OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

intel/perf: move initialization of pipeline statistics metrics to gen_perf

Browse Source 
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This commit is contained in:
Mark Janes
2019-08-02 17:17:54 -07:00
parent 9f84efb452
commit 9f5c160d82
3 changed files with 222 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files

280
src/intel/perf/gen_perf.c
View File

@@ -61,6 +61,11 @@
#define GEN9_RPSTAT0_PREV_GT_FREQ_SHIFT 0
#define GEN9_RPSTAT0_PREV_GT_FREQ_MASK INTEL_MASK(8, 0)
#define GEN6_SO_PRIM_STORAGE_NEEDED 0x2280
#define GEN7_SO_PRIM_STORAGE_NEEDED(n) (0x5240 + (n) * 8)
#define GEN6_SO_NUM_PRIMS_WRITTEN 0x2288
#define GEN7_SO_NUM_PRIMS_WRITTEN(n) (0x5200 + (n) * 8)
#define MAP_READ (1 << 0)
#define MAP_WRITE (1 << 1)
@@ -165,13 +170,32 @@ read_sysfs_drm_device_file_uint64(struct gen_perf_config *perf,
return read_file_uint64(buf, value);
}
static inline struct gen_perf_query_info *
append_query_info(struct gen_perf_config *perf, int max_counters)
{
struct gen_perf_query_info *query;
perf->queries = reralloc(perf, perf->queries,
struct gen_perf_query_info,
++perf->n_queries);
query = &perf->queries[perf->n_queries - 1];
memset(query, 0, sizeof(*query));
if (max_counters > 0) {
query->max_counters = max_counters;
query->counters =
rzalloc_array(perf, struct gen_perf_query_counter, max_counters);
}
return query;
}
static void
register_oa_config(struct gen_perf_config *perf,
const struct gen_perf_query_info *query,
uint64_t config_id)
{
struct gen_perf_query_info *registred_query =
gen_perf_query_append_query_info(perf, 0);
struct gen_perf_query_info *registred_query = append_query_info(perf, 0);
*registred_query = *query;
registred_query->oa_metrics_set_id = config_id;
@@ -395,8 +419,123 @@ get_register_queries_function(const struct gen_device_info *devinfo)
return NULL;
}
bool
gen_perf_load_oa_metrics(struct gen_perf_config *perf, int fd,
static inline void
add_stat_reg(struct gen_perf_query_info *query, uint32_t reg,
uint32_t numerator, uint32_t denominator,
const char *name, const char *description)
{
struct gen_perf_query_counter *counter;
assert(query->n_counters < query->max_counters);
counter = &query->counters[query->n_counters];
counter->name = name;
counter->desc = description;
counter->type = GEN_PERF_COUNTER_TYPE_RAW;
counter->data_type = GEN_PERF_COUNTER_DATA_TYPE_UINT64;
counter->offset = sizeof(uint64_t) * query->n_counters;
counter->pipeline_stat.reg = reg;
counter->pipeline_stat.numerator = numerator;
counter->pipeline_stat.denominator = denominator;
query->n_counters++;
}
static inline void
add_basic_stat_reg(struct gen_perf_query_info *query,
uint32_t reg, const char *name)
{
add_stat_reg(query, reg, 1, 1, name, name);
}
static void
load_pipeline_statistic_metrics(struct gen_perf_config *perf_cfg,
const struct gen_device_info *devinfo)
{
struct gen_perf_query_info *query =
append_query_info(perf_cfg, MAX_STAT_COUNTERS);
query->kind = GEN_PERF_QUERY_TYPE_PIPELINE;
query->name = "Pipeline Statistics Registers";
add_basic_stat_reg(query, IA_VERTICES_COUNT,
"N vertices submitted");
add_basic_stat_reg(query, IA_PRIMITIVES_COUNT,
"N primitives submitted");
add_basic_stat_reg(query, VS_INVOCATION_COUNT,
"N vertex shader invocations");
if (devinfo->gen == 6) {
add_stat_reg(query, GEN6_SO_PRIM_STORAGE_NEEDED, 1, 1,
"SO_PRIM_STORAGE_NEEDED",
"N geometry shader stream-out primitives (total)");
add_stat_reg(query, GEN6_SO_NUM_PRIMS_WRITTEN, 1, 1,
"SO_NUM_PRIMS_WRITTEN",
"N geometry shader stream-out primitives (written)");
} else {
add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(0), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 0)",
"N stream-out (stream 0) primitives (total)");
add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(1), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 1)",
"N stream-out (stream 1) primitives (total)");
add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(2), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 2)",
"N stream-out (stream 2) primitives (total)");
add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(3), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 3)",
"N stream-out (stream 3) primitives (total)");
add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(0), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 0)",
"N stream-out (stream 0) primitives (written)");
add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(1), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 1)",
"N stream-out (stream 1) primitives (written)");
add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(2), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 2)",
"N stream-out (stream 2) primitives (written)");
add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(3), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 3)",
"N stream-out (stream 3) primitives (written)");
}
add_basic_stat_reg(query, HS_INVOCATION_COUNT,
"N TCS shader invocations");
add_basic_stat_reg(query, DS_INVOCATION_COUNT,
"N TES shader invocations");
add_basic_stat_reg(query, GS_INVOCATION_COUNT,
"N geometry shader invocations");
add_basic_stat_reg(query, GS_PRIMITIVES_COUNT,
"N geometry shader primitives emitted");
add_basic_stat_reg(query, CL_INVOCATION_COUNT,
"N primitives entering clipping");
add_basic_stat_reg(query, CL_PRIMITIVES_COUNT,
"N primitives leaving clipping");
if (devinfo->is_haswell || devinfo->gen == 8) {
add_stat_reg(query, PS_INVOCATION_COUNT, 1, 4,
"N fragment shader invocations",
"N fragment shader invocations");
} else {
add_basic_stat_reg(query, PS_INVOCATION_COUNT,
"N fragment shader invocations");
}
add_basic_stat_reg(query, PS_DEPTH_COUNT,
"N z-pass fragments");
if (devinfo->gen >= 7) {
add_basic_stat_reg(query, CS_INVOCATION_COUNT,
"N compute shader invocations");
}
query->data_size = sizeof(uint64_t) * query->n_counters;
}
static bool
load_oa_metrics(struct gen_perf_config *perf, int fd,
const struct gen_device_info *devinfo)
{
perf_register_oa_queries_t oa_register = get_register_queries_function(devinfo);
@@ -582,6 +721,62 @@ gen_perf_query_result_clear(struct gen_perf_query_result *result)
result->hw_id = 0xffffffff; /* invalid */
}
static void
gen_perf_query_register_mdapi_statistic_query(struct gen_perf_config *perf_cfg,
const struct gen_device_info *devinfo)
{
if (!(devinfo->gen >= 7 && devinfo->gen <= 11))
return;
struct gen_perf_query_info *query =
append_query_info(perf_cfg, MAX_STAT_COUNTERS);
query->kind = GEN_PERF_QUERY_TYPE_PIPELINE;
query->name = "Intel_Raw_Pipeline_Statistics_Query";
/* The order has to match mdapi_pipeline_metrics. */
add_basic_stat_reg(query, IA_VERTICES_COUNT,
"N vertices submitted");
add_basic_stat_reg(query, IA_PRIMITIVES_COUNT,
"N primitives submitted");
add_basic_stat_reg(query, VS_INVOCATION_COUNT,
"N vertex shader invocations");
add_basic_stat_reg(query, GS_INVOCATION_COUNT,
"N geometry shader invocations");
add_basic_stat_reg(query, GS_PRIMITIVES_COUNT,
"N geometry shader primitives emitted");
add_basic_stat_reg(query, CL_INVOCATION_COUNT,
"N primitives entering clipping");
add_basic_stat_reg(query, CL_PRIMITIVES_COUNT,
"N primitives leaving clipping");
if (devinfo->is_haswell || devinfo->gen == 8) {
add_stat_reg(query, PS_INVOCATION_COUNT, 1, 4,
"N fragment shader invocations",
"N fragment shader invocations");
} else {
add_basic_stat_reg(query, PS_INVOCATION_COUNT,
"N fragment shader invocations");
}
add_basic_stat_reg(query, HS_INVOCATION_COUNT,
"N TCS shader invocations");
add_basic_stat_reg(query, DS_INVOCATION_COUNT,
"N TES shader invocations");
if (devinfo->gen >= 7) {
add_basic_stat_reg(query, CS_INVOCATION_COUNT,
"N compute shader invocations");
}
if (devinfo->gen >= 10) {
/* Reuse existing CS invocation register until we can expose this new
* one.
*/
add_basic_stat_reg(query, CS_INVOCATION_COUNT,
"Reserved1");
}
query->data_size = sizeof(uint64_t) * query->n_counters;
}
static void
fill_mdapi_perf_query_counter(struct gen_perf_query_info *query,
const char *name,
@@ -618,8 +813,8 @@ fill_mdapi_perf_query_counter(struct gen_perf_query_info *query,
sizeof(struct_name.field_name[0]), \
GEN_PERF_COUNTER_DATA_TYPE_##type_name)
void
gen_perf_query_register_mdapi_oa_query(const struct gen_device_info *devinfo,
static void
register_mdapi_oa_query(const struct gen_device_info *devinfo,
struct gen_perf_config *perf)
{
struct gen_perf_query_info *query = NULL;
@@ -632,7 +827,7 @@ gen_perf_query_register_mdapi_oa_query(const struct gen_device_info *devinfo,
switch (devinfo->gen) {
case 7: {
query = gen_perf_query_append_query_info(perf, 1 + 45 + 16 + 7);
query = append_query_info(perf, 1 + 45 + 16 + 7);
query->oa_format = I915_OA_FORMAT_A45_B8_C8;
struct gen7_mdapi_metrics metric_data;
@@ -657,7 +852,7 @@ gen_perf_query_register_mdapi_oa_query(const struct gen_device_info *devinfo,
break;
}
case 8: {
query = gen_perf_query_append_query_info(perf, 2 + 36 + 16 + 16);
query = append_query_info(perf, 2 + 36 + 16 + 16);
query->oa_format = I915_OA_FORMAT_A32u40_A4u32_B8_C8;
struct gen8_mdapi_metrics metric_data;
@@ -694,7 +889,7 @@ gen_perf_query_register_mdapi_oa_query(const struct gen_device_info *devinfo,
case 9:
case 10:
case 11: {
query = gen_perf_query_append_query_info(perf, 2 + 36 + 16 + 16 + 16 + 2);
query = append_query_info(perf, 2 + 36 + 16 + 16 + 16 + 2);
query->oa_format = I915_OA_FORMAT_A32u40_A4u32_B8_C8;
struct gen9_mdapi_metrics metric_data;
@@ -756,62 +951,6 @@ gen_perf_query_register_mdapi_oa_query(const struct gen_device_info *devinfo,
}
}
void
gen_perf_query_register_mdapi_statistic_query(const struct gen_device_info *devinfo,
struct gen_perf_config *perf)
{
if (!(devinfo->gen >= 7 && devinfo->gen <= 11))
return;
struct gen_perf_query_info *query =
gen_perf_query_append_query_info(perf, MAX_STAT_COUNTERS);
query->kind = GEN_PERF_QUERY_TYPE_PIPELINE;
query->name = "Intel_Raw_Pipeline_Statistics_Query";
/* The order has to match mdapi_pipeline_metrics. */
gen_perf_query_info_add_basic_stat_reg(query, IA_VERTICES_COUNT,
"N vertices submitted");
gen_perf_query_info_add_basic_stat_reg(query, IA_PRIMITIVES_COUNT,
"N primitives submitted");
gen_perf_query_info_add_basic_stat_reg(query, VS_INVOCATION_COUNT,
"N vertex shader invocations");
gen_perf_query_info_add_basic_stat_reg(query, GS_INVOCATION_COUNT,
"N geometry shader invocations");
gen_perf_query_info_add_basic_stat_reg(query, GS_PRIMITIVES_COUNT,
"N geometry shader primitives emitted");
gen_perf_query_info_add_basic_stat_reg(query, CL_INVOCATION_COUNT,
"N primitives entering clipping");
gen_perf_query_info_add_basic_stat_reg(query, CL_PRIMITIVES_COUNT,
"N primitives leaving clipping");
if (devinfo->is_haswell || devinfo->gen == 8) {
gen_perf_query_info_add_stat_reg(query, PS_INVOCATION_COUNT, 1, 4,
"N fragment shader invocations",
"N fragment shader invocations");
} else {
gen_perf_query_info_add_basic_stat_reg(query, PS_INVOCATION_COUNT,
"N fragment shader invocations");
}
gen_perf_query_info_add_basic_stat_reg(query, HS_INVOCATION_COUNT,
"N TCS shader invocations");
gen_perf_query_info_add_basic_stat_reg(query, DS_INVOCATION_COUNT,
"N TES shader invocations");
if (devinfo->gen >= 7) {
gen_perf_query_info_add_basic_stat_reg(query, CS_INVOCATION_COUNT,
"N compute shader invocations");
}
if (devinfo->gen >= 10) {
/* Reuse existing CS invocation register until we can expose this new
* one.
*/
gen_perf_query_info_add_basic_stat_reg(query, CS_INVOCATION_COUNT,
"Reserved1");
}
query->data_size = sizeof(uint64_t) * query->n_counters;
}
uint64_t
gen_perf_query_get_metric_id(struct gen_perf_config *perf,
const struct gen_perf_query_info *query)
@@ -1011,6 +1150,17 @@ gen_perf_dec_n_users(struct gen_perf_context *perf_ctx)
}
}
void
gen_perf_init_metrics(struct gen_perf_config *perf_cfg,
const struct gen_device_info *devinfo,
int drm_fd)
{
load_pipeline_statistic_metrics(perf_cfg, devinfo);
gen_perf_query_register_mdapi_statistic_query(perf_cfg, devinfo);
if (load_oa_metrics(perf_cfg, drm_fd, devinfo))
register_mdapi_oa_query(devinfo, perf_cfg);
}
void
gen_perf_init_context(struct gen_perf_context *perf_ctx,
struct gen_perf_config *perf_cfg,

61
src/intel/perf/gen_perf.h
View File

@@ -505,6 +505,9 @@ struct gen_perf_context {
int n_query_instances;
};
void gen_perf_init_metrics(struct gen_perf_config *perf_cfg,
const struct gen_device_info *devinfo,
int drm_fd);
void gen_perf_init_context(struct gen_perf_context *perf_ctx,
struct gen_perf_config *perf_cfg,
void * ctx, /* driver context (eg, brw_context) */
@@ -532,58 +535,6 @@ gen_perf_query_counter_get_size(const struct gen_perf_query_counter *counter)
}
}
static inline struct gen_perf_query_info *
gen_perf_query_append_query_info(struct gen_perf_config *perf, int max_counters)
{
struct gen_perf_query_info *query;
perf->queries = reralloc(perf, perf->queries,
struct gen_perf_query_info,
++perf->n_queries);
query = &perf->queries[perf->n_queries - 1];
memset(query, 0, sizeof(*query));
if (max_counters > 0) {
query->max_counters = max_counters;
query->counters =
rzalloc_array(perf, struct gen_perf_query_counter, max_counters);
}
return query;
}
static inline void
gen_perf_query_info_add_stat_reg(struct gen_perf_query_info *query,
uint32_t reg,
uint32_t numerator,
uint32_t denominator,
const char *name,
const char *description)
{
struct gen_perf_query_counter *counter;
assert(query->n_counters < query->max_counters);
counter = &query->counters[query->n_counters];
counter->name = name;
counter->desc = description;
counter->type = GEN_PERF_COUNTER_TYPE_RAW;
counter->data_type = GEN_PERF_COUNTER_DATA_TYPE_UINT64;
counter->offset = sizeof(uint64_t) * query->n_counters;
counter->pipeline_stat.reg = reg;
counter->pipeline_stat.numerator = numerator;
counter->pipeline_stat.denominator = denominator;
query->n_counters++;
}
static inline void
gen_perf_query_info_add_basic_stat_reg(struct gen_perf_query_info *query,
uint32_t reg, const char *name)
{
gen_perf_query_info_add_stat_reg(query, reg, 1, 1, name, name);
}
static inline struct gen_perf_config *
gen_perf_new(void *ctx)
{
@@ -591,8 +542,6 @@ gen_perf_new(void *ctx)
return perf;
}
bool gen_perf_load_oa_metrics(struct gen_perf_config *perf, int fd,
const struct gen_device_info *devinfo);
bool gen_perf_load_metric_id(struct gen_perf_config *perf, const char *guid,
uint64_t *metric_id);
@@ -605,10 +554,6 @@ void gen_perf_query_result_accumulate(struct gen_perf_query_result *result,
const uint32_t *start,
const uint32_t *end);
void gen_perf_query_result_clear(struct gen_perf_query_result *result);
void gen_perf_query_register_mdapi_statistic_query(const struct gen_device_info *devinfo,
struct gen_perf_config *perf);
void gen_perf_query_register_mdapi_oa_query(const struct gen_device_info *devinfo,
struct gen_perf_config *perf);
uint64_t gen_perf_query_get_metric_id(struct gen_perf_config *perf,
const struct gen_perf_query_info *query);
struct oa_sample_buf * gen_perf_get_free_sample_buf(struct gen_perf_context *perf);

96
src/mesa/drivers/dri/i965/brw_performance_query.c
View File

@@ -420,94 +420,6 @@ brw_delete_perf_query(struct gl_context *ctx,
}
/******************************************************************************/
static void
init_pipeline_statistic_query_registers(struct brw_context *brw)
{
const struct gen_device_info *devinfo = &brw->screen->devinfo;
struct gen_perf_config *perf = brw->perf_ctx.perf;
struct gen_perf_query_info *query =
gen_perf_query_append_query_info(perf, MAX_STAT_COUNTERS);
query->kind = GEN_PERF_QUERY_TYPE_PIPELINE;
query->name = "Pipeline Statistics Registers";
gen_perf_query_info_add_basic_stat_reg(query, IA_VERTICES_COUNT,
"N vertices submitted");
gen_perf_query_info_add_basic_stat_reg(query, IA_PRIMITIVES_COUNT,
"N primitives submitted");
gen_perf_query_info_add_basic_stat_reg(query, VS_INVOCATION_COUNT,
"N vertex shader invocations");
if (devinfo->gen == 6) {
gen_perf_query_info_add_stat_reg(query, GEN6_SO_PRIM_STORAGE_NEEDED, 1, 1,
"SO_PRIM_STORAGE_NEEDED",
"N geometry shader stream-out primitives (total)");
gen_perf_query_info_add_stat_reg(query, GEN6_SO_NUM_PRIMS_WRITTEN, 1, 1,
"SO_NUM_PRIMS_WRITTEN",
"N geometry shader stream-out primitives (written)");
} else {
gen_perf_query_info_add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(0), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 0)",
"N stream-out (stream 0) primitives (total)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(1), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 1)",
"N stream-out (stream 1) primitives (total)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(2), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 2)",
"N stream-out (stream 2) primitives (total)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_PRIM_STORAGE_NEEDED(3), 1, 1,
"SO_PRIM_STORAGE_NEEDED (Stream 3)",
"N stream-out (stream 3) primitives (total)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(0), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 0)",
"N stream-out (stream 0) primitives (written)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(1), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 1)",
"N stream-out (stream 1) primitives (written)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(2), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 2)",
"N stream-out (stream 2) primitives (written)");
gen_perf_query_info_add_stat_reg(query, GEN7_SO_NUM_PRIMS_WRITTEN(3), 1, 1,
"SO_NUM_PRIMS_WRITTEN (Stream 3)",
"N stream-out (stream 3) primitives (written)");
}
gen_perf_query_info_add_basic_stat_reg(query, HS_INVOCATION_COUNT,
"N TCS shader invocations");
gen_perf_query_info_add_basic_stat_reg(query, DS_INVOCATION_COUNT,
"N TES shader invocations");
gen_perf_query_info_add_basic_stat_reg(query, GS_INVOCATION_COUNT,
"N geometry shader invocations");
gen_perf_query_info_add_basic_stat_reg(query, GS_PRIMITIVES_COUNT,
"N geometry shader primitives emitted");
gen_perf_query_info_add_basic_stat_reg(query, CL_INVOCATION_COUNT,
"N primitives entering clipping");
gen_perf_query_info_add_basic_stat_reg(query, CL_PRIMITIVES_COUNT,
"N primitives leaving clipping");
if (devinfo->is_haswell || devinfo->gen == 8) {
gen_perf_query_info_add_stat_reg(query, PS_INVOCATION_COUNT, 1, 4,
"N fragment shader invocations",
"N fragment shader invocations");
} else {
gen_perf_query_info_add_basic_stat_reg(query, PS_INVOCATION_COUNT,
"N fragment shader invocations");
}
gen_perf_query_info_add_basic_stat_reg(query, PS_DEPTH_COUNT,
"N z-pass fragments");
if (devinfo->gen >= 7) {
gen_perf_query_info_add_basic_stat_reg(query, CS_INVOCATION_COUNT,
"N compute shader invocations");
}
query->data_size = sizeof(uint64_t) * query->n_counters;
}
/* gen_device_info will have incorrect default topology values for unsupported kernels.
* verify kernel support to ensure OA metrics are accurate.
*/
@@ -620,12 +532,10 @@ brw_init_perf_query_info(struct gl_context *ctx)
gen_perf_init_context(perf_ctx, perf_cfg, brw, brw->bufmgr, devinfo,
brw->hw_ctx, brw->screen->driScrnPriv->fd);
init_pipeline_statistic_query_registers(brw);
gen_perf_query_register_mdapi_statistic_query(devinfo, perf_cfg);
if (!oa_metrics_kernel_support(perf_ctx->drm_fd, devinfo))
return 0;
if ((oa_metrics_kernel_support(perf_ctx->drm_fd, devinfo)) &&
(gen_perf_load_oa_metrics(perf_cfg, perf_ctx->drm_fd, devinfo)))
gen_perf_query_register_mdapi_oa_query(devinfo, perf_cfg);
gen_perf_init_metrics(perf_cfg, devinfo, perf_ctx->drm_fd);
return perf_cfg->n_queries;
}