* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.
* rocDecode/HEVC: Changed variable naming to Google style.
* rocDecode/HEVC: Added VPS, SPS, PPS, and slice segment header content logging functions for debug purposes.
* rocDecode/HEVC: Compacted opening bracket lines to keep coding style consistency.
* * rocDecode/HEVC: Fixed an issue in profile-tier-level parsing where 44 bits are skipped in an incorrect way using ReadBits() which can only consume 32 bits max. Also formated SPS parsing code by using pointer instead of array element.
* * rocDecode/HEVC: Fixed the incorrect array size for sps_max_dec_pic_buffering_minus1, sps_max_num_reorder_pics and sps_max_num_reorder_pics in SPS structure define.
* * rocDecode/HEVC: Modified scaling list parsing to make sure we explicitly follow the spec.
* * rocDecode/HEVC: Added a few syntax elements to short team RPS structure, updated RPS parsing function and logging function.
* * rocDecode/HEVC: In PPS parsing function, use structure pointer instead of structure array element to improve coding clarity.
* * rocDecode/HEVC: Compacted the opening bracket lines. No functional changes.
* * rocDecode/HEVC: Added full parsing of slice segment header. Added PPS range extension parsing.
* * rocDecode/HEVC: Fixed a build error in debug mode due to merging from master branch: removing a redundant debug function.
* * rocDecode/HEVC: Changed the condition for sequence call back from picture size change to more general case where a new SPS is activated. Also moved the call from slice header parsing to upper level where frame data is processed.
* * rocDecode: Compacted opening bracket line. No functional changes.
[ROCm/rocdecode commit: 88a34e4db0]
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.
* rocDecode/HEVC: Changed variable naming to Google style.
* rocDecode/HEVC: Added VPS, SPS, PPS, and slice segment header content logging functions for debug purposes.
* rocDecode/HEVC: Compacted opening bracket lines to keep coding style consistency.
* * rocDecode/HEVC: Fixed an issue in profile-tier-level parsing where 44 bits are skipped in an incorrect way using ReadBits() which can only consume 32 bits max. Also formated SPS parsing code by using pointer instead of array element.
* * rocDecode/HEVC: Fixed the incorrect array size for sps_max_dec_pic_buffering_minus1, sps_max_num_reorder_pics and sps_max_num_reorder_pics in SPS structure define.
* * rocDecode/HEVC: Modified scaling list parsing to make sure we explicitly follow the spec.
* * rocDecode/HEVC: Added a few syntax elements to short team RPS structure, updated RPS parsing function and logging function.
* * rocDecode/HEVC: In PPS parsing function, use structure pointer instead of structure array element to improve coding clarity.
* * rocDecode/HEVC: Compacted the opening bracket lines. No functional changes.
* * rocDecode/HEVC: Added full parsing of slice segment header. Added PPS range extension parsing.
* * rocDecode/HEVC: Fixed a build error in debug mode due to merging from master branch: removing a redundant debug function.
* * rocDecode/HEVC: Changed the condition for sequence call back from picture size change to more general case where a new SPS is activated. Also moved the call from slice header parsing to upper level where frame data is processed.
* * rocDecode: Compacted opening bracket line. No functional changes.
Move context allocation into Device::init() method to simplify the logic and handle
HIP_VISIBLE_DEVICES properly
Change-Id: I0fc6f37c7ae39bedbdad0290295d6794c66d6c54
[ROCm/clr commit: a49d633883]
Move context allocation into Device::init() method to simplify the logic and handle
HIP_VISIBLE_DEVICES properly
Change-Id: I0fc6f37c7ae39bedbdad0290295d6794c66d6c54
* Updates:
- [API/CLI] rsmi_dev_*_partition_set &
rsmi_dev_*_partition_reset - exposed RSMI_STATUS_BUSY for
EBUSY writes + cleaned up accidental map insertions
(maplookup[] can insert values that are not in the map,
map.at(key) fixes this potential issue)
- [API] rsmi_dev_gpu_metrics_info_get() - returns
RSMI_STATUS_NOT_SUPPORTED for unsupported metric tables
outside of 1v1/1v2/1v3
- [API] writeDevInfoStr() - exposes RSMI_STATUS_BUSY for
EBUSY write errors; kept backward compatibility
for other writes which do not care about these states
- [API] rsmi_dev_od_volt_info_get()
& rsmi_dev_od_volt_curve_regions_get() have better logging
+ Expose more details on why they are erroring
- [Utils/logs/example] Expose AMD GPU gfx target version to aid in
system troubleshooting
- [Utils] Added test methods that look at od volt
freq & regions into here - for easier access across
several tests
- [Utils] Updated getRSMIStatusString(new argument - fullstatus;
default to true for backwards compatibility)
-> true shows shortened RSMI STATUS response
- [Utils] Added splitString to cut out noisy return responses
(used in getRSMIStatusString(), when fullstatus = true)
- [Utils] Added getFileCreationDate() to expose build date
of the library - helpful for local builds or experimental builds
- [Utils] Macro cleanup
- [Example] Added a few gpu_metric checks - helpful for upcoming
updates
- [Device] SYSFS/DebugFS - now have better r/w displayed in logs
- [LOGS] Expose library build date - see above for details
- [Tests] Add more warnings/errors to test builds
- [Tests] Moved up Partition tests for ordered test runs - helped
identify issues with GPU BUSY writes
- [Tests] compute_partition_read_write - handles RSMI_STATUS_BUSY
with waits for busy status found & cleaned up how we checked
for partition changes - with RSMI responses exposed more clearly
- [Tests] perf_determinism - multi gpu now properly runs through
with full resets as needed
- [Tests] volt_freq_curv_read - better error handling with more
verbose output
Change-Id: Ie94c6abb6a9aab95c345996d3ad3843cf6734977
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
* Updates:
- [API/CLI] rsmi_dev_*_partition_set &
rsmi_dev_*_partition_reset - exposed RSMI_STATUS_BUSY for
EBUSY writes + cleaned up accidental map insertions
(maplookup[] can insert values that are not in the map,
map.at(key) fixes this potential issue)
- [API] rsmi_dev_gpu_metrics_info_get() - returns
RSMI_STATUS_NOT_SUPPORTED for unsupported metric tables
outside of 1v1/1v2/1v3
- [API] writeDevInfoStr() - exposes RSMI_STATUS_BUSY for
EBUSY write errors; kept backward compatibility
for other writes which do not care about these states
- [API] rsmi_dev_od_volt_info_get()
& rsmi_dev_od_volt_curve_regions_get() have better logging
+ Expose more details on why they are erroring
- [Utils/logs/example] Expose AMD GPU gfx target version to aid in
system troubleshooting
- [Utils] Added test methods that look at od volt
freq & regions into here - for easier access across
several tests
- [Utils] Updated getRSMIStatusString(new argument - fullstatus;
default to true for backwards compatibility)
-> true shows shortened RSMI STATUS response
- [Utils] Added splitString to cut out noisy return responses
(used in getRSMIStatusString(), when fullstatus = true)
- [Utils] Added getFileCreationDate() to expose build date
of the library - helpful for local builds or experimental builds
- [Utils] Macro cleanup
- [Example] Added a few gpu_metric checks - helpful for upcoming
updates
- [Device] SYSFS/DebugFS - now have better r/w displayed in logs
- [LOGS] Expose library build date - see above for details
- [Tests] Add more warnings/errors to test builds
- [Tests] Moved up Partition tests for ordered test runs - helped
identify issues with GPU BUSY writes
- [Tests] compute_partition_read_write - handles RSMI_STATUS_BUSY
with waits for busy status found & cleaned up how we checked
for partition changes - with RSMI responses exposed more clearly
- [Tests] perf_determinism - multi gpu now properly runs through
with full resets as needed
- [Tests] volt_freq_curv_read - better error handling with more
verbose output
Change-Id: Ie94c6abb6a9aab95c345996d3ad3843cf6734977
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: 57b6135e54]
* Updates:
- [API/CLI] rsmi_dev_*_partition_set &
rsmi_dev_*_partition_reset - exposed RSMI_STATUS_BUSY for
EBUSY writes + cleaned up accidental map insertions
(maplookup[] can insert values that are not in the map,
map.at(key) fixes this potential issue)
- [API] rsmi_dev_gpu_metrics_info_get() - returns
RSMI_STATUS_NOT_SUPPORTED for unsupported metric tables
outside of 1v1/1v2/1v3
- [API] writeDevInfoStr() - exposes RSMI_STATUS_BUSY for
EBUSY write errors; kept backward compatibility
for other writes which do not care about these states
- [API] rsmi_dev_od_volt_info_get()
& rsmi_dev_od_volt_curve_regions_get() have better logging
+ Expose more details on why they are erroring
- [Utils/logs/example] Expose AMD GPU gfx target version to aid in
system troubleshooting
- [Utils] Added test methods that look at od volt
freq & regions into here - for easier access across
several tests
- [Utils] Updated getRSMIStatusString(new argument - fullstatus;
default to true for backwards compatibility)
-> true shows shortened RSMI STATUS response
- [Utils] Added splitString to cut out noisy return responses
(used in getRSMIStatusString(), when fullstatus = true)
- [Utils] Added getFileCreationDate() to expose build date
of the library - helpful for local builds or experimental builds
- [Utils] Macro cleanup
- [Example] Added a few gpu_metric checks - helpful for upcoming
updates
- [Device] SYSFS/DebugFS - now have better r/w displayed in logs
- [LOGS] Expose library build date - see above for details
- [Tests] Add more warnings/errors to test builds
- [Tests] Moved up Partition tests for ordered test runs - helped
identify issues with GPU BUSY writes
- [Tests] compute_partition_read_write - handles RSMI_STATUS_BUSY
with waits for busy status found & cleaned up how we checked
for partition changes - with RSMI responses exposed more clearly
- [Tests] perf_determinism - multi gpu now properly runs through
with full resets as needed
- [Tests] volt_freq_curv_read - better error handling with more
verbose output
Change-Id: Ie94c6abb6a9aab95c345996d3ad3843cf6734977
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 57b6135e54]
The src/core/isa_capture/code_object_track.cpp file includes the
amd-dbgapi header but does not use the library (and is not configured to
use the library).
Remove the unused import.
Change-Id: Icc6c46a1f52355e9e5631395dfad1b44365bdca4
The src/core/isa_capture/code_object_track.cpp file includes the
amd-dbgapi header but does not use the library (and is not configured to
use the library).
Remove the unused import.
Change-Id: Icc6c46a1f52355e9e5631395dfad1b44365bdca4
[ROCm/rocprofiler commit: 372fc3910b]
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.
* rocDecode/HEVC: Changed variable naming to Google style.
* rocDecode/HEVC: Added VPS, SPS, PPS, and slice segment header content logging functions for debug purposes.
* rocDecode/HEVC: Compacted opening bracket lines to keep coding style consistency.
* * rocDecode/HEVC: Fixed an issue in profile-tier-level parsing where 44 bits are skipped in an incorrect way using ReadBits() which can only consume 32 bits max. Also formated SPS parsing code by using pointer instead of array element.
* * rocDecode/HEVC: Fixed the incorrect array size for sps_max_dec_pic_buffering_minus1, sps_max_num_reorder_pics and sps_max_num_reorder_pics in SPS structure define.
* * rocDecode/HEVC: Modified scaling list parsing to make sure we explicitly follow the spec.
* * rocDecode/HEVC: Added a few syntax elements to short team RPS structure, updated RPS parsing function and logging function.
* * rocDecode/HEVC: In PPS parsing function, use structure pointer instead of structure array element to improve coding clarity.
* * rocDecode/HEVC: Compacted the opening bracket lines. No functional changes.
* * rocDecode/HEVC: Added full parsing of slice segment header. Added PPS range extension parsing.
* * rocDecode/HEVC: Fixed a build error in debug mode due to merging from master branch: removing a redundant debug function.
[ROCm/rocdecode commit: 298d8e3a8f]
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.
* rocDecode/HEVC: Changed variable naming to Google style.
* rocDecode/HEVC: Added VPS, SPS, PPS, and slice segment header content logging functions for debug purposes.
* rocDecode/HEVC: Compacted opening bracket lines to keep coding style consistency.
* * rocDecode/HEVC: Fixed an issue in profile-tier-level parsing where 44 bits are skipped in an incorrect way using ReadBits() which can only consume 32 bits max. Also formated SPS parsing code by using pointer instead of array element.
* * rocDecode/HEVC: Fixed the incorrect array size for sps_max_dec_pic_buffering_minus1, sps_max_num_reorder_pics and sps_max_num_reorder_pics in SPS structure define.
* * rocDecode/HEVC: Modified scaling list parsing to make sure we explicitly follow the spec.
* * rocDecode/HEVC: Added a few syntax elements to short team RPS structure, updated RPS parsing function and logging function.
* * rocDecode/HEVC: In PPS parsing function, use structure pointer instead of structure array element to improve coding clarity.
* * rocDecode/HEVC: Compacted the opening bracket lines. No functional changes.
* * rocDecode/HEVC: Added full parsing of slice segment header. Added PPS range extension parsing.
* * rocDecode/HEVC: Fixed a build error in debug mode due to merging from master branch: removing a redundant debug function.