PC Sampling Support (#715)

* cmake formatting (cmake-format) (#188)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* source formatting (clang-format v11) (#189)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: design of the pc sampling data struct; guarding parts of code that uses ROCr marker packets

* source formatting (clang-format v11) (#191)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* cmake formatting (cmake-format) (#192)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: shadow variable fix

* pcs: fix for compiler errors reported by CI/CD

* source formatting (clang-format v11) (#193)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: docs fix; samples uses rocprofiler::rocprofiler library

* cmake formatting (cmake-format) (#195)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: client in samples folder fixed

* pcs: client requires rocprofiler package as dependency

* pcs: client uses single context

* source formatting (clang-format v11) (#196)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: client using single buffer; no buffer destroy in client

* pcs: client::setup explicitly called from the example

* pcs: rocprofiler_pc_sample_record_t updated

* pcs: fixed init of external correlation id

* source formatting (clang-format v11) (#198)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: remove outdated files; update CMakeLists

* cmake formatting (cmake-format) (#212)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: using rocprofiler_agent_id_t

* pcs: Removing trailing whitespaces

Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>

* source formatting (clang-format v11) (#214)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: mapping agent_id to the agent

* source formatting (clang-format v11) (#215)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: const while iterating over agents

* source formatting (clang-format v11) (#216)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: calling get_buffer instead of get_buffers

* pcs: workgroup typo

* pcs: documentation for the public PC sampling API

* pcs: queue_cb_t signature adaptation

* pcs: mocks removed

* pcs: updating HsaApiTable with HSA/ROCr PC sampling API

* pcs: querying available PC sampling configs through IOCTL

* pcs: create the PCS session in IOCTL

* pcs: first actual PC samples delivered to the rocprofiler's client :)

* pcs: works with marker packet too

* pcs: using HSA table to call pc sampling related functions

* pcs: using ioctl instead of kfd in naming

* pcs: configuration service test fixed

* pcs: sample processing test fixed

* pcs: marker packet macro wrapper removed

* pcs: marker packet is part of the rocprofiler_packet union

* pcs: one fixme added

* pcs: client that uses pc-sampling and code obj tracing

* pcs: client that supprts PC sampling and code obj tracing refactored

* pcs: show more info for each PC sample

* pcs: hex output for the samples that do not belong to the matmul kernel

* pcs: querying avail configuration happens immediately before configuring

* pcs: hsa_ven_amd_pcs_create_from_id renamed

* pcs: using hsa_stop; accessing a buffer by id from parser

* pcs: includes reworked, tests returned to life

* pcs: rocrofiler dir removed as outdated

* cmake formatting (cmake-format) (#271)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* source formatting (clang-format v11) (#272)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: some warnings fixed

* source formatting (clang-format v11) (#273)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* cmake formatting (cmake-format) (#274)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: show MI200 relevant information in the sample

* pcs: queue cb fixed; rocr.h include fixed

* source formatting (clang-format v11) (#296)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: getting hsa_agent and the doorbell_id from hsa_queue

* source formatting (clang-format v11) (#297)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: correlation ID logic fixed

* source formatting (clang-format v11) (#303)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: pure pc sampling example fixed

* source formatting (clang-format v11) (#307)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* cmake formatting (cmake-format) (#308)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: interval value if the PC sampling is already configured

* pcs: ROCPROFILER_STATUS_ERROR_PC_SAMPLING_ALREADY_CONFIGURED

New status code if another process configured PC sampling service with different configuration.
Samples are extended to consider this case and retry if it happens.

* pcs: hsa_amd_queue_get_info mocked in tests

* source formatting (clang-format v11) (#328)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs (tests): query configs after configuring service

* source formatting (clang-format v11) (#329)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: sample checks workgroup_id_* and wave_id

* source formatting (clang-format v11) (#330)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs samples: running samples on the device 0

* pcs: kfd_ioctl updated

* pcs: ioctl config struct changed fields names

* pcs: status when PC sampling is configured by another process is renamed

* pcs: HSA PC sampling API table fixed

* pcs: tmp hack to be able to use HSA pc sampling table

* source formatting (clang-format v11) (#443)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs service use CIDs generated by HIP API tracing service

* source formatting (clang-format v11) (#455)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* cmake formatting (cmake-format) (#456)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: CID manager

* pcs: explicit flush with no delivered data executes retirement logic

* source formatting (clang-format v11) (#464)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: rocprofiler_query_pc_sampling_agent_configurations docs update

* source formatting (clang-format v11) (#465)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: rocprofiler_configure_pc_sampling_service docs update

* pcs: explicit sync introduced in PCSCIDManager

* pcs: new logic for retiring CIDs in PC sampling service documented

* pcs: queue interception cb signature updated

* source formatting (clang-format v11) (#471)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: if no agents supports PC sampling, fail gracefully

* elaborating when KFD returns EBUSY and EEXIST

* pcs: the second PC sampling examples fails gracefully

* code samples use only single kernel for now

* pcs: CID manager refactored

* source formatting (clang-format v11) (#481)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* pcs: ioctl update

* source formatting (clang-format v11) (#531)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs:code sample to test PC sampling applied on concurrent kernels

* source formatting (clang-format v11) (#533)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: pc sampling strest test included

* cmake formatting (cmake-format) (#539)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* source formatting (clang-format v11) (#540)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: standalone benchmark

* cmake formatting (cmake-format) (#555)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: glance in external correlation IDs

* source formatting (clang-format v11) (#557)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* another change in ioctl interface

* pcs: update queue interceptor callbacks and samples accroding to the agent 0 version

* source formatting (clang-format v11) (#611)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: avoid running problematic PC sampling test

* pcs: guarding tests not to fail on architectures not supporting PC sampling

* source formatting (clang-format v11) (#617)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: check IOCTL version prior to each KFD call

* pcs: ioctl refactoring

* pcs: PC sampling service increases the ref_count of the correlation ID of the kernel dispatch

* cmake formatting (cmake-format) (#631)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* source formatting (clang-format v11) (#632)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: PC sampling service provides external correlation IDs

* source formatting (clang-format v11) (#644)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: use rocprofiler_dim3_t for workgrou_ip

* source formatting (clang-format v11) (#645)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: minor fixes

* pcs: updating the documentation for the pc sampling API functions

* pcs: api table and queue controller fix

* pcs: don't generate marker packets for the agent if PC sampling is not configured on it

* pcs: multi-GPU and single-GPU clients

* source formatting (clang-format v11) (#700)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: warning and errors fixed

* source formatting (clang-format v11) (#702)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: clang compiler errors and warnings fixed

* source formatting (clang-format v11) (#716)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: const reference in cid manager

* source formatting (clang-format v11) (#717)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: const & func in manager explicit

* pcs: test to cover creating PC sampling service of agent that does not exist

* pcs: generate marker packets if service is active

* source formatting (clang-format v11) (#719)

Co-authored-by: vlaindic <139573562+vlaindic@users.noreply.github.com>

* pcs: refactoring hsa_adapter; use the correlation_id->thread_idx

* Update source/lib/rocprofiler-sdk/pc_sampling/cid_manager.cpp

* Update source/lib/rocprofiler-sdk/pc_sampling/cid_manager.cpp

* Update source/lib/rocprofiler-sdk/pc_sampling/hsa_adapter.cpp

* Update source/lib/rocprofiler-sdk/pc_sampling/hsa_adapter.cpp

* Update source/lib/rocprofiler-sdk/pc_sampling/hsa_adapter.cpp

* Update source/lib/rocprofiler-sdk/pc_sampling/hsa_adapter.cpp

* Update source/lib/rocprofiler-sdk/pc_sampling/utils.cpp

* Update utils.cpp

* moving pc-sampling tests and samples to pc-sampling label

* Format fix

* pcs: use configured instead of active service

* Update source/lib/rocprofiler-sdk/pc_sampling/service.cpp

* pcs: ensure configuring PC sampling on the HSA level is called only once

* pcs: minor fix

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update CMakeLists.txt

* pcs: refactoring IOCTL integration

* Update source/lib/rocprofiler-sdk/pc_sampling/tests/CMakeLists.txt

Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com>

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter.cpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter_types.hpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter.cpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter_types.hpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter.hpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* pcs: reverting back what bot doubled

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter_types.hpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* pcs: retesting the bot

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter_types.hpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* pcs: why bot fails on this IOCTL status

* pcs: why failing on <vector>

* Update source/lib/rocprofiler-sdk/pc_sampling/ioctl/ioctl_adapter.cpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* pcs: returning commits removed by bot

* pcs: formatting locally

* pcs: clients are flushing buffers inside the tool_fini

* pcs: sync function in public API

* pcs: sync prior to unloading the code object

* pcs: sync function requires context

* pcs: client uses CID retirement service

* pcs: test for flusing internal ROCr buffers

* pcs: source formatting

* Update source/lib/rocprofiler-sdk/pc_sampling/tests/CMakeLists.txt

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* pcs: code samples refactoring

* pcs: public API header refactored

* pcs: rocprofiler_buffer_flush drains internal PC sampling buffers too

* pcs: remove unnecessary functions

* pcs: do not call hsa's copytables

* pcs: include reordering

* pcs: using ROCP_ERROR inside PC sampling implementation

* pcs: pc_sampling sample uses ostream instean of printfs

* pcs: pc_sampling_codeobj tracing using ostream instead of prints

* pcs: registering once for interceptor callbacks

* pcs: do not generate internal CIDs if not in debug mode

* pcs: rebasing fixed; missing external correlation IDs

* pcs: code formatting

* enable kernel tracing service to receive external correlation IDs

* pcs: using ROCPROFILER_STATUS_ERROR_INCOMPATIBLE_KERNEL

* pcs: polishing parser

* formatting

* updating parser to use workgroup_id

* kfd_ioctl.h extracted in details folder

* refactoring

* pcs: preparing to generate code object information

* flush internal buffers prior to unloading code object

* pcs: generating marker records

* pcs: wrap code_object's shutdown function

* ROCR_VISIBLE_DEVICES and HIP_VISISBLE_DEVICES unsupported at the moment

* documenting the ignorance of ROCR/HIP_VISIBLE_DEVICES

* pcs: separate structs for code object loading/unloading markers

* pcs: inst_pkt_t changed the namespace

* pcs: removing wrapper around the shutdown function

* pcs: size in record field

* pcs: documentation refactoring + typdefs

* renaming PCSAgentConfig to PCSAgentSession

* pcs: service does not keep a pointer to the context

* pcs: static assertions related to the versioning

* pcs: rocprofiler_pc_sampling_configuration_t size field

* pcs: report API unimplemented unleass explicitly enabled

* pcs: skip tests if KFD does not support PC sampling

* pcs: if ROCr hides some devices, no PC samples will be delivered for it

* pcs: hip error check after kernel launch

* formatting

* removing PCS info from agent.h

* fix based on review

* Update continuous integration workflow

- use mi200 runner for code coverage (supports PC sampling)
- split sanitizer jobs across navi3, vega20, and mi300

* Updating pc sampling test labels

* ROCP_PC_SAMPLING_ENABLED env in CI

* ROCP_PC_SAMPLING_ENABLED for all CI mi200 jobs

* Rearrange sanitizer assignments

* fixes according to review

* removed unused functions

* pcs: rocprofiler_agent_id_t instead of handle as a key in map

* Update source/lib/rocprofiler-sdk/context/context.hpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* removing drm_fd from the agent.h

* pcs: removing one sample due to complexity

* pcs: refactoring sample

* simplifying sample

* new lines

* Improve queue_control enable intercepter logic

* Update lib/rocprofiler-sdk/hsa/types.hpp

- handle amd_ext size for HSA 1.12.0

* ROCP_PC_SAMPLING_ENABLED -> ROCPROFILER_PC_SAMPLING_BETA_ENABLED

* Update hsa_adapter.cpp

- anonymous namespace + remove debug

* parser update

* Apply suggestions from code review

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>
Co-authored-by: vlaindic <vladimir.indic@amd.com>
Co-authored-by: vlaindic <vlaindic@amd.com>
Co-authored-by: Vladimir Indic <139573562+vlaindic@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: gobhardw <gopesh.bhardwaj@amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
This commit is contained in:
Ammar ELWazir
2024-05-24 09:49:44 -05:00
committed by GitHub
parent f14f5a994e
commit 987ae3cc47
64 changed files with 6831 additions and 2012 deletions
@@ -184,17 +184,20 @@ add_upcoming_samples(const device_handle device,
const generic_sample_t* buffer,
const size_t available_samples,
Parser::CorrelationMap* corr_map,
rocprofiler_pc_sampling_record_s* samples)
rocprofiler_pc_sampling_record_t* samples)
{
pcsample_status_t status = PCSAMPLE_STATUS_SUCCESS;
for(uint64_t p = 0; p < available_samples; p++)
{
const auto* snap = reinterpret_cast<const perf_sample_snapshot_v1*>(buffer + p);
samples[p] = copySample<bHostTrap, GFXIP>((const void*) (buffer + p));
samples[p].size = 0; // pc sampling record with size 0 will indicate invalid sample
try
{
Parser::trap_correlation_id_t trap{.raw = snap->correlation_id};
samples[p].correlation_id = corr_map->get(device, trap);
samples[p].size = sizeof(rocprofiler_pc_sampling_record_t);
// set size after corr_map->get which may throw
} catch(std::exception& e)
{
status = PCSAMPLE_STATUS_PARSER_ERROR;
@@ -240,7 +243,7 @@ _parse_buffer(generic_sample_t* buffer,
while(pkt_counter > 0)
{
rocprofiler_pc_sampling_record_s* samples = nullptr;
rocprofiler_pc_sampling_record_t* samples = nullptr;
uint64_t available_samples = callback(&samples, pkt_counter, userdata);
if(available_samples == 0 || available_samples > pkt_counter)
@@ -87,7 +87,7 @@ union pcsample_header_v1_t
uint8_t raw;
};
typedef uint64_t (*user_callback_t)(rocprofiler_pc_sampling_record_s**, uint64_t, void*);
typedef uint64_t (*user_callback_t)(rocprofiler_pc_sampling_record_t**, uint64_t, void*);
/**
* The types of errors to be returned by parse_buffer.
@@ -23,7 +23,7 @@
#include "lib/rocprofiler-sdk/pc_sampling/parser/pc_record_interface.hpp"
uint64_t
PCSamplingParserContext::alloc(rocprofiler_pc_sampling_record_s** buffer, uint64_t size)
PCSamplingParserContext::alloc(rocprofiler_pc_sampling_record_t** buffer, uint64_t size)
{
std::unique_lock<std::shared_mutex> lock(mut);
assert(buffer != nullptr);
@@ -97,3 +97,21 @@ PCSamplingParserContext::shouldFlipRocrBuffer(const dispatch_pkt_id_t& pkt) cons
std::shared_lock<std::shared_mutex> lock(mut);
return corr_map->checkDispatch(pkt);
}
void
PCSamplingParserContext::generate_upcoming_pc_record(
uint64_t agent_id_handle,
const rocprofiler_pc_sampling_record_t* samples,
size_t num_samples)
{
auto buff_id = _agent_buffers.at(rocprofiler_agent_id_t{agent_id_handle});
rocprofiler::buffer::instance* buff = rocprofiler::buffer::get_buffer(buff_id);
if(!buff)
throw std::runtime_error(fmt::format("Buffer with id: {} does not exists", buff_id.handle));
for(size_t i = 0; i < num_samples; i++)
buff->emplace(ROCPROFILER_BUFFER_CATEGORY_PC_SAMPLING,
ROCPROFILER_PC_SAMPLING_RECORD_SAMPLE,
samples[i]);
};
@@ -22,23 +22,32 @@
#pragma once
#include "lib/rocprofiler-sdk/buffer.hpp"
#include "lib/rocprofiler-sdk/pc_sampling/parser/correlation.hpp"
#include "lib/rocprofiler-sdk/pc_sampling/parser/parser_types.h"
#include <rocprofiler-sdk/fwd.h>
#include <rocprofiler-sdk/cxx/hash.hpp>
#include <rocprofiler-sdk/cxx/operators.hpp>
#include <fmt/core.h>
#include <sys/types.h>
#include <cassert>
#include <condition_variable>
#include <cstdint>
#include <memory>
#include <mutex>
#include <shared_mutex>
#include <thread>
#include <unordered_set>
#include "lib/rocprofiler-sdk/pc_sampling/parser/correlation.hpp"
#include "lib/rocprofiler-sdk/pc_sampling/parser/parser_types.h"
struct PCSamplingData
{
PCSamplingData(size_t size)
: samples(size){};
PCSamplingData& operator=(PCSamplingData&) = delete;
std::vector<rocprofiler_pc_sampling_record_s> samples;
std::vector<rocprofiler_pc_sampling_record_t> samples;
};
class PCSamplingParserContext
@@ -52,7 +61,7 @@ public:
* @param[in] size Number of samples requested.
* @returns Number of samples actually allocated on *buffer.
*/
uint64_t alloc(rocprofiler_pc_sampling_record_s** buffer, uint64_t size);
uint64_t alloc(rocprofiler_pc_sampling_record_t** buffer, uint64_t size);
/**
* @brief Parses a chunk of samples.
@@ -95,6 +104,24 @@ public:
*/
bool shouldFlipRocrBuffer(const dispatch_pkt_id_t& pkt) const;
bool register_buffer_for_agent(rocprofiler_buffer_id_t buffer_id,
rocprofiler_agent_id_t agent_id)
{
std::unique_lock<std::shared_mutex> lock(mut);
// Single buffer per agent is allowed
if(_agent_buffers.count(agent_id) > 0) return false;
_agent_buffers.emplace(agent_id, buffer_id);
return true;
}
void unregister_buffer_from_agent(rocprofiler_agent_id_t agent_id)
{
std::unique_lock<std::shared_mutex> lock(mut);
_agent_buffers.erase(agent_id);
}
protected:
/**
* @brief Parses the given input data and generates pc sampling records.
@@ -103,7 +130,7 @@ protected:
template <typename GFX>
pcsample_status_t _parse(const upcoming_samples_t& upcoming, const generic_sample_t* data_)
{
std::shared_lock<std::shared_mutex> lock(mut);
// std::shared_lock<std::shared_mutex> lock(mut);
pcsample_status_t status = PCSAMPLE_STATUS_SUCCESS;
uint64_t pkt_counter = upcoming.num_samples;
@@ -112,7 +139,7 @@ protected:
while(pkt_counter > 0)
{
rocprofiler_pc_sampling_record_s* samples = nullptr;
rocprofiler_pc_sampling_record_t* samples = nullptr;
uint64_t memsize = alloc(&samples, pkt_counter);
if(memsize == 0 || memsize > pkt_counter) return PCSAMPLE_STATUS_CALLBACK_ERROR;
@@ -125,7 +152,7 @@ protected:
data_ += memsize;
pkt_counter -= memsize;
generate_upcoming_pc_record(samples, memsize);
generate_upcoming_pc_record(dev.handle, samples, memsize);
}
return status;
@@ -137,12 +164,9 @@ protected:
*/
pcsample_status_t flushForgetList();
static void generate_id_completion_record(const dispatch_pkt_id_t& pkt) { (void) pkt; };
static void generate_upcoming_pc_record(const rocprofiler_pc_sampling_record_s* samples,
size_t num_samples)
{
(void) samples;
(void) num_samples;
};
void generate_upcoming_pc_record(uint64_t agent_id_handle,
const rocprofiler_pc_sampling_record_t* samples,
size_t num_samples);
//! Maps doorbells and dispatch_index to correlation_id
std::unique_ptr<Parser::CorrelationMap> corr_map;
@@ -156,4 +180,7 @@ protected:
std::unordered_set<uint64_t> forget_list;
mutable std::shared_mutex mut;
private:
std::unordered_map<rocprofiler_agent_id_t, rocprofiler_buffer_id_t> _agent_buffers;
};
@@ -56,8 +56,8 @@ Benchmark(bool bWarmup)
for(size_t i = 0; i < SAMPLE_PER_DISPATCH; i++)
MockWave(dispatch).genPCSample();
std::pair<rocprofiler_pc_sampling_record_s*, size_t> userdata;
userdata.first = new rocprofiler_pc_sampling_record_s[TOTAL_NUM_SAMPLES];
std::pair<rocprofiler_pc_sampling_record_t*, size_t> userdata;
userdata.first = new rocprofiler_pc_sampling_record_t[TOTAL_NUM_SAMPLES];
userdata.second = TOTAL_NUM_SAMPLES;
auto t0 = std::chrono::system_clock::now();
@@ -65,9 +65,9 @@ Benchmark(bool bWarmup)
(generic_sample_t*) buffer->packets.data(),
buffer->packets.size(),
GFXIP_MAJOR,
[](rocprofiler_pc_sampling_record_s** sample, uint64_t size, void* userdata_) {
[](rocprofiler_pc_sampling_record_t** sample, uint64_t size, void* userdata_) {
auto* pair =
reinterpret_cast<std::pair<rocprofiler_pc_sampling_record_s*, size_t>*>(userdata_);
reinterpret_cast<std::pair<rocprofiler_pc_sampling_record_t*, size_t>*>(userdata_);
assert(TOTAL_NUM_SAMPLES == pair->second);
*sample = pair->first;
return size;
@@ -80,7 +80,7 @@ Benchmark(bool bWarmup)
{
std::cout << "Benchmark: Parsed " << int(samples_per_us * 1E3f + 0.5f) * 1E-3f
<< " Msample/s (";
std::cout << int(sizeof(rocprofiler_pc_sampling_record_s) * samples_per_us) << " MB/s)"
std::cout << int(sizeof(rocprofiler_pc_sampling_record_t) * samples_per_us) << " MB/s)"
<< std::endl;
}
@@ -33,14 +33,14 @@ std::mt19937 rdgen(1);
/**
* Sample user memory allocation callback.
* It expects userdata to be cast-able to a pointer to
* std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>>
* std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>>
*/
static uint64_t
alloc_callback(rocprofiler_pc_sampling_record_s** buffer, uint64_t size, void* userdata)
alloc_callback(rocprofiler_pc_sampling_record_t** buffer, uint64_t size, void* userdata)
{
*buffer = new rocprofiler_pc_sampling_record_s[size];
*buffer = new rocprofiler_pc_sampling_record_t[size];
auto& vector =
*reinterpret_cast<std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>>*>(
*reinterpret_cast<std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>>*>(
userdata);
vector.push_back({*buffer, size});
return size;
@@ -51,7 +51,7 @@ alloc_callback(rocprofiler_pc_sampling_record_s** buffer, uint64_t size, void* u
* the reconstructed correlation_id.
*/
static bool
check_samples(rocprofiler_pc_sampling_record_s* samples, uint64_t size)
check_samples(rocprofiler_pc_sampling_record_t* samples, uint64_t size)
{
for(size_t i = 0; i < size; i++)
if(samples[i].correlation_id.internal != samples[i].pc) return false;
@@ -71,7 +71,7 @@ TEST(pcs_parser, hello_world)
MockWave(dispatch).genPCSample();
MockWave(dispatch).genPCSample();
std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>> all_allocations;
std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>> all_allocations;
CHECK_PARSER(parse_buffer((generic_sample_t*) buffer->packets.data(),
buffer->packets.size(),
@@ -114,7 +114,7 @@ TEST(pcs_parser, reverse_wave_order)
for(auto it = dispatches.begin(); it != dispatches.end(); it++)
MockWave(*it).genPCSample();
std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>> all_allocations;
std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>> all_allocations;
CHECK_PARSER(parse_buffer((generic_sample_t*) buffer->packets.data(),
buffer->packets.size(),
@@ -150,7 +150,7 @@ TEST(pcs_parser, dispatch_wrapping)
MockWave(dispatch).genPCSample();
}
std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>> all_allocations;
std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>> all_allocations;
CHECK_PARSER(parse_buffer((generic_sample_t*) buffer->packets.data(),
buffer->packets.size(),
@@ -197,7 +197,7 @@ TEST(pcs_parser, random_samples)
for(int i = 0; i < num_samples; i++)
MockWave(dispatches[rdgen() % dispatches.size()]).genPCSample();
std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>> all_allocations;
std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>> all_allocations;
CHECK_PARSER(parse_buffer((generic_sample_t*) buffer->packets.data(),
buffer->packets.size(),
@@ -290,7 +290,7 @@ TEST(pcs_parser, queue_hammer)
<< std::endl;
std::cout << "Max queue occupancy: " << max_q_occupancy << "\n\n" << std::endl;
std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>> all_allocations;
std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>> all_allocations;
CHECK_PARSER(parse_buffer((generic_sample_t*) buffer->packets.data(),
buffer->packets.size(),
@@ -302,7 +302,7 @@ TEST(pcs_parser, queue_hammer)
NUM_ACTIONS); // QueueHammer test: Incorrect number of callbacks
for(auto sb = 0ul; sb < all_allocations.size(); sb++)
{
rocprofiler_pc_sampling_record_s* samples = all_allocations[sb].first;
rocprofiler_pc_sampling_record_t* samples = all_allocations[sb].first;
size_t num_samples = all_allocations[sb].second;
EXPECT_EQ(num_samples, NUM_QUEUES); // QueueHammer: Incorrect number of samples
@@ -329,7 +329,7 @@ TEST(pcs_parser, multi_buffer)
const auto& packets = firstBuffer->packets;
secondBuffer->packets = std::vector<packet_union_t>(packets.begin() + 2, packets.end());
std::vector<std::pair<rocprofiler_pc_sampling_record_s*, uint64_t>> all_allocations;
std::vector<std::pair<rocprofiler_pc_sampling_record_t*, uint64_t>> all_allocations;
CHECK_PARSER(parse_buffer((generic_sample_t*) firstBuffer->packets.data(),
firstBuffer->packets.size(),
@@ -24,13 +24,15 @@
# undef NDEBUG
#endif
#include "lib/rocprofiler-sdk/pc_sampling/parser/pc_record_interface.hpp"
#include "lib/rocprofiler-sdk/pc_sampling/parser/tests/mocks.hpp"
#include <rocprofiler-sdk/cxx/operators.hpp>
#include <gtest/gtest.h>
#include <cassert>
#include <cstddef>
#include "lib/rocprofiler-sdk/pc_sampling/parser/pc_record_interface.hpp"
#include "lib/rocprofiler-sdk/pc_sampling/parser/tests/mocks.hpp"
#define GFXIP_MAJOR 9
#define TYPECHECK(x) \
@@ -295,7 +297,7 @@ class WaveIssueAndErrorTest : public WaveSnapTest
void genPCSample(bool valid, bool issued, bool dual, bool error)
{
rocprofiler_pc_sampling_record_s sample;
rocprofiler_pc_sampling_record_t sample;
::memset(&sample, 0, sizeof(sample));
sample.pc = dispatch->unique_id;
sample.correlation_id.internal = dispatch->getMockId().raw;
@@ -320,7 +322,7 @@ class WaveIssueAndErrorTest : public WaveSnapTest
dispatch->submit(std::move(pss));
};
std::vector<rocprofiler_pc_sampling_record_s> compare;
std::vector<rocprofiler_pc_sampling_record_t> compare;
};
class WaveOtherFieldsTest : public WaveSnapTest
@@ -347,9 +349,7 @@ class WaveOtherFieldsTest : public WaveSnapTest
assert(parsed[0][i].flags.reserved == false);
assert(compare[i].exec_mask == parsed[0][i].exec_mask);
assert(compare[i].workgroup_id_x == parsed[0][i].workgroup_id_x);
assert(compare[i].workgroup_id_y == parsed[0][i].workgroup_id_y);
assert(compare[i].workgroup_id_z == parsed[0][i].workgroup_id_z);
assert(compare[i].workgroup_id == parsed[0][i].workgroup_id);
assert(compare[i].chiplet == parsed[0][i].chiplet);
assert(compare[i].wave_id == parsed[0][i].wave_id);
@@ -360,13 +360,13 @@ class WaveOtherFieldsTest : public WaveSnapTest
void genPCSample(int pc, int exec, int blkx, int blky, int blkz, int chip, int wave, int hwid)
{
rocprofiler_pc_sampling_record_s sample;
rocprofiler_pc_sampling_record_t sample;
::memset(&sample, 0, sizeof(sample));
sample.exec_mask = exec;
sample.workgroup_id_x = blkx;
sample.workgroup_id_y = blky;
sample.workgroup_id_z = blkz;
sample.workgroup_id.x = blkx;
sample.workgroup_id.y = blky;
sample.workgroup_id.z = blkz;
sample.chiplet = chip;
sample.wave_id = wave;
@@ -392,7 +392,7 @@ class WaveOtherFieldsTest : public WaveSnapTest
(void) pc;
};
std::vector<rocprofiler_pc_sampling_record_s> compare;
std::vector<rocprofiler_pc_sampling_record_t> compare;
};
TEST(pcs_parser, gfx9_test)
@@ -65,7 +65,7 @@ public:
submit(uni);
}
std::vector<std::vector<rocprofiler_pc_sampling_record_s>> get_parsed_buffer(int GFXIP_MAJOR)
std::vector<std::vector<rocprofiler_pc_sampling_record_t>> get_parsed_buffer(int GFXIP_MAJOR)
{
parsed_data = {};
@@ -78,18 +78,18 @@ public:
return parsed_data;
}
static uint64_t alloc_parse_memory(rocprofiler_pc_sampling_record_s** sample,
static uint64_t alloc_parse_memory(rocprofiler_pc_sampling_record_t** sample,
uint64_t req_size,
void* userdata)
{
auto* buffer = reinterpret_cast<MockRuntimeBuffer*>(userdata);
buffer->parsed_data.push_back(std::vector<rocprofiler_pc_sampling_record_s>(req_size));
buffer->parsed_data.push_back(std::vector<rocprofiler_pc_sampling_record_t>(req_size));
*sample = buffer->parsed_data.back().data();
return req_size;
}
std::vector<packet_union_t> packets;
std::vector<std::vector<rocprofiler_pc_sampling_record_s>> parsed_data;
std::vector<std::vector<rocprofiler_pc_sampling_record_t>> parsed_data;
};
/**
@@ -32,18 +32,18 @@
#include "lib/rocprofiler-sdk/pc_sampling/parser/rocr.h"
template <typename SType>
inline rocprofiler_pc_sampling_record_s
inline rocprofiler_pc_sampling_record_t
copySampleHeader(const SType& sample)
{
rocprofiler_pc_sampling_record_s ret;
rocprofiler_pc_sampling_record_t ret;
ret.flags = pcsample_header_v1_t{.raw = 0}.flags;
ret.flags.type = AMD_SNAPSHOT_V1;
ret.pc = sample.pc;
ret.exec_mask = sample.exec_mask;
ret.workgroup_id_x = sample.workgroup_id_x;
ret.workgroup_id_y = sample.workgroup_id_y;
ret.workgroup_id_z = sample.workgroup_id_z;
ret.workgroup_id.x = sample.workgroup_id_x;
ret.workgroup_id.y = sample.workgroup_id_y;
ret.workgroup_id.z = sample.workgroup_id_z;
ret.chiplet = sample.chiplet_and_wave_id >> 8;
ret.wave_id = sample.chiplet_and_wave_id & 0x3F;
@@ -52,23 +52,23 @@ copySampleHeader(const SType& sample)
return ret;
}
inline rocprofiler_pc_sampling_record_s
inline rocprofiler_pc_sampling_record_t
copyHostTrapSample(const perf_sample_host_trap_v1& sample)
{
rocprofiler_pc_sampling_record_s ret = copySampleHeader<perf_sample_host_trap_v1>(sample);
rocprofiler_pc_sampling_record_t ret = copySampleHeader<perf_sample_host_trap_v1>(sample);
ret.flags.type = AMD_HOST_TRAP_V1;
return ret;
}
template <typename gfx>
inline rocprofiler_pc_sampling_record_s
inline rocprofiler_pc_sampling_record_t
copyStochasticSample(const perf_sample_snapshot_v1& sample);
template <>
inline rocprofiler_pc_sampling_record_s
inline rocprofiler_pc_sampling_record_t
copyStochasticSample<GFX9>(const perf_sample_snapshot_v1& sample)
{
rocprofiler_pc_sampling_record_s ret = copySampleHeader<perf_sample_snapshot_v1>(sample);
rocprofiler_pc_sampling_record_t ret = copySampleHeader<perf_sample_snapshot_v1>(sample);
ret.flags.valid = sample.perf_snapshot_data & (~sample.perf_snapshot_data >> 26) & 0x1;
// Check wave_id matches snapshot_wave_id
@@ -88,10 +88,10 @@ copyStochasticSample<GFX9>(const perf_sample_snapshot_v1& sample)
}
template <>
inline rocprofiler_pc_sampling_record_s
inline rocprofiler_pc_sampling_record_t
copyStochasticSample<GFX11>(const perf_sample_snapshot_v1& sample)
{
rocprofiler_pc_sampling_record_s ret = copySampleHeader<perf_sample_snapshot_v1>(sample);
rocprofiler_pc_sampling_record_t ret = copySampleHeader<perf_sample_snapshot_v1>(sample);
ret.flags.valid = sample.perf_snapshot_data & (~sample.perf_snapshot_data >> 23) & 0x1;
// Check wave_id matches snapshot_wave_id
@@ -195,12 +195,12 @@ translate_inst(int in)
#undef LUTOVERLOAD
template <bool HostTrap, typename GFX>
inline rocprofiler_pc_sampling_record_s
inline rocprofiler_pc_sampling_record_t
copySample(const void* sample)
{
if(HostTrap) return copyHostTrapSample(*(const perf_sample_host_trap_v1*) sample);
rocprofiler_pc_sampling_record_s ret =
rocprofiler_pc_sampling_record_t ret =
copyStochasticSample<GFX>(*(const perf_sample_snapshot_v1*) sample);
ret.snapshot.inst_type = translate_inst<GFX>(ret.snapshot.inst_type);