find_name(ntv_event_table_t evt_table, const char *evt_na
 int cuptid_event_table_insert_record(ntv_event_table_t evt_table, const char *evt_name, unsigned int evt_code, int evt_pos);
 int cuptid_event_table_get_item(ntv_event_table_t evt_table, unsigned int evt_idx, ntv_event_t *record);
 
+int cuptid_get_num_qualified_evts(int *count, uint64_t event_code);
 #endif /* __CUPTI_DISPATCH_H__ */

src/components/cuda/cupti_events.c

@@ -50,13 +50,12 @@ int cuptie_control_reset(cuptie_control_t ctl)
     return PAPI_ENOIMPL;
 }
 
-int cuptie_event_enum(cuptiu_event_table_t *all_evt_names)
+int cuptie_evt_enum(uint64_t *event_code, int modifier)
 {
     return PAPI_ENOIMPL;
 }
 
-int cuptie_event_name_to_descr(const char *evt_name, char *description)
-{
+int cuptie_event_code_to_descr(uint64_t event_code, char *descr, int len) {
     return PAPI_ENOIMPL;
 }
 

src/components/cuda/cupti_events.h

@@ -9,6 +9,8 @@
 
 #include "cupti_utils.h"
 
+#include <stdint.h>
+
 typedef void *cuptie_control_t;
 
 int cuptie_init(void);
@@ -18,8 +20,8 @@ int cuptie_control_start(cuptie_control_t ctl);
 int cuptie_control_stop(cuptie_control_t ctl);
 int cuptie_control_read(cuptie_control_t ctl, long long *values);
 int cuptie_control_reset(cuptie_control_t ctl);
-int cuptie_event_enum(cuptiu_event_table_t *all_evt_names);
-int cuptie_event_name_to_descr(const char *evt_name, char *description);
+int cuptie_evt_enum(uint64_t *event_code, int modifier);
+int cuptie_event_code_to_descr(uint64_t event_code, char *descr, int len);
 int cuptie_shutdown(void);
 
 #endif  /* __CUPTI_EVENTS_H__ */