2
0

Pull from Github

Squashed commit of the following:

commit f029195705a15700380c6f832ba5d15d46fd6de7
Author: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Date:   Thu Jul 13 14:38:56 2023 -0500

    Formatting workflows for source (clang-format) and cmake (cmake-format) (#4)

    * Add .cmake-format.yaml file

    * Add formatting workflow

    * provide base input for creating PR

    * Update scheme for extracting branch name

    - disable running formatting on push to amd-staging branch

    * patch .cmake-format.yaml for find_package signature

    - apparently cmake-format doesn't format the full signature of find_package

    * run formatting (clang-format v11) (#7)

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

    * run cmake formatting (cmake-format) (#6)

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

    ---------

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

commit bc4d135fdd8a1a9e51235f18a5d575fd2b3735e6
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Thu Jul 13 12:55:17 2023 -0500

    Removing Build cache for potential issues with auto-generated header files (#5)

    Change-Id: I9e2319f4335e2f88585ffa6fac2bd88a1c952e6e

commit ce86dea6a311d44d880fa684eb78f3329295e2a4
Author: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Date:   Thu Jul 13 11:08:58 2023 -0500

    Fix decltype(<hsa-function>) function pointer usage (#3)

    - the following is done in several places:
        decltype(hsa_memory_allocate)* hsa_memory_allocate
    - above can cause compiler errors
    - replace decltype(<hsa-function>) with decltype(::<hsa-function>)
      - this ensures that the type within the decltype is recognized as the global scope HSA function, not the variable
    - in many places, the variable has a "_fn" suffix to prevent this issue but added '::' anyway for consistency

commit ac49fdd92a72e9c99394253a02da413a6c2e3b3a
Merge: a07946a 03a0855
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Wed Jul 12 11:36:24 2023 -0500

    Merge pull request #2 from ROCm-Developer-Tools/gerrit-amd-staging

    Pull from gerrit

commit 03a085588cffe863e8f466de67be1cfb205b675a
Merge: e88cad2 a07946a
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Wed Jul 12 10:57:30 2023 -0500

    Merge branch 'amd-staging' into gerrit-amd-staging

commit a07946a5cd4c670c83c27ad1a076a9d4567ce6d7
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 15:46:04 2023 +0000

    Enabling Cached Builds

commit 525e494a7f13941077a8fd4ad6840904db4d27d4
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 04:53:54 2023 +0000

    Updating missed GPU Targets

commit 42c75862f628c9bee7cfb7dc04dff2619430efbc
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 04:43:02 2023 +0000

    Adding V1 Testing

commit 9d72fd4aee85e4b0c12e717060d2730fa5b73be1
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 03:34:31 2023 +0000

    Fixing Artifacts directory path

commit f4000cc558b3b2e4676f7994f7ce8c8e6f94518e
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 03:27:26 2023 +0000

    Fixing CMake for test build job

commit 2ce8115d4c33948c3c8f957f545a95a04e1d6cd2
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 03:16:18 2023 +0000

    Fixing Ubuntu CMake for ubuntu test build

commit 6d0ed439191be900748d0c025157f9d689a73ec7
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 01:28:41 2023 +0000

    Removing Navi21

commit e349a7642e5ae5eb03ab9fcd0a0f74f09f78cab5
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 01:14:14 2023 +0000

    Removing Navi21

commit fefd02fe68d2a4bca7ec2e381960ad004ee9fc5b
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 00:42:48 2023 +0000

    Fixing CMake Job

commit 2ea46abf7bf92643efa8c549fa70346ffbd79d65
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 00:35:13 2023 +0000

    Fixing CMake Job

commit d99d681ed1999c5fcf291dc678b11a77205fb0f3
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Wed Jul 12 00:32:13 2023 +0000

    Fixing Pull Latest Dockers and CMake Jobs

commit dfc4498072d13b4a1df3a63047d34c682c3d9a29
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Tue Jul 11 23:54:21 2023 +0000

    Fixing CMake job

commit 919efe04de707f7c702031be15c3e2c5f8442cbb
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Tue Jul 11 23:52:13 2023 +0000

    Adding Pull Last dockers job

commit be1b1256e8b0e05308e8f7e7e69bee3acca55281
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Tue Jul 11 18:25:40 2023 -0500

    Update cmake.yml

commit 212299fa4355ae6ec18f9aaacbb79c51ea6c6f97
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Tue Jul 11 18:23:35 2023 -0500

    Update cmake.yml

commit 7c2c1327086a61466cc6cac39f70865c051a8bc7
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Tue Jul 11 18:18:53 2023 -0500

    Update cmake.yml

commit 191b5ce007e612e814c1d7a3afb4ad398f3852e1
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Tue Jul 11 16:03:22 2023 -0500

    Update cmake.yml

commit 8824113d95f3e13c7ce4d0af8e0d9d8f522a6c4a
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Tue Jul 11 16:28:09 2023 +0000

    Fixing Pull from Gerrit job name

    Change-Id: I9e7ed9a27a13ca49d62c93bdadb30f0057e4d385

commit cc3d5e4b02ffb439e8cc2b3efa53527c376f9982
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Tue Jul 11 16:21:43 2023 +0000

    Adding Staging sync job

    Change-Id: I0551f43878b0678ce4b3e74e27d62357cf95ad95

commit b9be2eee71380a2e6dd34d520e92d0c4209277a0
Author: Ammar ELWazir <Ammar.ELWazir@amd.com>
Date:   Tue Jul 11 15:57:11 2023 +0000

    Fixing build.sh

    Change-Id: Ia987b0244f0875370d5fe69907b3f5e9cea914de

commit 9eee33a95a1abd656a7ac5ca10a9f245e9825431
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 21:39:46 2023 -0500

    Update cmake.yml

commit 7093b85a78497140e8b52632ca2a002bdaeacd62
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 21:33:29 2023 -0500

    Update cmake.yml

commit f54697172c72a67740f9fdfa0c217b6ea6931576
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 21:01:26 2023 -0500

    Update cmake.yml

commit 1b6620e16f8940386b0f4f04e69e2410d21c0e26
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 20:21:02 2023 -0500

    Update cmake.yml

commit a94bec740c6b42c4b79c87bca20fa87b99bf060d
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 19:46:35 2023 -0500

    Update cmake.yml

commit 85d6b29d4375a69d575c18ece8542c50f2ddfcc3
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 19:34:39 2023 -0500

    Update cmake.yml

commit 8c004887cf1435f1a6214c3d2455299a8a27bd4c
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 19:31:17 2023 -0500

    Update cmake.yml

commit a14a9168e17d9348a53c6e9c9a47ba1edb4c4509
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 19:25:46 2023 -0500

    Update cmake.yml

commit 000f2f40b84e6a2f7d4becdbf5aed01436ca4c83
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 19:08:18 2023 -0500

    Update cmake.yml

commit a28a53d56731cad848fa9133d1c4dbaa8fc7afa7
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 19:03:39 2023 -0500

    Update cmake.yml

commit a6a2db01027f0b01fdfbb5997ddb772c7f51b649
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 18:21:53 2023 -0500

    Update cmake.yml

commit 118ef2a88b2d44e3207c31c343da3e5e5ec6f176
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 17:55:57 2023 -0500

    Update cmake.yml

commit 03c4c232396440cd0be6d2dd7baf4ceea1c2589d
Author: Ammar ELWazir <aelwazir@amd.com>
Date:   Mon Jul 10 17:48:49 2023 -0500

    Create cmake.yml

Change-Id: I77992f15694e77cbae49c56f9ff02f4f9079235d
Este cometimento está contido em:
Ammar ELWazir
2023-07-13 19:48:38 +00:00
cometido por Ammar Elwazir
ascendente 019ddfe68e
cometimento d4a33cf33a
144 ficheiros modificados com 154836 adições e 166916 eliminações
+65 -67
Ver ficheiro
@@ -27,7 +27,7 @@ THE SOFTWARE.
#include <hsa/hsa.h>
#include <hsa/hsa_ext_amd.h>
#include <unistd.h> // usleep
#include <unistd.h> // usleep
#include <atomic>
#include <list>
#include <map>
@@ -91,8 +91,7 @@ class Group {
barrier_signal_{},
dispatch_signal_{},
orig_signal_{},
record_{}
{}
record_{} {}
void Insert(const profile_info_t& info) {
const rocprofiler_feature_kind_t kind = info.rinfo->kind;
@@ -110,11 +109,10 @@ class Group {
}
hsa_status_t Finalize(const bool is_concurrent = false) {
hsa_status_t status = pmc_profile_.Finalize(start_vector_, stop_vector_,
read_vector_, is_concurrent);
hsa_status_t status =
pmc_profile_.Finalize(start_vector_, stop_vector_, read_vector_, is_concurrent);
if (status == HSA_STATUS_SUCCESS) {
status = trace_profile_.Finalize(start_vector_, stop_vector_,
read_vector_, is_concurrent);
status = trace_profile_.Finalize(start_vector_, stop_vector_, read_vector_, is_concurrent);
}
if (status == HSA_STATUS_SUCCESS) {
if (!pmc_profile_.Empty()) ++n_profiles_;
@@ -137,32 +135,20 @@ class Group {
Context* GetContext() { return context_; }
uint32_t GetIndex() const { return index_; }
void SetBarrierSignal(const hsa_signal_t &signal) {
barrier_signal_ = signal;
}
hsa_signal_t& GetBarrierSignal() {
return barrier_signal_;
}
void SetDispatchSignal(const hsa_signal_t &signal) {
dispatch_signal_ = signal;
}
hsa_signal_t& GetDispatchSignal() {
return dispatch_signal_;
}
void SetOrigSignal(const hsa_signal_t &signal) {
orig_signal_ = signal;
}
const hsa_signal_t& GetOrigSignal() const {
return orig_signal_;
}
rocprofiler_dispatch_record_t* GetRecord() {
return &record_;
}
void SetBarrierSignal(const hsa_signal_t& signal) { barrier_signal_ = signal; }
hsa_signal_t& GetBarrierSignal() { return barrier_signal_; }
void SetDispatchSignal(const hsa_signal_t& signal) { dispatch_signal_ = signal; }
hsa_signal_t& GetDispatchSignal() { return dispatch_signal_; }
void SetOrigSignal(const hsa_signal_t& signal) { orig_signal_ = signal; }
const hsa_signal_t& GetOrigSignal() const { return orig_signal_; }
rocprofiler_dispatch_record_t* GetRecord() { return &record_; }
atomic_refs_t* AtomicRefsCount() { return reinterpret_cast<atomic_refs_t*>(&refs_); }
void ResetRefsCount() { AtomicRefsCount()->store(n_profiles_, std::memory_order_release); }
void IncrRefsCount() { AtomicRefsCount()->fetch_add(1, std::memory_order_acq_rel); }
uint32_t FetchDecrRefsCount() { return AtomicRefsCount()->fetch_sub(1, std::memory_order_acq_rel); }
uint32_t FetchDecrRefsCount() {
return AtomicRefsCount()->fetch_sub(1, std::memory_order_acq_rel);
}
private:
PmcProfile pmc_profile_;
@@ -188,23 +174,23 @@ class Context {
public:
typedef std::map<std::string, rocprofiler_feature_t*> info_map_t;
static void Create(Context* obj, const util::AgentInfo* agent_info, Queue* queue, rocprofiler_feature_t* info,
const uint32_t info_count, rocprofiler_handler_t handler, void* handler_arg)
{
static void Create(Context* obj, const util::AgentInfo* agent_info, Queue* queue,
rocprofiler_feature_t* info, const uint32_t info_count,
rocprofiler_handler_t handler, void* handler_arg) {
new (obj) Context(agent_info, queue, info, info_count, handler, handler_arg);
obj->Construct(agent_info, queue, info, info_count, handler, handler_arg);
}
static void Release(Context* obj) { obj->Destruct(); }
static Context* Create(const util::AgentInfo* agent_info, Queue* queue, rocprofiler_feature_t* info,
const uint32_t info_count, rocprofiler_handler_t handler, void* handler_arg)
{
static Context* Create(const util::AgentInfo* agent_info, Queue* queue,
rocprofiler_feature_t* info, const uint32_t info_count,
rocprofiler_handler_t handler, void* handler_arg) {
Context* obj = new Context(agent_info, queue, info, info_count, handler, handler_arg);
if (obj == NULL) EXC_RAISING(HSA_STATUS_ERROR, "allocation error");
try {
obj->Construct(agent_info, queue, info, info_count, handler, handler_arg);
} catch(...) {
} catch (...) {
delete obj;
obj = NULL;
std::cerr << "Error: Context Create failed" << std::endl;
@@ -213,7 +199,9 @@ class Context {
return obj;
}
static void Destroy(Context* obj) { if (obj != NULL) delete obj; }
static void Destroy(Context* obj) {
if (obj != NULL) delete obj;
}
void Reset(const uint32_t& group_index) { set_[group_index].ResetRefsCount(); }
@@ -293,8 +281,10 @@ class Context {
hsa_rsrc_->SignalWaitRestore(tuple.completion_signal, 1);
// Restore other signals
RestoreSignals(tuple);
for (rocprofiler_feature_t* rinfo : *(tuple.info_vector)) rinfo->data.kind = ROCPROFILER_DATA_KIND_UNINIT;
callback_data_t callback_data{tuple.profile, tuple.info_vector, tuple.info_vector->size(), NULL};
for (rocprofiler_feature_t* rinfo : *(tuple.info_vector))
rinfo->data.kind = ROCPROFILER_DATA_KIND_UNINIT;
callback_data_t callback_data{tuple.profile, tuple.info_vector, tuple.info_vector->size(),
NULL};
const hsa_status_t status =
api_->hsa_ven_amd_aqlprofile_iterate_data(tuple.profile, DataCallback, &callback_data);
if (status != HSA_STATUS_SUCCESS) AQL_EXC_RAISING(status, "context iterate data failed");
@@ -310,7 +300,8 @@ class Context {
if (expr) {
auto it = info_map_.find(name);
if (it == info_map_.end())
EXC_RAISING(HSA_STATUS_ERROR, "metric '" << name << "', rocprofiler info is not found " << this);
EXC_RAISING(HSA_STATUS_ERROR,
"metric '" << name << "', rocprofiler info is not found " << this);
rocprofiler_feature_t* info = it->second;
info->data.result_double = expr->Eval(args);
info->data.kind = ROCPROFILER_DATA_KIND_DOUBLE;
@@ -324,7 +315,7 @@ class Context {
for (auto& tuple : profile_vector) {
if (pcsmp_mode_) const_cast<profile_t*>(tuple.profile)->event_count = UINT32_MAX;
const hsa_status_t status =
api_->hsa_ven_amd_aqlprofile_iterate_data(tuple.profile, callback, data);
api_->hsa_ven_amd_aqlprofile_iterate_data(tuple.profile, callback, data);
if (status != HSA_STATUS_SUCCESS) AQL_EXC_RAISING(status, "context iterate data failed");
}
}
@@ -342,7 +333,10 @@ class Context {
hsa_agent_t GetAgent() const { return agent_; }
Group* GetGroup(const uint32_t& index) { return &set_[index]; }
rocprofiler_handler_t GetHandler(void** arg) const { *arg = handler_arg_; return handler_; }
rocprofiler_handler_t GetHandler(void** arg) const {
*arg = handler_arg_;
return handler_;
}
// Concurrent profiling mode
static bool k_concurrent_;
@@ -358,8 +352,7 @@ class Context {
metrics_(NULL),
handler_(handler),
handler_arg_(handler_arg),
pcsmp_mode_(false)
{}
pcsmp_mode_(false) {}
~Context() { Destruct(); }
@@ -375,8 +368,7 @@ class Context {
}
void Construct(const util::AgentInfo* agent_info, Queue* queue, rocprofiler_feature_t* info,
const uint32_t info_count, rocprofiler_handler_t handler, void* handler_arg)
{
const uint32_t info_count, rocprofiler_handler_t handler, void* handler_arg) {
if (info_count == 0) {
set_.push_back(Group(agent_info_, this, 0));
return;
@@ -386,9 +378,11 @@ class Context {
if (metrics_ == NULL) EXC_RAISING(HSA_STATUS_ERROR, "MetricsDict create failed");
if (Initialize(info, info_count) == false) {
fprintf(stdout, "\nInput metrics out of HW limit. Proposed metrics group set:\n"); fflush(stdout);
fprintf(stdout, "\nInput metrics out of HW limit. Proposed metrics group set:\n");
fflush(stdout);
MetricsGroupSet(agent_info, info, info_count).Print(stdout);
fprintf(stdout, "\n"); fflush(stdout);
fprintf(stdout, "\n");
fflush(stdout);
EXC_RAISING(HSA_STATUS_ERROR, "Metrics list exceeds HW limits");
}
Finalize();
@@ -420,8 +414,8 @@ class Context {
info_map_[name] = info;
auto ret = metrics_map_.insert({name, NULL});
if (!ret.second)
EXC_RAISING(HSA_STATUS_ERROR, "input metric '" << name
<< "' is registered more then once");
EXC_RAISING(HSA_STATUS_ERROR,
"input metric '" << name << "' is registered more then once");
}
}
@@ -437,8 +431,9 @@ class Context {
if (kind == ROCPROFILER_FEATURE_KIND_METRIC) { // Processing metrics features
const Metric* metric = metrics_->Get(name);
if (metric == NULL)
EXC_RAISING(HSA_STATUS_ERROR, "input metric '" << name << "' is not supported on this hardware: "
<< agent_info_->name);
EXC_RAISING(HSA_STATUS_ERROR,
"input metric '"
<< name << "' is not supported on this hardware: " << agent_info_->name);
#if 0
std::cout << " " << name << (metric->GetExpr() ? " = " + metric->GetExpr()->String() : " counter") << std::endl;
#endif
@@ -493,9 +488,9 @@ class Context {
info->kind = ROCPROFILER_FEATURE_KIND_TRACE;
const event_t* event = NULL;
if (kind & ROCPROFILER_FEATURE_KIND_PCSMP_MOD) { // PC sampling
if (kind & ROCPROFILER_FEATURE_KIND_PCSMP_MOD) { // PC sampling
pcsmp_mode_ = true;
} else if (kind & ROCPROFILER_FEATURE_KIND_SPM_MOD) { // SPM trace
} else if (kind & ROCPROFILER_FEATURE_KIND_SPM_MOD) { // SPM trace
const Metric* metric = metrics_->Get(name);
if (metric == NULL)
EXC_RAISING(HSA_STATUS_ERROR, "input metric '" << name << "' is not found");
@@ -559,14 +554,14 @@ class Context {
const bool trace_local = TraceProfile::IsLocal();
util::HsaRsrcFactory* hsa_rsrc = &util::HsaRsrcFactory::Instance();
if (sample_id == 0) {
const uint32_t output_buffer_size = profile->output_buffer.size;
const uint32_t output_buffer_size64 = profile->output_buffer.size / sizeof(uint64_t);
const util::AgentInfo* agent_info = hsa_rsrc->GetAgentInfo(profile->agent);
void* ptr = (trace_local) ? hsa_rsrc->AllocateSysMemory(agent_info, output_buffer_size) :
calloc(output_buffer_size64, sizeof(uint64_t));
rinfo->data.result_bytes.size = output_buffer_size;
rinfo->data.result_bytes.ptr = ptr;
callback_data->ptr = reinterpret_cast<char*>(ptr);
const uint32_t output_buffer_size = profile->output_buffer.size;
const uint32_t output_buffer_size64 = profile->output_buffer.size / sizeof(uint64_t);
const util::AgentInfo* agent_info = hsa_rsrc->GetAgentInfo(profile->agent);
void* ptr = (trace_local) ? hsa_rsrc->AllocateSysMemory(agent_info, output_buffer_size)
: calloc(output_buffer_size64, sizeof(uint64_t));
rinfo->data.result_bytes.size = output_buffer_size;
rinfo->data.result_bytes.ptr = ptr;
callback_data->ptr = reinterpret_cast<char*>(ptr);
}
char* result_bytes_ptr = reinterpret_cast<char*>(rinfo->data.result_bytes.ptr);
const char* end = result_bytes_ptr + rinfo->data.result_bytes.size;
@@ -577,8 +572,10 @@ class Context {
char* dest = ptr + sizeof(*header);
if ((dest + size) >= end) {
if (dest < end) size = end - dest;
else EXC_RAISING(HSA_STATUS_ERROR, "Trace data out of output buffer");
if (dest < end)
size = end - dest;
else
EXC_RAISING(HSA_STATUS_ERROR, "Trace data out of output buffer");
}
bool suc = true;
@@ -593,7 +590,9 @@ class Context {
rinfo->data.result_bytes.instance_count = sample_id + 1;
rinfo->data.kind = ROCPROFILER_DATA_KIND_BYTES;
} else
EXC_RAISING(HSA_STATUS_ERROR, "Agent Memcpy failed, dst(" << (void*)dest << ") src(" << (void*)src << ") size(" << size << ")");
EXC_RAISING(HSA_STATUS_ERROR,
"Agent Memcpy failed, dst(" << (void*)dest << ") src(" << (void*)src
<< ") size(" << size << ")");
} else {
if (sample_id == 0) {
rinfo->data.result_bytes.ptr = profile->output_buffer.ptr;
@@ -647,8 +646,7 @@ class Context {
bool pcsmp_mode_;
};
#define CONTEXT_INSTANTIATE() \
bool rocprofiler::Context::k_concurrent_ = false;
#define CONTEXT_INSTANTIATE() bool rocprofiler::Context::k_concurrent_ = false;
} // namespace rocprofiler