Functions — github.com/clMathLibraries/clFFT

CodeHub MCPcopy Create free account

hub / github.com/clMathLibraries/clFFT / functions

Functions2,530 in github.com/clMathLibraries/clFFT

⨍ Functions 2,530◇ Types & classes 165

↓ 6 callersFunctionnan_as_hex

src/tests/buffer_memory.cpp:34

↓ 6 callersMethodset_all_to_impulse

src/tests/buffer.h:1143

↓ 6 callersMethodset_input_to_buffer

src/tests/cl_transform.h:616

↓ 5 callersMethodAddSample

src/statTimer/statisticalTimer.CPU.cpp:223

↓ 5 callersFunctionclfftGetPlanTransposeResult

src/library/accessors.cpp:705

↓ 5 callersFunctionclfftSetPlanCallback

src/library/accessors.cpp:770

↓ 5 callersMethodclose

src/library/fft_binary_lookup.cpp:102

↓ 5 callersFunctionprettyPrintclFFTStatus

src/client/openCL.misc.cpp:240

↓ 5 callersFunctionsep

src/library/fft_binary_lookup.cpp:56

↓ 5 callersMethodsetProgramCode

src/library/repo.cpp:111

↓ 4 callersFunctionButterflyName

src/library/generator.stockham.h:184

↓ 4 callersFunctionPrecisionWidth

src/library/plan.cpp:442

↓ 4 callersFunctionbody

* This processes one or more 64-byte data blocks, but does NOT update * the bit counters. There are no alignment requirements. */

src/library/md5sum.c:100

↓ 4 callersFunctioncleanupCL

src/client/openCL.misc.cpp:477

↓ 4 callersFunctionclfftGetVersion

src/library/lifetime.cpp:86

↓ 4 callersFunctiondo_mkdir

src/library/fft_binary_lookup.cpp:684

↓ 4 callersMethodimag_ptr

src/tests/buffer.h:809

↓ 4 callersMethodindex

src/tests/buffer.h:394

↓ 4 callersMethodscale_data

src/tests/buffer.h:1160

↓ 3 callersFunctionBitScanF

src/library/private.h:331

↓ 3 callersMethodGenerateButterfly

src/library/generator.stockham.h:2096

↓ 3 callersMethodGetNumB1

src/library/generator.stockham.cpp:2025

↓ 3 callersMethodGetWGSAndNT

src/library/generator.stockham.cpp:369

↓ 3 callersFunctionIs1DPossible

src/library/plan.h:608

↓ 3 callersFunctionPassName

src/library/generator.stockham.h:194

↓ 3 callersFunctionTwTableLargeName

src/library/generator.stockham.h:208

↓ 3 callersFunctioncheck_for_1235_factors

(values, option)

src/scripts/perf/measurePerformance.py:404

↓ 3 callersFunctioncreate_prime_factors

(args,input_list)

src/scripts/perf/measurePerformance.py:505

↓ 3 callersFunctionfindFactors

src/scripts/perf/measurePerformance.py:316

↓ 3 callersFunctiongenTransposePrototypeLeadingDimensionBatched

src/library/generator.transpose.cpp:254

↓ 3 callersFunctiongenTwiddleMath

Small snippet of code that multiplies the twiddle factors into the butterfiles. It is only emitted if the plan tells the generator that it wants the

src/library/generator.transpose.cpp:84

↓ 3 callersFunctiongenTwiddleMathLeadingDimensionBatched

Small snippet of code that multiplies the twiddle factors into the butterfiles. It is only emitted if the plan tells the generator that it wants the

src/library/generator.transpose.cpp:121

↓ 3 callersMethodgetclKernel

src/library/repo.cpp:284

↓ 3 callersMethodpopulateCache

src/library/fft_binary_lookup.cpp:529

↓ 3 callersMethodstride

src/tests/buffer.h:912

↓ 3 callersFunctionvalidateFactors

src/scripts/perf/measurePerformance.py:346

↓ 2 callersFunctionCalculateBlockSize

src/library/generator.transpose.gcn.cpp:1110

↓ 2 callersFunctionCeilPo2

Find the smallest power of 2 that is >= n; return its power of 2 factor e.g., CeilPo2 (7) returns 3 : (2^3 >= 7)

src/library/generator.stockham.h:89

↓ 2 callersFunctionFreeSharedLibrary

If the function succeeds, the return value is nonzero. If the function fails, the return value is zero.

src/include/sharedLibrary.h:72

↓ 2 callersMethodGenerateKernel

src/library/generator.stockham.cpp:3200

↓ 2 callersMethodGenerateKernel

src/library/generator.copy.cpp:145

↓ 2 callersMethodGetMax1DLength

src/library/plan.cpp:4811

↓ 2 callersFunctionLoadFunctionAddr

This takes a shared module handle returned from LoadSharedLibrary, and a text string of a symbol to load from the module, and returns a pointer to tha

src/include/sharedLibrary.h:92

↓ 2 callersFunctionLoadSharedLibrary

src/include/sharedLibrary.h:32

↓ 2 callersFunctionOffsetCalc

src/library/generator.transpose.gcn.cpp:123

↓ 2 callersFunctionReadParameterFile

src/library/generator.stockham.cpp:189

↓ 2 callersMethodSample

src/callback-client/client.h:100

↓ 2 callersMethodSetPostcallback

src/library/generator.stockham.cpp:2041

↓ 2 callersMethodSetPrecallback

src/library/generator.stockham.cpp:2035

↓ 2 callersMethodStart

src/callback-client/client.h:99

↓ 2 callersMethodSweepRegs

SweepRegs is to iterate through the registers to do the three basic operations: reading, twiddle multiplication, writing

src/library/generator.stockham.cpp:755

↓ 2 callersFunctionTwTableLargeFunc

src/library/generator.stockham.h:213

↓ 2 callersFunctionTwTableName

src/library/generator.stockham.h:203

↓ 2 callersFunctioncheckDevExt

Returns CLFFT_SUCCESS if the fp64 is present, CLFFT_DEVICE_NO_DOUBLE if it is not found.

src/library/plan.cpp:181

↓ 2 callersFunctionclfftCopyPlan

src/library/plan.cpp:4552

↓ 2 callersFunctionclfftGetPlanContext

src/library/accessors.cpp:55

↓ 2 callersFunctioncreateOpenCLMemoryBuffer

src/client/openCL.misc.cpp:498

↓ 2 callersFunctioncreateOpenCLMemoryBuffer

src/callback-client/openCL.misc.cpp:492

↓ 2 callersMethoddestroy_plan

src/tests/fftw_transform.h:109

↓ 2 callersFunctiondiscoverCLPlatforms

src/client/openCL.misc.cpp:357

↓ 2 callersFunctiongenTransposeKernelBatched

generate transepose kernel with sqaure 2d matrix of row major with arbitrary batch size Below is a matrix(row major) containing three sqaure sub matri

src/library/generator.transpose.cpp:1947

↓ 2 callersMethodgenerateKernel

OpenCL does not take unicode strings as input, so this routine returns only ASCII strings Feed this generator the FFTPlan, and it returns the generate

src/library/action.transpose.cpp:199

↓ 2 callersFunctiongetKernelName

src/library/plan.cpp:372

↓ 2 callersMethodgetProgramCode

src/library/repo.cpp:146

↓ 2 callersMethodgetProgramEntryPoint

src/library/repo.cpp:174

↓ 2 callersFunctionget_R2C_fftwf_output

Compute reference output using fftw for float type

src/callback-client/callback-client.cpp:520

↓ 2 callersFunctionget_cycles

-> get_cycles function gets the swapping logic required for given row x col matrix. -> cycle_map[0] holds the total number of cycles required. -> cycl

src/library/generator.transpose.cpp:327

↓ 2 callersMethodgetclProgram

src/library/repo.cpp:226

↓ 2 callersMethodinitParams

src/library/action.transpose.cpp:105

↓ 2 callersMethodis_interleaved

src/tests/cl_transform.h:243

↓ 2 callersMethodis_planar

src/tests/cl_transform.h:237

↓ 2 callersMethodis_real

src/tests/cl_transform.h:231

↓ 2 callersMethodmake_plan

src/tests/fftw_transform.h:41

↓ 2 callersMethodmake_sure_padding_was_not_overwritten

src/tests/buffer.h:1193

↓ 2 callersFunctionmaxBatchSize

(lengthx, lengthy, lengthz, layout, precision, exe, device)

src/scripts/perf/fftPerformanceTesting.py:132

↓ 2 callersFunctionmax_problem_size_in_datapoints

src/tests/accuracy_test_random.cpp:89

↓ 2 callersMethodmultiply_3pt_average

Calculates a 3 point average of other_buffer and multiplies with buffer only real layout is supported for other_buffer currently

src/tests/buffer.h:659

↓ 2 callersFunctionpermutation_calculation

calculate the permutation cycles consumed in swap kernels. each cycle is strored in a vecotor. hopfully there are mutliple independent vectors thus we

src/library/generator.transpose.cpp:363

↓ 2 callersFunctionprettyPrintDeviceInfo

src/client/openCL.misc.cpp:83

↓ 2 callersFunctionprettyPrintDeviceInfo

src/callback-client/openCL.misc.cpp:83

↓ 2 callersFunctionprettyPrintPlatformInfo

src/client/openCL.misc.cpp:32

↓ 2 callersFunctionprettyPrintPlatformInfo

src/callback-client/openCL.misc.cpp:32

↓ 2 callersFunctionprettyPrintclFFTStatus

src/callback-client/openCL.misc.cpp:240

↓ 2 callersMethodprivatizeData

src/library/repo.h:54

↓ 2 callersFunctionreleaseOpenCLMemBuffer

src/client/openCL.misc.cpp:510

↓ 2 callersFunctionreleaseOpenCLMemBuffer

src/callback-client/openCL.misc.cpp:504

↓ 2 callersMethodset_input_precallback_special

src/tests/fftw_transform.h:477

↓ 2 callersMethodset_output_postcallback_special

src/tests/fftw_transform.h:494

↓ 2 callersMethodsetclKernel

src/library/repo.cpp:247

↓ 2 callersMethodswap_layouts

/ swap_layouts should only be used with in-place real-to-complex or complex-to-real transforms

src/tests/cl_transform.h:535

↓ 2 callersMethodtotal_number_of_points_including_data_and_intervening

/ note that this returns the size in number of points and does not take layout into consideration. this will yield the same number for real, interleav

src/tests/buffer.h:890

↓ 1 callersMethodAllocateBuffers

src/library/plan.cpp:4747

↓ 1 callersFunctionBSF

src/library/private.h:62

↓ 1 callersFunctionComplexMul

src/library/generator.stockham.h:113

↓ 1 callersMethodConstructAndEnqueueConstantBuffers

src/library/plan.cpp:4589

↓ 1 callersFunctionDetermineSizes

Given the length of 1d fft, this function determines the appropriate work group size and the number of transforms per work group TODO for optimization

src/library/generator.stockham.cpp:388

↓ 1 callersFunctionFloorPo2

src/library/generator.stockham.h:101

↓ 1 callersMethodGeneratePass

src/library/generator.stockham.cpp:2047

↓ 1 callersMethodGetNumB2

src/library/generator.stockham.cpp:2026

↓ 1 callersMethodGetNumB4

src/library/generator.stockham.cpp:2027

← previous next →101–200 of 2,530, ranked by callers