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>
142 wiersze
4.8 KiB
C++
142 wiersze
4.8 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 <map>
|
|
|
|
#include "amd_smi/amdsmi.h"
|
|
#include "perf_level_read_write.h"
|
|
#include "../test_common.h"
|
|
|
|
|
|
TestPerfLevelReadWrite::TestPerfLevelReadWrite() : TestBase() {
|
|
set_title("AMDSMI Performance Level Read/Write Test");
|
|
set_description("The Performance Level tests verify that the performance "
|
|
"level settings can be read and controlled properly.");
|
|
}
|
|
|
|
TestPerfLevelReadWrite::~TestPerfLevelReadWrite(void) {
|
|
}
|
|
|
|
void TestPerfLevelReadWrite::SetUp(void) {
|
|
TestBase::SetUp();
|
|
|
|
return;
|
|
}
|
|
|
|
void TestPerfLevelReadWrite::DisplayTestInfo(void) {
|
|
TestBase::DisplayTestInfo();
|
|
}
|
|
|
|
void TestPerfLevelReadWrite::DisplayResults(void) const {
|
|
TestBase::DisplayResults();
|
|
return;
|
|
}
|
|
|
|
void TestPerfLevelReadWrite::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();
|
|
}
|
|
|
|
|
|
void TestPerfLevelReadWrite::Run(void) {
|
|
amdsmi_status_t ret;
|
|
amdsmi_dev_perf_level_t pfl, orig_pfl;
|
|
|
|
TestBase::Run();
|
|
if (setup_failed_) {
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "** SetUp Failed for this test. Skipping.**" << std::endl;
|
|
}
|
|
return;
|
|
}
|
|
|
|
for (uint32_t dv_ind = 0; dv_ind < num_monitor_devs(); ++dv_ind) {
|
|
PrintDeviceHeader(processor_handles_[dv_ind]);
|
|
|
|
ret = amdsmi_get_gpu_perf_level(processor_handles_[dv_ind], &orig_pfl);
|
|
if (ret == AMDSMI_STATUS_NOT_SUPPORTED) {
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t**amdsmi_get_gpu_perf_level(): Not supported on this machine" << std::endl;
|
|
}
|
|
ASSERT_EQ(ret, AMDSMI_STATUS_NOT_SUPPORTED);
|
|
continue;
|
|
}
|
|
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t**Original Perf Level:"
|
|
<< GetPerfLevelStr(orig_pfl) << std::endl;
|
|
}
|
|
|
|
uint32_t pfl_i = static_cast<uint32_t>(AMDSMI_DEV_PERF_LEVEL_FIRST);
|
|
for (; pfl_i <= static_cast<uint32_t>(AMDSMI_DEV_PERF_LEVEL_LAST); pfl_i++) {
|
|
if (pfl_i == static_cast<uint32_t>(orig_pfl)) {
|
|
continue;
|
|
}
|
|
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "Set Performance Level to " <<
|
|
GetPerfLevelStr(static_cast<amdsmi_dev_perf_level_t>(pfl_i)) <<
|
|
" ..." << std::endl;
|
|
}
|
|
ret = amdsmi_set_gpu_perf_level(processor_handles_[dv_ind],
|
|
static_cast<amdsmi_dev_perf_level_t>(pfl_i));
|
|
if (ret == AMDSMI_STATUS_NOT_SUPPORTED) {
|
|
std::cout << "\t**" << GetPerfLevelStr(static_cast<amdsmi_dev_perf_level_t>(pfl_i))
|
|
<< " returned AMDSMI_STATUS_NOT_SUPPORTED" << std::endl;
|
|
} else {
|
|
CHK_ERR_ASRT(ret)
|
|
ret = amdsmi_get_gpu_perf_level(processor_handles_[dv_ind], &pfl);
|
|
CHK_ERR_ASRT(ret)
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t**New Perf Level:" << GetPerfLevelStr(pfl) <<
|
|
std::endl;
|
|
}
|
|
}
|
|
}
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "Reset Perf level to " << GetPerfLevelStr(orig_pfl) <<
|
|
" ..." << std::endl;
|
|
}
|
|
ret = amdsmi_set_gpu_perf_level(processor_handles_[dv_ind], orig_pfl);
|
|
if (ret == AMDSMI_STATUS_NOT_SUPPORTED) {
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t** Not supported on this machine" << std::endl;
|
|
}
|
|
continue;
|
|
}
|
|
CHK_ERR_ASRT(ret)
|
|
ret = amdsmi_get_gpu_perf_level(processor_handles_[dv_ind], &pfl);
|
|
CHK_ERR_ASRT(ret)
|
|
|
|
IF_VERB(STANDARD) {
|
|
std::cout << "\t**New Perf Level:" << GetPerfLevelStr(pfl) <<
|
|
std::endl;
|
|
}
|
|
}
|
|
}
|