Home
last modified time | relevance | path

Searched refs:GPU (Results 1 – 25 of 452) sorted by relevance

12345678910>>...19

/external/tensorflow/tensorflow/core/kernels/
Dconstant_op.cc100 REGISTER_KERNEL(GPU, Eigen::half);
101 REGISTER_KERNEL(GPU, bfloat16);
102 REGISTER_KERNEL(GPU, float);
103 REGISTER_KERNEL(GPU, double);
104 REGISTER_KERNEL(GPU, uint8);
105 REGISTER_KERNEL(GPU, int8);
106 REGISTER_KERNEL(GPU, qint8);
107 REGISTER_KERNEL(GPU, uint16);
108 REGISTER_KERNEL(GPU, int16);
109 REGISTER_KERNEL(GPU, qint16);
[all …]
Ddepthwise_conv_ops_test.cc36 enum class Device { CPU, GPU }; enumerator
40 if (device == Device::GPU) { in Run()
104 TEST_F(DepthwiseConvOpTest, DepthwiseConvFloatGpu) { Run<float>(Device::GPU); } in TEST_F()
106 Run<double>(Device::GPU); in TEST_F()
109 Run<Eigen::half>(Device::GPU); in TEST_F()
Dcwise_op_reciprocal.cc22 REGISTER4(UnaryOp, GPU, "Inv", functor::inverse, float, Eigen::half, double,
29 REGISTER3(SimpleBinaryOp, GPU, "InvGrad", functor::inverse_grad, float,
36 REGISTER4(UnaryOp, GPU, "Reciprocal", functor::inverse, float, Eigen::half,
46 REGISTER3(SimpleBinaryOp, GPU, "ReciprocalGrad", functor::inverse_grad, float,
Dcwise_op_div.cc31 REGISTER9(BinaryOp, GPU, "Div", functor::div, float, Eigen::half, double, uint8,
33 REGISTER4(BinaryOp, GPU, "TruncateDiv", functor::div, uint8, uint16, int16,
35 REGISTER5(BinaryOp, GPU, "RealDiv", functor::div, float, Eigen::half, double,
37 REGISTER2(BinaryOp, GPU, "DivNoNan", functor::div_no_nan, float, double);
Dcwise_op_igammas.cc24 REGISTER2(BinaryOp, GPU, "Igamma", functor::igamma, float, double);
25 REGISTER2(BinaryOp, GPU, "IgammaGradA", functor::igamma_grad_a, float, double);
26 REGISTER2(BinaryOp, GPU, "Igammac", functor::igammac, float, double);
Dsparse_xent_op.cc129 REGISTER(GPU, float, int32)
130 REGISTER(GPU, float, int64)
131 REGISTER(GPU, Eigen::half, int32)
132 REGISTER(GPU, Eigen::half, int64)
Dcwise_op_zeta.cc23 REGISTER2(BinaryOp, GPU, "Zeta", functor::zeta, float, double);
24 REGISTER2(BinaryOp, GPU, "Polygamma", functor::polygamma, float, double);
Dcwise_op_bessel.cc24 REGISTER3(UnaryOp, GPU, "BesselI0e", functor::bessel_i0e, Eigen::half, float,
26 REGISTER3(UnaryOp, GPU, "BesselI1e", functor::bessel_i1e, Eigen::half, float,
/external/tensorflow/tensorflow/compiler/tests/
Dlstm_layer_inference.pbtxt6 device: "/device:GPU:*"
31 device: "/device:GPU:*"
53 device: "/device:GPU:*"
76 device: "/device:GPU:*"
107 device: "/device:GPU:*"
120 device: "/device:GPU:*"
133 device: "/device:GPU:*"
144 device: "/device:GPU:*"
182 device: "/device:GPU:*"
214 device: "/device:GPU:*"
[all …]
/external/llvm/lib/Target/AMDGPU/
DAMDGPUSubtarget.cpp38 StringRef GPU, StringRef FS) { in initializeSubtargetDependencies() argument
53 ParseSubtargetFeatures(GPU, FullFS); in initializeSubtargetDependencies()
70 AMDGPUSubtarget::AMDGPUSubtarget(const Triple &TT, StringRef GPU, StringRef FS, in AMDGPUSubtarget() argument
72 : AMDGPUGenSubtargetInfo(TT, GPU, FS), in AMDGPUSubtarget()
119 InstrItins(getInstrItineraryForCPU(GPU)) { in AMDGPUSubtarget()
120 initializeSubtargetDependencies(TT, GPU, FS); in AMDGPUSubtarget()
181 R600Subtarget::R600Subtarget(const Triple &TT, StringRef GPU, StringRef FS, in R600Subtarget() argument
183 AMDGPUSubtarget(TT, GPU, FS, TM), in R600Subtarget()
188 SISubtarget::SISubtarget(const Triple &TT, StringRef GPU, StringRef FS, in SISubtarget() argument
190 AMDGPUSubtarget(TT, GPU, FS, TM), in SISubtarget()
DAMDGPUTargetMachine.cpp125 static StringRef getGPUOrDefault(const Triple &TT, StringRef GPU) { in getGPUOrDefault() argument
126 if (!GPU.empty()) in getGPUOrDefault()
127 return GPU; in getGPUOrDefault()
185 StringRef GPU = getGPUName(F); in getSubtargetImpl() local
188 SmallString<128> SubtargetKey(GPU); in getSubtargetImpl()
197 I = llvm::make_unique<R600Subtarget>(TargetTriple, GPU, FS, *this); in getSubtargetImpl()
226 StringRef GPU = getGPUName(F); in getSubtargetImpl() local
229 SmallString<128> SubtargetKey(GPU); in getSubtargetImpl()
238 I = llvm::make_unique<SISubtarget>(TargetTriple, GPU, FS, *this); in getSubtargetImpl()
/external/tensorflow/tensorflow/lite/g3doc/performance/
Dgpu.md1 # TensorFlow Lite GPU delegate
4 accelerators. This document describes how to preview the experimental GPU backend using the
11 resulting in lower latency. In the best scenario, inference on the GPU may now
17 Another benefit with GPU inference is its power efficiency. GPUs carry out the
23 …rimental GPU delegate is to follow the below tutorials, which go through building our classificati…
28 [Experimental GPU Delegate for Android](https://youtu.be/Xkhgre8r5G0) video.
38 #### Step 2. Edit `app/build.gradle` to use the experimental GPU AAR
54 enabling the GPU. Change from quantized to a float model and then click GPU to
55 run on the GPU.
62 [Experimental GPU Delegate for iOS](https://youtu.be/a5H4Zwjp49c) video.
[all …]
Dgpu_advanced.md1 # TensorFlow Lite on GPU
4 hardware accelerators. This document describes how to use the GPU backend using
8 ## Benefits of GPU Acceleration
17 on the GPU may run fast enough to become suitable for real-time applications
25 neural network on a GPU may eliminate this concern.
29 Another benefit that comes with GPU inference is its power efficiency. A GPU
35 TensorFlow Lite on GPU supports the following ops in 16-bit and 32-bit float
62 Run TensorFlow Lite on GPU with `TfLiteDelegate`. In Java, you can specify the
66 // NEW: Prepare GPU delegate.
84 To use TensorFlow Lite on GPU, get the GPU delegate via `NewGpuDelegate()` and
[all …]
Ddelegates.md15 Instead of relying on the CPU, some devices have hardware accelerators, such as GPU or DSP, that al…
18 ## Using the experimental GPU delegate
20 …sorFlow Lite provides an experimental GPU delegate that can be used to accelerate models on device…
22 …GPU delegate, see [TensorFlow Lite on GPU](https://www.tensorflow.org/lite/performance/gpu_advance…
/external/autotest/client/site_tests/graphics_GpuReset/
Dcontrol7 PURPOSE = 'Reset the GPU and check recovery mechanism.'
9 Detection of udev event notification of a GPU hang.
23 The purpose of this test is to exercise the GPU failure path. We craft an
24 erroneous GPU command packet and send it to the GPU, and wait for a udev
25 event notifying us of a GPU hang. If the event doesn't come back, the test
/external/tensorflow/tensorflow/core/protobuf/
Dconfig.proto17 // Fraction of the available GPU memory to allocate for each process.
18 // 1 means to allocate all of the GPU memory, 0.5 means the process
19 // allocates up to ~50% of the available GPU memory.
21 // GPU memory is pre-allocated unless the allow_growth option is enabled.
24 // the amount of memory available on the GPU device by using host memory as a
37 // GPU memory region, instead starting small and growing as needed.
40 // The type of GPU allocation strategy to use.
55 // A comma-separated list of GPU ids that determines the 'visible'
56 // to 'virtual' mapping of GPU devices. For example, if TensorFlow
57 // can see 8 GPU devices in the process, and one wanted to map
[all …]
/external/tensorflow/tensorflow/python/eager/
Dbenchmarks_test.py56 GPU = "/device:GPU:0" variable
173 if device == GPU:
205 self._benchmark_create_tensor([[3.0]], dtypes.float32.as_datatype_enum, GPU)
212 GPU)
218 self._benchmark_create_tensor([[3]], dtypes.int32.as_datatype_enum, GPU)
225 np.array([[3]], dtype=np.int32), dtypes.int32.as_datatype_enum, GPU)
263 with context.device(GPU):
275 with context.device(GPU):
491 with context.device(GPU):
499 with context.device(GPU):
[all …]
/external/swiftshader/third_party/llvm-7.0/llvm/lib/Target/AMDGPU/
DAMDGPUSubtarget.cpp48 StringRef GPU, StringRef FS) { in initializeSubtargetDependencies() argument
51 ParseSubtargetFeatures(GPU, FullFS); in initializeSubtargetDependencies()
68 StringRef GPU, StringRef FS) { in initializeSubtargetDependencies() argument
94 ParseSubtargetFeatures(GPU, FullFS); in initializeSubtargetDependencies()
145 GCNSubtarget::GCNSubtarget(const Triple &TT, StringRef GPU, StringRef FS, in GCNSubtarget() argument
147 AMDGPUGenSubtargetInfo(TT, GPU, FS), in GCNSubtarget()
211 InstrInfo(initializeSubtargetDependencies(TT, GPU, FS)), in GCNSubtarget()
447 R600Subtarget::R600Subtarget(const Triple &TT, StringRef GPU, StringRef FS, in R600Subtarget() argument
449 R600GenSubtargetInfo(TT, GPU, FS), in R600Subtarget()
462 TLInfo(TM, initializeSubtargetDependencies(TT, GPU, FS)), in R600Subtarget()
[all …]
/external/tensorflow/tensorflow/core/common_runtime/
Dring_gatherer_test.cc631 DEF_TEST(FLOAT, GPU, 1, 2, 1, 1, 0)
632 DEF_TEST(FLOAT, GPU, 1, 2, 1, 2, 0)
633 DEF_TEST(FLOAT, GPU, 1, 2, 1, 8, 0)
634 DEF_TEST(FLOAT, GPU, 1, 2, 1, 16, 0)
635 DEF_TEST(FLOAT, GPU, 1, 2, 1, 1001, 0)
636 DEF_TEST(FLOAT, GPU, 1, 8, 1, 1001, 0)
637 DEF_TEST(FLOAT, GPU, 1, 8, 1, 4096, 0)
638 DEF_TEST(FLOAT, GPU, 1, 8, 1, 4095, 0)
639 DEF_TEST(FLOAT, GPU, 1, 8, 1, 32768, 0)
640 DEF_TEST(FLOAT, GPU, 1, 4, 1, 32768, 0)
[all …]
Dring_reducer_test.cc712 DEF_TEST(FLOAT, GPU, 1, 2, 1, 1, 0)
713 DEF_TEST(FLOAT, GPU, 1, 2, 1, 2, 0)
714 DEF_TEST(FLOAT, GPU, 1, 2, 1, 8, 0)
715 DEF_TEST(FLOAT, GPU, 1, 2, 1, 16, 0)
716 DEF_TEST(FLOAT, GPU, 1, 2, 1, 1001, 0)
717 DEF_TEST(FLOAT, GPU, 1, 8, 1, 1001, 0)
718 DEF_TEST(FLOAT, GPU, 1, 8, 1, 4096, 0)
719 DEF_TEST(FLOAT, GPU, 1, 8, 3, 4095, 0)
720 DEF_TEST(FLOAT, GPU, 1, 8, 3, 1045991, 0)
721 DEF_TEST(FLOAT, GPU, 1, 4, 4, 1045991, 0)
[all …]
/external/skia/resources/lua/
Dslides_content2.lua53 - SkImageFilter w/ CPU and GPU implementations
81 - GPU optimizations
95 - GPU
107 - GPU
/external/skqp/platform_tools/android/apps/skqp/src/main/assets/resources/lua/
Dslides_content2.lua53 - SkImageFilter w/ CPU and GPU implementations
81 - GPU optimizations
95 - GPU
107 - GPU
/external/skqp/resources/lua/
Dslides_content2.lua53 - SkImageFilter w/ CPU and GPU implementations
81 - GPU optimizations
95 - GPU
107 - GPU
/external/eigen/bench/tensors/
DREADME3 … suite, in which each benchmark comes in 2 flavors: one that runs on CPU, and one that runs on GPU.
8 To compile the floating point GPU benchmarks, simply call:
11 …GPU tensor benchmarks that uses half floats (aka fp16) instead of regular floats. To compile these…
/external/tensorflow/tensorflow/compiler/xla/service/gpu/
Dbackend_configs.proto5 // Backend configs for XLA:GPU.
7 // These are metadata that the GPU backend attaches to HloInstrucitons and later
24 // true, cudnn may choose not to use tensor cores, e.g. because the GPU or

12345678910>>...19