Functions — github.com/SAITPublic/PIMSimulator

CodeHub MCPcopy Create free account

hub / github.com/SAITPublic/PIMSimulator / functions

Functions526 in github.com/SAITPublic/PIMSimulator

⨍ Functions 526◇ Types & classes 110

↓ 51 callersFunctionsignal

Signal and silence signaling NaN. \param nan half-precision NaN value \return quiet NaN \exception FE_INVALID if \a nan is signaling NaN

↓ 27 callersFunctioninvalid

Raise domain error and return NaN. return quiet NaN \exception FE_INVALID

↓ 26 callersFunctionraise

Raise floating-point exception. \param flags exceptions to raise \param cond condition to raise exceptions for

↓ 19 callersFunctionisnan

Check for NaN. See also:** Documentation for [std::isnan](https://en.cppreference.com/w/cpp/numeric/math/isnan). \param arg number to check \retval tr

lib/half.h:4597

↓ 17 callersFunctionuLog2

↓ 16 callersMethodaddTransaction

src/MemorySystem.cpp:175

↓ 16 callersMethodfind

src/ConfigurationDB.h:53

↓ 16 callersMethodstr

↓ 14 callersFunctionconvertH2F

src/FP16.cpp:15

↓ 14 callersMethodloadFp16

src/Burst.h:395

↓ 14 callersMethodtoInt

src/PIMCmd.cpp:100

↓ 13 callersFunctionselect

Select value or signaling NaN. \param x preferred half-precision value \param y ignored half-precision value except for signaling NaN \return \a y if

↓ 11 callersMethodclear

src/tests/KernelTestCases.h:69

↓ 11 callersMethodgetTotalDim

src/Burst.h:472

↓ 11 callersFunctionpole

Raise pole error and return infinity. \param sign half-precision value with sign bit only \return half-precision infinity with sign of \a sign \except

↓ 11 callersMethodprint

src/PIMBlock.cpp:109

↓ 11 callersMethodwrite

src/Bank.cpp:92

↓ 10 callersFunctionceil

Nearest integer not less than half value. See also:** Documentation for [std::ceil](https://en.cppreference.com/w/cpp/numeric/math/ceil). \param arg h

lib/half.h:4271

↓ 10 callersMethoddimTobShape

src/tests/TestCases.h:375

↓ 10 callersFunctionlog2

Fixed point binary logarithm. This uses the BKM algorithm in L-mode. \param m mantissa in [1,2) as Q1.30 \param n number of iterations (at most 32) \r

lib/half.h:1656

↓ 10 callersMethodread

src/Bank.cpp:79

↓ 9 callersFunctionsign_mask

Platform-independent sign mask. \param arg integer value in two's complement \retval -1 if \a arg negative \retval 0 if \a arg positive

↓ 8 callersFunctiondivide64

64-bit division. \param x upper 32 bit of dividend \param y divisor \param s variable to store sticky bit for rounding \return (\a x << 32) / \a y

lib/half.h:1521

↓ 8 callersFunctionexp2

Fixed point binary exponential. This uses the BKM algorithm in E-mode. \param m exponent in [0,1) as Q0.31 \param n number of iterations (at most 32)

lib/half.h:1632

↓ 8 callersMethodgetDataSize

src/tests/TestCases.h:328

↓ 8 callersFunctionmultiply64

64-bit multiplication. \param x first factor \param y second factor \return upper 32 bit of \a x * \a y rounded to nearest

lib/half.h:1507

↓ 8 callersMethodrunPIM

src/tests/PIMKernel.cpp:21

↓ 6 callersFunctionabs

Absolute value. See also:** Documentation for [std::abs](https://en.cppreference.com/w/cpp/numeric/math/fabs). \param arg operand \return absolute val

lib/half.h:2875

↓ 6 callersFunctioncompsignal

Check and signal for any NaN. \param x first half-precision value to check \param y second half-precision value to check \retval true if either \a x o

↓ 6 callersMethodprintDim

src/tests/TestCases.h:333

↓ 5 callersMethodWillAcceptTransaction

src/MemorySystem.cpp:269

↓ 5 callersMethodaddrGenSafe

src/tests/KernelAddrGen.cpp:57

↓ 5 callersMethodaddressMapping

src/AddressMapping.cpp:74

↓ 5 callersMethodgetValue

src/SystemConfiguration.h:245

↓ 5 callersMethodsetValue

src/SystemConfiguration.h:161

↓ 5 callersMethodstep

src/SimulatorObject.cpp:36

↓ 5 callersMethodupdate

src/Rank.cpp:478

↓ 4 callersMethodaddrGen

src/tests/KernelAddrGen.cpp:25

↓ 4 callersFunctionangle_arg

Reduce argument for trigonometric functions. \param abs half-precision floating-point value \param k value to take quarter period \return \a abs reduc

lib/half.h:1726

↓ 4 callersFunctionarithmetic_shift

Platform-independent arithmetic right shift. \param arg integer value in two's complement \param i shift amount (at most 31) \return \a arg right shif

↓ 4 callersFunctionatan2

Fixed point arc tangent. This uses the CORDIC algorithm in vectoring mode. \param my y coordinate as Q0.30 \param mx x coordinate as Q0.30 \param n nu

lib/half.h:1704

↓ 4 callersMethodexecuteEltwise

src/tests/PIMKernel.cpp:499

↓ 4 callersFunctionfp16Equal

src/FP16.cpp:27

↓ 4 callersMethodhasPendingTransactions

src/MultiChannelMemorySystem.cpp:579

↓ 4 callersMethodisReservedRA

src/PIMRank.h:108

↓ 4 callersMethodisSameBankgroup

src/AddressMapping.cpp:69

↓ 4 callersFunctionldexp

Multiply by power of two. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::ldexp](https://en.cppreferen

lib/half.h:4424

↓ 4 callersMethodloadTobShape

src/Burst.h:372

↓ 4 callersMethodreadResult

src/tests/PIMKernel.cpp:473

↓ 4 callersFunctionset

↓ 4 callersFunctionsincos

Fixed point sine and cosine. This uses the CORDIC algorithm in rotation mode. \param mz angle in [-pi/2,pi/2] as Q1.30 \param n number of iterations (

lib/half.h:1680

↓ 4 callersFunctiontrim

Removes leading and trailing whitespaces */

↓ 3 callersFunctionLoadArrayFromNumpy

↓ 3 callersFunctioncheck_underflow

Check value for underflow. \param arg non-zero half-precision value to check \return \a arg \exception FE_UNDERFLOW if arg is subnormal

↓ 3 callersMethodexecuteGemv

void PIMKernel::preloadEltwise(NumpyBurstType* operand, pimBankType pb_type, unsigned starting_row, unsigned starting_co

src/tests/PIMKernel.cpp:364

↓ 3 callersMethodgetCycle

src/tests/PIMKernel.cpp:30

↓ 3 callersFunctionhyperbolic_args

Get exponentials for hyperbolic computation \param abs half-precision floating-point value \param exp variable to take unbiased exponent of larger res

lib/half.h:1779

↓ 3 callersMethodpreloadNoReplacement

src/tests/PIMKernel.cpp:325

↓ 3 callersFunctionsqrt

lib/half.h:1611

↓ 2 callersMethodadderTree

src/tests/PIMKernel.cpp:599

↓ 2 callersFunctionatan2_args

Get arguments for atan2 function. \param abs half-precision floating-point value \return \a abs and sqrt(1 - \a abs^2) as Q0.30

lib/half.h:1753

↓ 2 callersFunctionbuiltin_isnan

↓ 2 callersFunctionbuiltin_signbit

↓ 2 callersFunctioncomp_size

↓ 2 callersFunctionconvertF2H

src/FP16.cpp:21

↓ 2 callersMethoddoPIM

src/PIMRank.cpp:323

↓ 2 callersFunctionfileExists

src/MultiChannelMemorySystem.cpp:110

↓ 2 callersMethodfinalize

src/CSVWriter.h:143

↓ 2 callersMethodfromInt

src/PIMCmd.cpp:27

↓ 2 callersMethodgetResultColGemv

src/tests/PIMKernel.cpp:249

↓ 2 callersFunctionisPowerOfTwo

↓ 2 callersMethodisToggleCond

src/PIMRank.cpp:116

↓ 2 callersMethodmeasureCycle

src/tests/PIMBenchTestCases.h:164

↓ 2 callersMethodpreloadGemv

src/tests/PIMKernel.cpp:283

↓ 2 callersMethodprintStats

src/tests/PIMBenchTestCases.h:304

↓ 2 callersMethodprintTestMessage

src/tests/PIMBenchTestCases.h:299

↓ 2 callersMethodreadData

src/tests/PIMKernel.cpp:588

↓ 2 callersMethodreceiveFromBus

get a bus packet from either data or cmd bus

src/MemoryController.cpp:103

↓ 2 callersFunctionscalbln

Multiply by power of two. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::scalbln](https://en.cpprefer

lib/half.h:4386

↓ 2 callersMethodsetChanId

src/Rank.cpp:64

↓ 2 callersMethodsetRankId

src/Rank.cpp:69

↓ 2 callersMethodtoStr

src/PIMCmd.cpp:149

↓ 2 callersMethodupdatefromFile

src/ConfigurationDB.h:86

↓ 1 callersFunctionFilenameWithNumberSuffix

src/MultiChannelMemorySystem.cpp:124

↓ 1 callersFunctionReLU

data/relu/gen_np_relu.py:17

↓ 1 callersMethodadd

src/PIMBlock.cpp:24

↓ 1 callersMethodaddBarrier

src/MemorySystem.cpp:190

↓ 1 callersMethodaddBarrier

src/tests/PIMKernel.cpp:116

↓ 1 callersMethodattachMemoryController

attachMemoryController() must be called before any other Rank functions are called

src/Rank.cpp:85

↓ 1 callersMethodattachRank

src/PIMRank.cpp:41

↓ 1 callersMethodattachRanks

gives the memory controller a handle on the rank objects

src/MemoryController.cpp:146

↓ 1 callersMethodbankgroupId

src/AddressMapping.cpp:63

↓ 1 callersFunctionbuiltin_isinf

↓ 1 callersFunctioncos

Cosine function. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::cos](https://en.cppreference.com/w/cp

lib/half.h:3754

↓ 1 callersMethoddump

src/ConfigurationDB.h:92

↓ 1 callersMethodenqueue

Adds a command to appropriate queue

src/CommandQueue.cpp:134

↓ 1 callersFunctionfabs

Absolute value. See also:** Documentation for [std::fabs](https://en.cppreference.com/w/cpp/numeric/math/fabs). \param arg operand \return absolute va

lib/half.h:2869

↓ 1 callersFunctionferaiseexcept

Raise exception flags. This raises the specified floating point exceptions and also invokes any additional automatic exception handling as configured

lib/half.h:4761

↓ 1 callersFunctionfloor

Nearest integer not greater than half value. See also:** Documentation for [std::floor](https://en.cppreference.com/w/cpp/numeric/math/floor). \param

lib/half.h:4281

↓ 1 callersFunctionfrexp

Decompress floating-point number. See also:** Documentation for [std::frexp](https://en.cppreference.com/w/cpp/numeric/math/frexp). \param arg number

lib/half.h:4366

next →1–100 of 526, ranked by callers