You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: TESTS.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -137,7 +137,7 @@ RemoteAccessMemoryMaxSaturation|Uses stream memory write to measure max data bus
137
137
SLM_DataAccessLatency|generates SLM local memory transactions inside thread group to measure latency between reads (uses Intel only private intel_get_cycle_counter() )|<ul><li>--direction write or read mode (0 or 1)</li><li>--occupancyDiv H/W load divider by 8, 4, 2, full occupancy</li><li>--size SLM Size</li></ul>|:x:|:heavy_check_mark:|
138
138
SlmSwitchLatency|Enqueues 2 kernels with different SLM size. Measures switch time between these kernels.|<ul><li>--firstSlmSize Size of the shared local memory per thread group. First kernel.</li><li>--secondSlmSize Size of the shared local memory per thread group. Second kernel.</li><li>--wgs Size of the work group.</li></ul>|:heavy_check_mark:|:x:|
139
139
StreamAfterTransfer|Goal of this test is to measure how stream kernels perform right after host to device transfer populating the data. Test does clean caches, then emits transfers and then follows with stream kernel and measures GPU execution time of it.|<ul><li>--size Size of the memory to stream. Must be divisible by datatype size.</li><li>--type Memory streaming type (Read or Write or Scale or Triad)</li><li>--useEvents Perform GPU-side measurements using events (0 or 1)</li></ul>|:x:|:heavy_check_mark:|
140
-
StreamMemory|Streams memory inside of kernel in a fashion described by 'type'. Copy means one memory location is read from and the second one is written to. Triad means two buffers are read and one is written to. In read and write memory is only read or written to.|<ul><li>--contents Buffer contents zeros/random (Zeros or Random)</li><li>--memoryPlacement Memory type used for stream (Device or Host or Shared or non-USM-mapped or non-USMmisaligned or non-USM4KBAligned or non-USM2MBAligned or non-USMmisaligned-imported or non-USM4KBAligned-imported or non-USM2MBAligned-imported)</li><li>--multiplier multiplies id used for accessing the resources to simulate partials</li><li>--size Size of the memory to stream. Must be divisible by datatype size.</li><li>--type Memory streaming type (Read or Write or Scale or Triad)</li><li>--useEvents Perform GPU-side measurements using events (0 or 1)</li></ul>|:heavy_check_mark:|:heavy_check_mark:|
140
+
StreamMemory|Streams memory inside of kernel in a fashion described by 'type'. Copy means one memory location is read from and the second one is written to. Triad means two buffers are read and one is written to. In read and write memory is only read or written to.|<ul><li>--contents Buffer contents zeros/random (Zeros or Random)</li><li>--memoryPlacement Memory type used for stream (Device or Host or Shared or non-USM-mapped or non-USMmisaligned or non-USM4KBAligned or non-USM2MBAligned or non-USMmisaligned-imported or non-USM4KBAligned-imported or non-USM2MBAligned-imported)</li><li>--multiplier multiplies id used for accessing the resources to simulate partials</li><li>--size Size of the memory to stream. Must be divisible by datatype size.</li><li>--type Memory streaming type (Read or Write or Scale or Triad)</li><li>--useEvents Perform GPU-side measurements using events (0 or 1)</li><li>--vectorSize size of uint vector type 1/2/4/8/16</li></ul>|:heavy_check_mark:|:heavy_check_mark:|
141
141
StreamMemoryImmediate|Streams memory inside of kernel in a fashion described by 'type' using immediate command list. Copy means one memory location is read from and the second one is written to. Triad means two buffers are read and one is written to. In read and write memory is only read or written to.|<ul><li>--size Size of the memory to stream. Must be divisible by datatype size.</li><li>--type Memory streaming type (Read or Write or Scale or Triad)</li><li>--useEvents Perform GPU-side measurements using events (0 or 1)</li></ul>|:heavy_check_mark:|:x:|
142
142
UnmapBuffer|allocates an OpenCL buffer and measures unmap bandwidth. Unmapping operation meansmemory transfer from CPU to GPU or a no-op, depending on map flags.|<ul><li>--compressed Select if the buffer is to be compressed. Will be skipped, if device does not support compression (0 or 1)</li><li>--contents Contents of the buffer (Zeros or Random)</li><li>--mapFlags OpenCL map flags passed during memory mapping (Read or Write or WriteInvalidate)</li><li>--size Size of the buffer</li><li>--useEvents Perform GPU-side measurements using events (0 or 1)</li></ul>|:x:|:heavy_check_mark:|
143
143
UsmConcurrentCopy|allocates four unified shared memory buffers, 2 in device memory and 2 in host memory. Measures concurrent copy bandwidth between them.|<ul><li>--d2hEngine Engine used for device to host copy (RCS or CCS0 or CCS1 or CCS2 or CCS3 or BCS or BCS1 or BCS2 or BCS3 or BCS4 or BCS5 or BCS6 or BCS7 or BCS8)</li><li>--h2dEngine Engine used for host to device copy (RCS or CCS0 or CCS1 or CCS2 or CCS3 or BCS or BCS1 or BCS2 or BCS3 or BCS4 or BCS5 or BCS6 or BCS7 or BCS8)</li><li>--size Size of the buffer</li></ul>|:heavy_check_mark:|:x:|
if (auto result = ProgramHelperOcl::buildProgramFromSourceFile(opencl.context, opencl.device, programName, compilerOptions.str().c_str(), program); result != TestResult::Success) {
0 commit comments