Functions — github.com/CNugteren/CLBlast

CodeHub MCPcopy Create free account

hub / github.com/CNugteren/CLBlast / functions

Functions2,813 in github.com/CNugteren/CLBlast

⨍ Functions 2,813◇ Types & classes 430

↓ 2 callersMethodDoSymv

src/routines/level2/xsymv.cpp:30

↓ 2 callersMethodDoSyr

src/routines/level2/xsyr.cpp:30

↓ 2 callersMethodDoSyr2

src/routines/level2/xsyr2.cpp:30

↓ 2 callersMethodDoSyr2k

src/routines/level3/xsyr2k.cpp:30

↓ 2 callersMethodDoSyrk

src/routines/level3/xsyrk.cpp:50

↓ 2 callersMethodDoTbmv

src/routines/level2/xtbmv.cpp:31

↓ 2 callersMethodDoTpmv

src/routines/level2/xtpmv.cpp:31

↓ 2 callersMethodDoTrmm

src/routines/level3/xtrmm.cpp:34

↓ 2 callersMethodDoTrmv

src/routines/level2/xtrmv.cpp:31

↓ 2 callersMethodDoTrsm

src/routines/level3/xtrsm.cpp:40

↓ 2 callersMethodDoTrsv

src/routines/level2/xtrsv.cpp:83

↓ 2 callersFunctionEuclidGCD

Solve Bezout's identity a * p + b * q = r = GCD(a, b)

src/utilities/utilities.cpp:688

↓ 2 callersFunctionEvaluateCondition

src/kernel_preprocessor.cpp:162

↓ 2 callersFunctionFillMatrix

src/routines/common.cpp:91

↓ 2 callersMethodInvalidate

src/cache.cpp:101

↓ 2 callersMethodIsAMD

src/cupp11.hpp:335

↓ 2 callersMethodIsLocalMemoryValid

Configuration-validity checks

src/cupp11.hpp:312

↓ 2 callersMethodIsNVIDIA

src/cupp11.hpp:336

↓ 2 callersMethodLaunch

Launches a kernel onto the specified queue

src/cupp11.hpp:741

↓ 2 callersMethodLocalMemSize

src/cupp11.hpp:272

↓ 2 callersMethodLocalMemUsage

Retrieves the amount of local memory used per work-group for this kernel. Note that this the shared memory in CUDA terminology.

src/cupp11.hpp:731

↓ 2 callersFunctionMakeReason

src/utilities/clblast_exceptions.cpp:24

↓ 2 callersMethodNVIDIAComputeCapability

src/cupp11.hpp:343

↓ 2 callersFunctionOverrideParametersFromJSONFiles

test/test_utilities.cpp:203

↓ 2 callersFunctionParseMath

Simple unsigned integer math parser

src/kernel_preprocessor.cpp:71

↓ 2 callersFunctionRunGemmRoutineMNK

src/tuning/routines/xgemm.cpp:34

↓ 2 callersFunctionRunPreprocessor

test/correctness/misc/preprocessor.cpp:162

↓ 2 callersFunctionSetConfigurations

Finds all configurations. It also applies the user-defined constraints within.

src/tuning/configurations.cpp:22

↓ 2 callersFunctionSetOpenCLKernelStandard

src/utilities/utilities.cpp:673

↓ 2 callersMethodSupportsFP64

src/cupp11.hpp:287

↓ 2 callersFunctionTestSimilarity

test/correctness/tester.cpp:597

↓ 2 callersFunctionTestSimilarityNear

test/correctness/tester.cpp:562

↓ 2 callersFunctionadd_default_sections

(database, grouping, verbose, values_dict, condition, enable_warning)

scripts/database/database/defaults.py:50

↓ 2 callersFunctionbenchmark_single

(benchmark, comparisons, platform, device, num_runs, precision, load_from_disk, plot_titl

scripts/benchmark/benchmark.py:95

↓ 2 callersFunctioncblasXaxpy

Forwards the Netlib BLAS calls for SAXPY/DAXPY/CAXPY/ZAXPY

test/wrapper_cblas.hpp:199

↓ 2 callersFunctioncblas_sgemm

src/clblast_netlib_c.cpp:2718

↓ 2 callersFunctionclblasXaxpy

Forwards the clBLAS calls for SAXPY/DAXPY/CAXPY/ZAXPY

test/wrapper_clblas.hpp:271

↓ 2 callersFunctioncublasXaxpy

Forwards the cuBLAS calls for SAXPY/DAXPY/CAXPY/ZAXPY

test/wrapper_cublas.hpp:260

↓ 2 callersFunctionget_common_best_parameters

Sets defaults based on the best values of entries supported by all devices. This might cause a problem in case not every device was tuned with the

scripts/database/database/defaults.py:169

↓ 2 callersFunctionget_cpp_separator

Retrieves a C++ comment separator

scripts/database/database/clblast.py:52

↓ 2 callersMethodoperator()

Accessors to the private data-members

src/cupp11.hpp:682

↓ 2 callersFunctionprecision_to_string

Translates a precision number (represented as Python string) into a descriptive string

scripts/database/database/clblast.py:36

↓ 1 callersMethodAMDBoardName

Platform specific extensions

src/cupp11.hpp:342

↓ 1 callersMethodAdrenoVersion

Returns the Qualcomm Adreno GPU version (i.e. a650, a730, a740, etc.)

src/clpp11.hpp:369

↓ 1 callersFunctionCLBlastDgemv

src/clblast_c.cpp:742

↓ 1 callersFunctionCLBlastFillCache

Fills the cache with binaries for a specific device

src/clblast_c.cpp:3098

↓ 1 callersFunctionCLBlastHaxpy

src/clblast_c.cpp:308

↓ 1 callersFunctionCLBlastSgemm

src/clblast_c.cpp:1800

↓ 1 callersFunctionCLBlastiSamax

src/clblast_c.cpp:537

↓ 1 callersFunctionCUDAToHost

test/wrapper_cuda.hpp:57

↓ 1 callersFunctionClearCache

Clears the cache of stored binaries

src/api_common.cpp:25

↓ 1 callersFunctionComplexConjugate

test/test_utilities.cpp:53

↓ 1 callersMethodComputeArch

src/cupp11.hpp:281

↓ 1 callersMethodComputeUnits

src/cupp11.hpp:301

↓ 1 callersMethodCoreClock

src/cupp11.hpp:300

↓ 1 callersFunctionFillCache

Fills the cache with all binaries for a specific device

src/api_common.cpp:120

↓ 1 callersFunctionFillVector

src/routines/common.cpp:125

↓ 1 callersFunctionGenerateProperTrsmMatrices

test/routines/level3/xtrsm_data.hpp:97

↓ 1 callersFunctionGetBestParametersFromJSONFile

test/test_utilities.cpp:228

↓ 1 callersFunctionGetBestResult

Computes the best switching point

src/tuning/routines/routine_tuner.hpp:43

↓ 1 callersMethodGetBuildInfo

Retrieves the warning/error message from the compiler (if any)

src/cupp11.hpp:447

↓ 1 callersMethodGetDefines

Returns a list of OpenCL pre-processor defines in string form

src/database/database.cpp:187

↓ 1 callersMethodGetExtraInfo

Retrieves the above extra information

src/cupp11.hpp:349

↓ 1 callersMethodGetFunctionName

Retrieves the name of the kernel

src/cupp11.hpp:738

↓ 1 callersMethodGetIR

Retrieves an intermediate representation of the compiled program (i.e. PTX)

src/cupp11.hpp:460

↓ 1 callersMethodGetModule

Accessor to the private data-members

src/cupp11.hpp:473

↓ 1 callersMethodGetParameterNames

Retrieves the names of all the parameters

src/database/database.cpp:205

↓ 1 callersMethodGetValuesString

... or just the values as string

src/database/database.cpp:196

↓ 1 callersFunctionHasOnlyDigits

src/kernel_preprocessor.cpp:63

↓ 1 callersFunctionHostToCUDA

test/wrapper_cuda.hpp:77

↓ 1 callersMethodIsPostNVIDIAVolta

Returns if the Nvidia chip is a Volta or later archicture (major version 7 or higher)

src/cupp11.hpp:346

↓ 1 callersMethodNumDevices

Returns the number of devices on this platform

src/cupp11.hpp:201

↓ 1 callersMethodNumDevices

Returns the number of devices on this platform

src/clpp11.hpp:190

↓ 1 callersMethodNumFailedTests

Returns the number of failed tests

test/correctness/tester.hpp:81

↓ 1 callersFunctionOpenCLDiagnostics

test/diagnostics.cpp:21

↓ 1 callersMethodParseArguments

test/performance/client.cpp:62

↓ 1 callersMethodPerformanceTest

test/performance/client.cpp:288

↓ 1 callersFunctionPopulateConfigurations

Iterates recursively over all permutations of the user-defined parameters

src/tuning/configurations.cpp:38

↓ 1 callersFunctionPreprocessDefinesAndComments

First pass: detect defines and comments

src/kernel_preprocessor.cpp:331

↓ 1 callersMethodRemove

src/cache.cpp:71

↓ 1 callersFunctionRetrieveParameters

Retrieves the current tuning parameters for this device-precision-kernel combination

src/api_common.cpp:140

↓ 1 callersFunctionRunKernelTimed

src/utilities/timing.cpp:22

↓ 1 callersMethodStatusIsCompilationWarningOrError

Confirms whether a certain status code is an actual compilation error or warning

src/cupp11.hpp:444

↓ 1 callersMethodSupportsFP16

src/cupp11.hpp:288

↓ 1 callersFunctionTestArrayToRegisterPromotion

test/correctness/misc/preprocessor.cpp:83

↓ 1 callersFunctionTestBatchedMatrixA

src/utilities/buffer_test.hpp:170

↓ 1 callersFunctionTestBatchedMatrixB

src/utilities/buffer_test.hpp:178

↓ 1 callersFunctionTestBatchedMatrixC

src/utilities/buffer_test.hpp:186

↓ 1 callersFunctionTestDefines

test/correctness/misc/preprocessor.cpp:23

↓ 1 callersMethodTestInvalid

test/correctness/testblas.cpp:280

↓ 1 callersMethodTestRegular

test/correctness/testblas.cpp:99

↓ 1 callersFunctionTestStridedBatchedMatrixA

src/utilities/buffer_test.hpp:196

↓ 1 callersFunctionTestStridedBatchedMatrixB

src/utilities/buffer_test.hpp:205

↓ 1 callersFunctionTestStridedBatchedMatrixC

src/utilities/buffer_test.hpp:214

↓ 1 callersFunctionTestVectorIndex

src/utilities/buffer_test.hpp:155

↓ 1 callersFunctionTestVectorZ

src/utilities/buffer_test.hpp:124

↓ 1 callersFunctionValidConfiguration

Loops over all user-defined constraints to check whether or not the configuration is valid

src/tuning/configurations.cpp:66

↓ 1 callersFunctionadd_tuning_parameter

(database, parameter_name, kernel, value)

scripts/database/database.py:76

↓ 1 callersFunctionargmin

scripts/database/database/bests.py:45

↓ 1 callersMethodbegin

src/clpp11.hpp:630

← previous next →201–300 of 2,813, ranked by callers