| /external/arm-trusted-firmware/docs/plat/ |
| D | nvidia-tegra.rst | 4 - .. rubric:: T194
7 T194 has eight NVIDIA Carmel CPU cores in a coherent multi-processor
8 configuration. The Carmel cores support the ARM Architecture version 8.2,
9 executing both 64-bit AArch64 code, and 32-bit AArch32 code. The Carmel
10 processors are organized as four dual-core clusters, where each cluster has
11 a dedicated 2 MiB Level-2 unified cache. A high speed coherency fabric connects
12 these processor complexes and allows heterogeneous multi-processing with all
13 eight cores if required.
15 - .. rubric:: T186
18 The NVIDIA® Parker (T186) series system-on-chip (SoC) delivers a heterogeneous
[all …]
|
| D | rpi3.rst | 4 The `Raspberry Pi 3`_ is an inexpensive single-board computer that contains four
5 Arm Cortex-A53 cores.
7 The following instructions explain how to use this port of the TF-A with the
11 port of TF-A can't boot a AArch64 kernel. The `Linux tree fork`_ maintained by
16 which is available from both the Non-secure and Secure worlds. This port
21 ------
25 card) and is located between all Arm cores and the DRAM. Check the `Raspberry Pi
30 the cores boot in AArch64 mode.
34 - If a file called ``kernel8.img`` is located on the ``boot`` partition of the
38 - If there is also a file called ``armstub8.bin``, it will load it at address
[all …]
|
| D | brcm-stingray.rst | 5 -----------
6 Broadcom's Stingray(BCM958742t) is a multi-core processor with 8 Cortex-A72 cores.
7 Trusted Firmware-A (TF-A) is used to implement secure world firmware, supporting
14 -------------
16 Bootrom --> TF-A BL2 --> TF-A BL31 --> BL33(u-boot)
20 - Trusted Firmware-A:
21 `link <https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/>`__
24 ------------
29 - Prepare AARCH64 toolchain.
31 - Build u-boot first, and get the binary image: u-boot.bin,
[all …]
|
| /external/eigen/doc/ |
| D | TopicMultithreading.dox | 3 /** \page TopicMultiThreading Eigen and multi-threading
7 Some %Eigen's algorithms can exploit the multiple cores present in your hardware.
9 - GCC: \c -fopenmp
10 - ICC: \c -openmp
11 - MSVC: check the respective option in the build properties.
25 You can disable %Eigen's multi threading at compile time by defining the \link TopicPreprocessorDir…
27 Currently, the following algorithms can make use of multi-threading:
28 - general dense matrix - matrix products
29 - PartialPivLU
30 - row-major-sparse * dense vector/matrix products
[all …]
|
| /external/cpuinfo/src/x86/ |
| D | topology.c | 24 * HTT: indicates multi-core/hyper-threading support on this core. in cpuinfo_x86_detect_topology()
25 * - Intel, AMD: edx[bit 28] in basic info. in cpuinfo_x86_detect_topology()
36 * CmpLegacy: core multi-processing legacy mode. in cpuinfo_x86_detect_topology()
37 * - AMD: ecx[bit 1] in extended info (reserved bit on Intel CPUs). in cpuinfo_x86_detect_topology()
45 * NC: number of physical cores - 1. The number of cores in the processor is NC+1. in cpuinfo_x86_detect_topology()
46 * - AMD: ecx[bits 0-7] in leaf 0x80000008 (reserved zero bits on Intel CPUs). in cpuinfo_x86_detect_topology()
49 topology->core_bits_length = bit_length(cores_per_processor); in cpuinfo_x86_detect_topology()
50 …cpuinfo_log_debug("HTT: APIC ID = %08"PRIx32", cores per processor = %"PRIu32, apic_id, cores_per_… in cpuinfo_x86_detect_topology()
53 * LogicalProcessorCount: the number of cores per processor. in cpuinfo_x86_detect_topology()
54 * - AMD: ebx[bits 16-23] in basic info (different interpretation on Intel CPUs). in cpuinfo_x86_detect_topology()
[all …]
|
| /external/tensorflow/tensorflow/dtensor/python/ |
| D | tpu_util.py | 7 # http://www.apache.org/licenses/LICENSE-2.0
15 """TPU-specific utilities for DTensor."""
52 # `_topology.device_coordinates` maps TF task-device ordinals to TPU core IDs.
55 # Cache core ID <-> location mappings so we need not make repeated C++ calls.
56 # Both are indexed by TF task-device ordinals.
96 # User can specify local_device_ids or use default list for multi host.
106 num_devices_per_task: int) -> topology.Topology:
111 and then by per-task device ordinals.
154 calling `dtensor.initialize_multi_client` to initialize multi-client DTensor.
156 variables that controls the initialization of multi-client DTensor.
[all …]
|
| /external/grpc-grpc/src/python/grpcio_tests/tests/qps/ |
| D | worker_server.py | 7 # http://www.apache.org/licenses/LICENSE-2.0
44 cores = multiprocessing.cpu_count()
47 yield self._get_server_status(start_time, start_time, port, cores)
51 status = self._get_server_status(start_time, end_time, port, cores)
57 def _get_server_status(self, start_time, end_time, port, cores): argument
59 elapsed_time = end_time - start_time
64 return control_pb2.ServerStatus(stats=stats, port=port, cores=cores)
137 elapsed_time = end_time - start_time
163 # In multi-channel tests, we split the load across all channels
180 return control_pb2.CoreResponse(cores=multiprocessing.cpu_count())
|
| /external/libpcap/ |
| D | pcap-tstamp.manmisc.in | 22 .TH PCAP-TSTAMP @MAN_MISC_INFO@ "14 July 2020"
24 pcap-tstamp \- packet time stamps in libpcap
41 capture device and when the networking stack time-stamps the packet;
48 a high-resolution timer might use a counter that runs at a rate
58 different CPU cores on a multi-core or multi-processor system might be
60 synchronized, so packets time-stamped by different cores might not have
68 the fraction-of-a-second part of the time stamp might roll over past
76 In addition, packets time-stamped by different cores might be
77 time-stamped in one order and added to the queue of packets for libpcap
82 packets; those time stamps are usually high-resolution time stamps, and
[all …]
|
| /external/gemmlowp/internal/ |
| D | multi_thread_gemm.h | 7 // http://www.apache.org/licenses/LICENSE-2.0
15 // multi_thread_gemm.h: Multi-threaded GEMM entry point.
31 // This value was empirically derived on an end-to-end application benchmark.
36 // time interval that we might be busy-waiting is very small, so for that
45 // or even turn off the CPU cores that they were running on. That would result
48 // between consecutive GEMM invokations, not just intra-GEMM considerations.
54 // are busy-waiting.
79 // If we can't use NOPs, let's use a non-inline function call as a basic
97 // First does some busy-waiting for a fixed number of no-op cycles,
101 // The idea of doing some initial busy-waiting is to help get
[all …]
|
| /external/lz4/contrib/snap/ |
| D | snapcraft.yaml | 6 speed > 500 MB/s per core, scalable with multi-cores CPU. It features an
8 reaching RAM speed limits on multi-core systems.
20 LZ4 library is provided as open-source software using BSD 2-Clause license.
|
| /external/ltp/testcases/kernel/power_management/lib/ |
| D | pm_sched_mc.py | 32 os.system('dmesg -c >/dev/null')
69 '''Return 1 if the system is multi socket else return 0
77 print("Failed to check if system is multi socket system")
88 if line.startswith('cpu cores'):
97 print("Failed to check if system is hyper-threaded")
101 ''' Return true if system has sockets has multiple cores
109 if line.startswith('cpu cores'):
127 print("Failed to check if system is multi core system")
140 if line.startswith('cpu cores'):
145 print("Failed to check if system is hyper-threaded")
[all …]
|
| /external/cpuinfo/src/x86/mach/ |
| D | init.c | 8 #include <cpuinfo/internal-api.h>
17 return (UINT32_C(1) << bits) - UINT32_C(1); in bit_mask()
22 struct cpuinfo_core* cores = NULL; in cpuinfo_x86_mach_init() local
38 cores = calloc(mach_topology.cores, sizeof(struct cpuinfo_core)); in cpuinfo_x86_mach_init()
39 if (cores == NULL) { in cpuinfo_x86_mach_init()
40 cpuinfo_log_error("failed to allocate %zu bytes for descriptions of %"PRIu32" cores", in cpuinfo_x86_mach_init()
41 mach_topology.cores * sizeof(struct cpuinfo_core), mach_topology.cores); in cpuinfo_x86_mach_init()
44 /* On x86 cluster of cores is a physical package */ in cpuinfo_x86_mach_init()
64 const uint32_t threads_per_core = mach_topology.threads / mach_topology.cores; in cpuinfo_x86_mach_init()
66 const uint32_t cores_per_package = mach_topology.cores / mach_topology.packages; in cpuinfo_x86_mach_init()
[all …]
|
| /external/tensorflow/tensorflow/python/distribute/cluster_resolver/ |
| D | cluster_resolver.py | 7 # http://www.apache.org/licenses/LICENSE-2.0
46 ….append(session._DeviceAttributes(d.name, d.device_type, 0, 0)) # pylint: disable=protected-access
79 In general, multi-client tf.distribute strategies such as
82 the other hand, these concepts are not applicable in single-client strategies,
87 - task_type is the name of the server's current named job (e.g. 'worker',
89 - task_id is the ordinal index of the server within the task type.
90 - rpc_layer is the protocol used by TensorFlow to communicate with other
103 ClusterSpec returned is up-to-date at the time of calling this function.
125 returned is up-to-date at the time to calling this function. This usually
134 """Returns the number of accelerator cores per worker.
[all …]
|
| /external/swiftshader/third_party/llvm-10.0/llvm/include/llvm/Support/ |
| D | Threading.h | 1 //===-- llvm/Support/Threading.h - Control multithreading mode --*- C++ -*-===//
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
7 //===----------------------------------------------------------------------===//
9 // This file declares helper functions for running LLVM in a multi-threaded
12 //===----------------------------------------------------------------------===//
19 #include "llvm/Config/llvm-config.h" // for LLVM_ON_UNIX
52 /// Returns true if LLVM is compiled with support for multi-threading, and
63 /// \param UserFn - The callback to execute.
64 /// \param UserData - An argument to pass to the callback function.
65 /// \param StackSizeInBytes - A requested size (in bytes) for the thread stack
[all …]
|
| /external/ComputeLibrary/docs/contributor_guide/ |
| D | implementation_topics.dox | 2 /// Copyright (c) 2017-2021 Arm Limited.
4 /// SPDX-License-Identifier: MIT
35 - max[n].start() <= sub[n].start() < max[n].end()
36 - sub[n].start() < sub[n].end() <= max[n].end()
37 - max[n].step() == sub[n].step()
38 - (sub[n].start() - max[n].start()) % max[n].step() == 0
39 - (sub[n].end() - sub[n].start()) % max[n].step() == 0
79 @section implementation_topic_multithreading Multi-threading
81 …hread, however if your system has several CPU cores, you will probably want the kernel to use seve…
87 const Window &max_window = kernel->window();
[all …]
|
| /external/swiftshader/third_party/llvm-subzero/include/llvm/Support/ |
| D | Threading.h | 1 //===-- llvm/Support/Threading.h - Control multithreading mode --*- C++ -*-===//
8 //===----------------------------------------------------------------------===//
10 // This file declares helper functions for running LLVM in a multi-threaded
13 //===----------------------------------------------------------------------===//
18 #include "llvm/Config/llvm-config.h" // for LLVM_ON_UNIX
40 /// Returns true if LLVM is compiled with support for multi-threading, and
44 /// llvm_execute_on_thread - Execute the given \p UserFn on a separate
52 /// \param UserFn - The callback to execute.
53 /// \param UserData - An argument to pass to the callback function.
54 /// \param RequestedStackSize - If non-zero, a requested size (in bytes) for
[all …]
|
| /external/openscreen/third_party/abseil/src/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/tensorflow/third_party/absl/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/webrtc/third_party/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/rust/crates/grpcio-sys/grpc/third_party/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/cronet/third_party/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/libtextclassifier/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
53 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
54 int cpu = -1; in RunAll()
|
| /external/angle/third_party/abseil-cpp/absl/random/internal/ |
| D | nanobenchmark_test.cc | 7 // https://www.apache.org/licenses/LICENSE-2.0
55 // Avoid migrating between cores - important on multi-socket systems. in RunAll()
56 int cpu = -1; in RunAll()
|
| /external/pigweed/pw_snapshot/pw_snapshot_protos/ |
| D | snapshot_metadata.proto | 7 // https://www.apache.org/licenses/LICENSE-2.0
35 // (e.g. base-64 encoded or binary data).
38 // Null-pointer dereference
51 // string is case-sensitive. This should always be human readable text, and
58 // "codename-local-[build_id]"
59 // "codename-release-193"
66 // possible, detailing hardware revision, and distinguishing different cores
67 // in a multi-core device. Snapshots aggregated as related_snapshots should
72 // "propellerhat-evk"
73 // "gshoe-sensor-core-pvt"
[all …]
|