391451752b
Changes:
- Updated AMD SMI firmware to display "N/A" for unavailable firmware in partitioned environments, improving clarity.
Example (in DPX):
$ amd-smi firmware
GPU: 0
FW_LIST:
...
FW 12:
FW_ID: PM
FW_VERSION: 00.86.39.00
GPU: 1
FW_LIST: N/A
- Fixed amd-smi partition not showing current partition information on
asics with inablity to set memory or accelerator partitions.
$ amd-smi partition -c -m
CURRENT_PARTITION:
GPU_ID MEMORY ACCELERATOR_TYPE ACCELERATOR_PROFILE_INDEX PARTITION_ID
0 NPS1 CPX 2 0
1 N/A N/A N/A 1
2 N/A N/A N/A 2
3 N/A N/A N/A 3
4 N/A N/A N/A 4
5 N/A N/A N/A 5
6 NPS1 SPX 0 0
7 NPS1 SPX 0 0
8 NPS1 SPX 0 0
MEMORY_PARTITION:
GPU_ID MEMORY_PARTITION_CAPS CURRENT_MEMORY_PARTITION
0 N/A NPS1
1 N/A N/A
2 N/A N/A
3 N/A N/A
4 N/A N/A
5 N/A N/A
6 N/A NPS1
7 N/A NPS1
8 N/A NPS1
- Refactored amd_smi_drm_example.cc:
- Grouped partition changes and restores original partition settings.
- Now handles partitioned environments allowing example to continue even if some APIs are not supported in partitioned configurations.
- Modified amdsmi_asic_info_t (see amdsmi_get_gpu_asic_info()) to report OAM ID as N/A if 0xFFFFFFFF (was 0xFFFF).
Allows for better handling of OAM IDs in partitioned environments (DNE for non-primary nodes,
since its a physical identifier). Easier to handle in tests and example code (ie. now consistent w/ max size of the structure's value).
- Introduced amdsmi_RAII_open_FD() (internal API) to manage file descriptors using RAII, ensuring proper closure and preventing resource leaks.
Updated the following APIs to use this function:
- amdsmi_get_gpu_asic_info(), amdsmi_get_gpu_vram_usage(),
amdsmi_get_gpu_vram_info(), amdsmi_get_gpu_vbios_info(),
amdsmi_get_gpu_driver_info(), amdsmi_get_gpu_virtualization_mode()
- Updated AMD SMI test_base.cc/.h:
- Improved output and handling for partitioned environments.
- Added detailed ASIC information logging to align with structure changes.
- Enhanced error messages for better context before ASSERT checks.
- Resolved test failures in partitioned environments by updating
logic and handling for partition-specific configurations.
Fixed tests include:
- computepartition_read_write.cc, frequencies_read_write.cc,
gpu_metrics_read.cc, mem_util_read.cc, memorypartition_read_write.cc,
perf_level_read.cc, perf_level_read_write.cc, power_cap_read_write.cc,
power_read.cc, sys_info_read.cc, gpu_busy_read.cc
Change-Id: I36e903f8fddd714c74c719459c71aba8bbb77e6f
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Resetting head + adding fixes for tests ran in partitions
Change-Id: I0c1e9ac07488b50c95f3bc6d8a724e67d2c715dc
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
139 خطوط
4.6 KiB
C++
139 خطوط
4.6 KiB
C++
/*
|
|
* Copyright (c) Advanced Micro Devices, Inc. All rights reserved.
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
* of this software and associated documentation files (the "Software"), to deal
|
|
* in the Software without restriction, including without limitation the rights
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
* copies of the Software, and to permit persons to whom the Software is
|
|
* furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice shall be included in
|
|
* all copies or substantial portions of the Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
* THE SOFTWARE.
|
|
*/
|
|
|
|
#include <stdint.h>
|
|
#include <stddef.h>
|
|
#include <gtest/gtest.h>
|
|
|
|
#include <iostream>
|
|
#include <string>
|
|
#include <map>
|
|
|
|
#include "amd_smi/amdsmi.h"
|
|
#include "mem_util_read.h"
|
|
#include "../test_common.h"
|
|
#include "amd_smi/impl/amd_smi_utils.h"
|
|
|
|
TestMemUtilRead::TestMemUtilRead() : TestBase() {
|
|
set_title("Memory Utilization Read Test");
|
|
set_description("The Memory Utilization Read tests verifies that "
|
|
"memory busy percent, size and amount used can be read properly.");
|
|
}
|
|
|
|
TestMemUtilRead::~TestMemUtilRead(void) {
|
|
}
|
|
|
|
void TestMemUtilRead::SetUp(void) {
|
|
TestBase::SetUp();
|
|
|
|
return;
|
|
}
|
|
|
|
void TestMemUtilRead::DisplayTestInfo(void) {
|
|
TestBase::DisplayTestInfo();
|
|
}
|
|
|
|
void TestMemUtilRead::DisplayResults(void) const {
|
|
TestBase::DisplayResults();
|
|
return;
|
|
}
|
|
|
|
void TestMemUtilRead::Close() {
|
|
// This will close handles opened within rsmitst utility calls and call
|
|
// amdsmi_shut_down(), so it should be done after other hsa cleanup
|
|
TestBase::Close();
|
|
}
|
|
|
|
static const std::map<amdsmi_memory_type_t, const char *>
|
|
kDevMemoryTypeNameMap = {
|
|
{AMDSMI_MEM_TYPE_VRAM, "VRAM memory"},
|
|
{AMDSMI_MEM_TYPE_VIS_VRAM, "Visible VRAM memory"},
|
|
{AMDSMI_MEM_TYPE_GTT, "GTT memory"},
|
|
};
|
|
|
|
void TestMemUtilRead::Run(void) {
|
|
amdsmi_status_t err;
|
|
uint64_t total;
|
|
uint64_t usage;
|
|
|
|
TestBase::Run();
|
|
if (setup_failed_) {
|
|
std::cout << "** SetUp Failed for this test. Skipping.**" << std::endl;
|
|
return;
|
|
}
|
|
|
|
auto err_chk = [&](const char *str) {
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t** " << str << std::endl;
|
|
}
|
|
if (err != AMDSMI_STATUS_SUCCESS) {
|
|
if (err == AMDSMI_STATUS_FILE_ERROR ||
|
|
err == AMDSMI_STATUS_NOT_SUPPORTED) {
|
|
ASSERT_TRUE(err == AMDSMI_STATUS_NOT_SUPPORTED
|
|
|| err == AMDSMI_STATUS_FILE_ERROR);
|
|
} else {
|
|
CHK_ERR_ASRT(err)
|
|
}
|
|
}
|
|
};
|
|
|
|
for (uint32_t x = 0; x < num_iterations(); ++x) {
|
|
for (uint32_t i = 0; i < num_monitor_devs(); ++i) {
|
|
PrintDeviceHeader(processor_handles_[i]);
|
|
|
|
for (uint32_t mem_type = AMDSMI_MEM_TYPE_FIRST;
|
|
mem_type <= AMDSMI_MEM_TYPE_LAST; ++mem_type) {
|
|
err = amdsmi_get_gpu_memory_total(processor_handles_[i],
|
|
static_cast<amdsmi_memory_type_t>(mem_type), &total);
|
|
smi_amdgpu_get_status_string(err, false);
|
|
std::string mem_type_str =
|
|
kDevMemoryTypeNameMap.at(static_cast<amdsmi_memory_type_t>(mem_type));
|
|
std::string input_str =
|
|
"amdsmi_get_gpu_memory_total(" + mem_type_str + "): "
|
|
+ smi_amdgpu_get_status_string(err, false);
|
|
err_chk(input_str.c_str());
|
|
if (err != AMDSMI_STATUS_SUCCESS) {
|
|
continue;
|
|
}
|
|
|
|
err = amdsmi_get_gpu_memory_usage(processor_handles_[i],
|
|
static_cast<amdsmi_memory_type_t>(mem_type), &usage);
|
|
input_str =
|
|
"amdsmi_get_gpu_memory_usage(" + mem_type_str + "): "
|
|
+ smi_amdgpu_get_status_string(err, false);
|
|
err_chk(input_str.c_str());
|
|
if (err != AMDSMI_STATUS_SUCCESS) {
|
|
continue;
|
|
}
|
|
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t**" <<
|
|
kDevMemoryTypeNameMap.at(static_cast<amdsmi_memory_type_t>(mem_type))
|
|
<< " Calculated Utilization: " <<
|
|
(static_cast<float>(usage)*100)/static_cast<float>(total) << "% (" << usage <<
|
|
"/" << total << ")" << std::endl;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|