| /external/tensorflow/tensorflow/core/profiler/g3doc/ |
| D | advise.md | 43 top 1 operation type: SoftmaxCrossEntropyWithLogits, cpu: 1.37sec, accelerator: 0us, total: 1.37sec…
44 top 2 operation type: MatMul, cpu: 427.39ms, accelerator: 280.76ms, total: 708.14ms (13.83%)
45 top 3 operation type: ConcatV2, cpu: 357.83ms, accelerator: 31.80ms, total: 389.63ms (7.61%)
46 seq2seq_attention_model.py:360:build_graph:self._add_seq2seq(), cpu: 3.16sec, accelerator: 214.84ms…
47 …seq2seq_attention_model.py:293:_add_seq2seq:decoder_outputs, ..., cpu: 2.46sec, accelerator: 3.25m…
48 …seq2seq_lib.py:181:sampled_sequence_...:average_across_ti..., cpu: 2.46sec, accelerator: 3.24ms, t…
49 …seq2seq_lib.py:147:sequence_loss_by_...:crossent = loss_f..., cpu: 2.46sec, accelerator: 3.06ms, t…
50 …ntion_model.py:289:sampled_loss_func:num_classes=vsize), cpu: 2.46sec, accelerator: 3.06ms, total:…
51 …ntion_model.py:282:sampled_loss_func:labels = tf.resha..., cpu: 164us, accelerator: 0us, total: 16…
52 …seq2seq_lib.py:148:sequence_loss_by_...:log_perp_list.app..., cpu: 1.33ms, accelerator: 120us, tot…
[all …]
|
| D | profile_time.md | 12 in the graph. An operation can be placed on an accelerator or on CPU.
16 When an operation is placed on accelerator, it will first be scheduled
19 accelerator. While some computation (e.g. pre-processing) is still done
20 in CPU. OpKernel::Compute can dispatch computation on accelerator
21 and return, or it can also wait for the accelerator to finish.
25 * <b>accelerator_micros</b>, which is the part of computation time spent on accelerator.
30 Since accelerator, such as GPU, usually runs operation asynchronously, you
32 accelerator.
|
| D | python_api.md | 54 # Note: When run on accelerator (e.g. GPU), an operation might perform some
55 # cpu computation, enqueue the accelerator computation. The accelerator
57 # times: 1) accelerator computation. 2) cpu computation (might wait on
58 # accelerator). 3) the sum of 1 and 2.
|
| D | options.md | 47 Each accelerator usually performs massive parallel processing. The profiler
51 micros: This is the sum of cpu and accelerator times.
52 accelerator_micros: This is the accelerator times.
87 accelerator_micros and cpu_micros. Note: cpu and accelerator can run in parallel.
89 …cros`: Show nodes that spend at least this number of microseconds to run on accelerator (e.g. GPU).
|
| /external/tensorflow/tensorflow/core/profiler/ |
| D | README.md | 16 * accelerator utilization check
142 node name | requested bytes | total execution time | accelerator execution time | cpu execution tim…
174 top 1 operation type: SoftmaxCrossEntropyWithLogits, cpu: 1.37sec, accelerator: 0us, total: 1.37sec…
175 top 2 operation type: MatMul, cpu: 427.39ms, accelerator: 280.76ms, total: 708.14ms (13.83%)
176 top 3 operation type: ConcatV2, cpu: 357.83ms, accelerator: 31.80ms, total: 389.63ms (7.61%)
177 …quence_loss_by_example/SoftmaxCrossEntropyWithLogits_11, cpu: 89.92ms, accelerator: 0us, total: 89…
178 …train_step/update_seq2seq/output_projection/w/ApplyAdam, cpu: 84.52ms, accelerator: 0us, total: 84…
179 …quence_loss_by_example/SoftmaxCrossEntropyWithLogits_19, cpu: 73.02ms, accelerator: 0us, total: 73…
180 seq2seq_attention_model.py:360:build_graph:self._add_seq2seq(), cpu: 3.16sec, accelerator: 214.84ms…
181 …seq2seq_attention_model.py:293:_add_seq2seq:decoder_outputs, ..., cpu: 2.46sec, accelerator: 3.25m…
[all …]
|
| D | tfprof_log.proto | 57 // Whether or not the TF device tracer fails to return accelerator
58 // information (which could lead to 0 accelerator execution time).
105 // For accelerator, vector size can be larger than 1, multiple kernel fires
|
| /external/swiftshader/third_party/llvm-7.0/llvm/test/tools/dsymutil/X86/ |
| D | accelerator.test | 1 RUN: dsymutil -accelerator=Dwarf -oso-prepend-path=%p/.. %p/../Inputs/basic.macho.x86_64 -o %t.dwar…
2 RUN: dsymutil -accelerator=Apple -oso-prepend-path=%p/.. %p/../Inputs/basic.macho.x86_64 -o %t.appl…
10 RUN: dsymutil -update -accelerator=Dwarf %t.apple.dSYM
11 RUN: dsymutil -update -accelerator=Apple %t.dwarf.dSYM
|
| /external/swiftshader/third_party/llvm-7.0/llvm/test/DebugInfo/X86/ |
| D | accel-tables.ll | 1 ; Verify the emission of accelerator tables for various targets for the DWARF<=4 case
15 ; No accelerator tables if type units are enabled, as DWARF v4 type units are
16 ; not compatible with accelerator tables.
21 ; accelerator table generation.
|
| D | accel-tables-dwarf5.ll | 1 ; Verify the emission of accelerator tables for the DWARF v5 case.
20 ; accelerator table generation.
|
| /external/swiftshader/third_party/llvm-7.0/llvm/test/DebugInfo/ |
| D | dwarfdump-accel.test | 4 Gather some DIE indexes to verify the accelerator table contents.
59 Check that an empty accelerator section is handled correctly.
71 Verify the debug info in the apple_names accelerator table.
|
| /external/v4l2_codec2/vda/ |
| D | vp9_decoder.cc | 20 VP9Decoder::VP9Decoder(VP9Accelerator* accelerator) in VP9Decoder() argument
22 accelerator_(accelerator), in VP9Decoder()
23 parser_(accelerator->IsFrameContextRequired()) { in VP9Decoder()
|
| D | vp8_decoder.cc | 14 VP8Decoder::VP8Decoder(VP8Accelerator* accelerator) in VP8Decoder() argument
18 accelerator_(accelerator) { in VP8Decoder()
|
| D | vp8_decoder.h | 68 VP8Decoder(VP8Accelerator* accelerator);
|
| D | vp9_decoder.h | 96 explicit VP9Decoder(VP9Accelerator* accelerator);
|
| /external/u-boot/lib/rsa/ |
| D | Kconfig | 31 bool "Enable RSA Modular Exponentiation with FSL crypto accelerator"
35 accelerator - CAAM.
|
| /external/swiftshader/third_party/llvm-7.0/llvm/docs/CommandGuide/ |
| D | dsymutil.rst | 45 accelerator tables to be removed.
90 Update an existing dSYM file to contain the latest accelerator tables and
92 '.apple_types' hashed accelerator tables.
|
| D | llvm-dwarfdump.rst | 40 Search for the exact text <name> in the accelerator tables
42 When there is no accelerator tables or the name of the DIE
43 you are looking for is not found in the accelerator tables,
|
| /external/llvm/test/DebugInfo/ |
| D | dwarfdump-accel.test | 3 Gather some DIE indexes to verify the accelerator table contents.
55 Check that an empty accelerator section is handled correctly.
|
| /external/swiftshader/third_party/llvm-7.0/llvm/test/tools/llvm-dwarfdump/X86/ |
| D | apple_types_verify_tag.s | 6 # CHECK-NEXT: error: Tag DW_TAG_ptr_to_member_type in accelerator table does not match Tag DW_TAG_b…
121 ….short 31 ## error: Tag DW_TAG_ptr_to_member_type in accelerator table does not match Tag DW_…
|
| /external/swiftshader/third_party/llvm-7.0/llvm/test/tools/llvm-rc/ |
| D | tag-accelerators.test | 133 ; CARET1-NEXT: Accelerator ID 100: No character following '^' in accelerator event
145 ; CARET3-NEXT: Accelerator ID 10: VIRTKEY accelerator events can't be preceded by '^'
151 ; NONALPHA1-NEXT: Accelerator ID 1: Control character accelerator event should be alphabetic
|
| /external/tensorflow/tensorflow/contrib/tfprof/ |
| D | README.md | 14 * accelerator utilization check
|
| /external/tensorflow/tensorflow/contrib/eager/python/examples/pix2pix/ |
| D | pix2pix_eager.ipynb | 29 "accelerator": "GPU",
|
| /external/swiftshader/third_party/llvm-7.0/llvm/test/tools/dsymutil/ |
| D | cmdline.test | 8 HELP: -accelerator
|
| /external/autotest/client/site_tests/camera_HAL3/ |
| D | control.jea | 9 PURPOSE = "Verify Jpeg encode accelerator works in USB HALv3."
|
| D | control.jda | 9 PURPOSE = "Verify Jpeg decode accelerator works in USB HALv3."
|