Introduction to OpenCL, 2010

Introduction to OpenCL
How to select OpenCL devices, initialise a compute context, allocate device memory,
compile and run kernels, output results

OpenCL Workshop | December 1, 2010 | Brisbane, Australia!
Tomasz Bednarz, CESRE!

OpenCL is a trademark of Apple, Inc.

Welcome to Open Computing Language (OpenCLTM)
•  N-Body Simulation Demo"
•  Khronos Group and OpenCL standard"
•  OpenCL Anatomy"
•  Platform Model"
•  Execution Model"
•  Memory Model"

•  Short Introduction to OpenCL Programming "
•  OpenCL C language"
•  Supported data types"
•  Synchronisation primitives"

•  Additional information and resources."

CSIRO. Introduction to OpenCL. OpenCL Workshop at the OzViz 2010, Brisbane, December 2010.

N-Body Simulation

Lars Nyland, Mark Harris, Jan Prins “Fast N-Body Simulation with CUDA”. In Hubert
Nguyen, editor, GPU Gems 3, chapter 31, pages 677-695, Addison Wesley 2007.

•  Applications"
• 
• 
• 
• 

Molecular dynamics"
Astronomical and astrophysical simulations"
Fluid dynamics simulation"
Radiosity (Radiometric transfer)"

•  N2 interactions to compute per time-step"
•  For the brute force all-pairs approach
discussed here"

•  Highly Parallel"
•  High Arithmetic intensity"

Two of these galaxies
attract each other.

N-Body Simulation (http://developer.nvidia.com/gpugems3)
•  N-Body simulation models the motion of particles subject to a
force due to the particle-particle interactions between all particles
in the system"
•  Typical example: simulation of stars in a galaxy subject to the
gravitational force"

•  Given N bodies with an initial position xj and velocity vj for 1≤i≤N,
the force fij on body i caused by its gravitational attraction to body
j is given by the following:"

fij = G

mi m j
rij

2

!

rij
rij

Fi =

#

fij = Gmi

1! j!N
i" j

#

m j rij

1! j!N
i" j

rij

3

where mi and mj are the masses of bodies i and j."
•  The acceleration is computed as:"
F

ai =

j

i

mi


i

rij = x j ! xi

N-Body Simulation
•  As bodies approach each other, the force between
them grows without bound, therefore softening factor
e2>0 may be added"

Fi ! Gmi

#
1" j"N

m j rij

(

2

rij + e

2

)

3

2

•  The softening factor limits the magnitude of the force
between the bodies, which is desirable for numerical
integration of the system state"
•  Acceleration:"

F
ai = i ! G " $
mi
1# j#N

m j rij

(

2

rij + e

2

)

3

2


N-Body Simulation: parallel concept

single interaction
between i and j

Outer Loop (i)

Particle i

Particle j

Inner Loop (j)

•  Particles i, j interact with each other"
•  OpenCL can be used to compute acceleration on all bodies in parallel "
•  N/p work groups of p work items process p bodies at a time"
•  Every work item loads all other body positions from off-chip memory"
•  N2 loads … bandwidth bound = poor performance "

•  Optimization (using tiles) to be presented in the afternoon session"

N-Body Simulation: body-body force calculation

Fi ! Gmi

#
1" j"N

ai =

Fi
! G" $
mi
1# j#N

m j rij

(
(

http://developer.download.nvidia.com/compute/opencl/sdk/website/samples.html#oclNbody
http://developer.apple.com/library/mac/#samplecode/OpenCL_NBody_Simulation_Example/Introduction/Intro.html

2

rij + e

2

m j rij
2

rij + e

2

)
)

3

3

2

2

http://www.khronos.org/opencl/

http://www.khronos.org/opencl/

What is OpenCL?
OpenCL - Open Computing Language: open, royalty-free standard for programming
heterogeneous parallel computing at the intersection of GPU and multi-core CPU capabilities.

CPUs
Multiple cores driving
performance increases

Multi-processor
programming, threading
libraries - e.g. OpenMP

GPUs
Emerging
Intersection

Heterogeneous
Computing


Increasingly general
purpose data-parallel
computing

Graphics APIs and
Shading Languages,
Vendor Compute APIs

Courtesy of

What is OpenCL?
Roadmap convergence

OpenGL 4.0 and OpenGL ES 2.0
are both streamlined, programmable
pipelines. GL and ES working groups
are working on convergence. WebGL
is a positive pressure for portable 3D
content for all platforms.

Desktop Visual Computing

OpenGL and OpenCL have direct
interoperability. OpenCL objects can be
Created from OpenGL Textures, Buffer
Objects and Renderbuffers.

Parallel computing and
visualisation
OpenCL – the center of a
visual computing
ecosystem with parallel
computations, 3D, video,
audio, and image
processing on desktop,
embedded and mobile
systems!

Desktop 3D Ecosystem

Cross-platform
desktop 3D

3D for Web
Heterogeneous
Parallel Programing
Embedded 3D

Surface and
synch abstraction

Streaming Media and
Image Processing

Mobile Visual Computing
Compute, graphics and AV APIs
interoperate through EGL.


Hundreds of men
years invested by
industry experts in
coordinated
ecosystem!

Streamlined APIs for mobile and
embedded graphics, media and
compute acceleration
Based on http://www.khronos.org/opencl/

OpenCL Timeline
•  OpenCL 1.0 was released six months after the proposal was created"
•  OpenCL ships first on Appleʼs Mac OS X Snow Leopard"
•  18 month cadence between OpenCL 1.0 and OpenCL 1.1"
•  Backward compatible to protect software investment"
Multiple conformant
implementations ship
across diverse OS and
platforms.!

Khronos releases
publicly OpenCL 1.1 as
royalty-free specification.!

June 2008

May 2009
December 2008

OpenCL working group!
is proposed by Apple. !
Draft spec is contributed!
to Khronos.!

June 2010
2nd Half 2009

Khronos releases
OpenCL 1.0 conformance
tests to ensure highquality implementations.!


OpenCL 1.1 spec is
released and first
implementation ship.!


OCL Quick Reference Cards

http://www.khronos.org/files/opencl-quick-reference-card.pdf

Design goals of OpenCL
•  Enable all compute resources in system"
•  CPUs, GPUs, and other processors enabled as peers"
•  Data- and task- parallel compute model"

•  Efficient parallel programming model"
•  ANSI C99 based kernel language"

•  Low-level abstraction"
•  Abstracts the specifics of the underlying hardware"
•  High-performance, but device independent "

•  Define precision requirements for all floating-point computations"
•  Consistent results on all platforms and devices"

•  Interoperability with Graphics APIs"
•  Dedicated support for OpenGL, OpenGL ES and DirectX"

•  Drive future hardware requirements"
•  Applicable to both consumer and HPC applications"

It’s heterogeneous world
•  Platform model encapsulates
compute resources"
•  A modern platform includes:"
• 
• 
• 
• 

One or more CPUs"
One or more GPUs"
Optional accelerators (e.g. DSPs)"
Other?"

Using OpenCL Programmers write a single portable
program that uses ALL resources !
in the heterogeneous platform!



OpenCL Platform Model
•  One Host connected to one or more Compute Devices"
•  Compute device can be a CPU, GPU or other processor"

•  Each Compute Device is composed of one or more Compute Units"
•  Compute Unit can may be a core, multi-processor, etc."

•  Each Compute Unit is further divided into one or more Processing Elements "
•  Processing Elements execute code as SIMD or SPMD!
PROCESSING ELEMENT

….
COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE
UNIT

.....

COMPUTE DEVICE

COMPUTE DEVICE

HOST!

COMPUTE
UNIT

Anatomy of OpenCL Application
OpenCL Application
Device Code
- Written in OpenCL C
- Executes on the device

Host Code
- Written in C/C++
- Executes on the host

COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE
UNIT

COMPUTE DEVICE

….

HOST!

COMPUTE
UNIT

COMPUTE
UNIT

.....

COMPUTE
DEVICES

COMPUTE
UNIT

COMPUTE DEVICE

•  Host code sends commands to the Devices:"

•  To transfer data between host memory and device memories!
•  To execute device code!


Anatomy of OpenCL Application
•  Serial code executes in a Host (CPU) thread"
•  Parallel code executes in many Device (GPU) threads across multiple processing elements"
OCL Application
Serial code
Parallel code
Serial code
Parallel code

Host = CPU

Device = GPU

…

Host = CPU

Device = GPU


…

OpenCL Execution Model
•  OpenCL application runs on a Host which submits
work to the Compute Devices!
•  Work item: the basic unit of work on an OpenCL device"
•  Kernel: the code for a work item, which is basically C
function"
•  Program: Collection of kernels and other functions
(analogous to a dynamic library). Managed by host."
•  Context: The environment within which work-items
execute, which includes devices and their memories and
command queues (contains all resources for computation)"
•  Command queue: A queue used by the Host application
to submit work to a Device (kernel execution instances)"
•  Work is queued in-order, one queue per device"
•  Work can be executed in-order or out of order"
•  Events are used for synchronisation"

MEMORY!

GPU!

CPU!

CONTEXT
GPU
&
CPU
Queues

COMMANDS

OpenCL Execution Model
•  Portable execution model that allows a kernel to execute at each point in a
problem domain (N-dimensional computational domain) à decomposition of a
task into work-items!
Traditional loop as a function in C

OpenCL C kernel

void !
addVector(const float *A,!
const float *B,!
float *C,!
int N)!
{!
int index;!

__kernel void !
addVector(__global const float *A,!
__global const float *B,!
__global float *C,!
int N)!
{!
int index = get_global_id(0);!

!

!
for (index=0; index<N, index++)!
C[index] = A[index]+B[index];!
}!

if (index < N)!
}!
!

Work item: the basic unit of work on an OpenCL device
Kernel: the code for a work item, which is basically C function

Kernel Execution on Platform Model
Work-Item

Compute element

Work-Group

Compute unit

Kernel execution instance

•  Each work-item is executed by a
compute element!
•  Each work-group is executed on a
compute unit"
•  Several concurrent work-groups can
reside on one compute unit depending
on work-groupʼs memory requirements
and compute unitʼs memory resources"

Compute device

…


•  Each kernel is executed on a compute
device!

Benefits of Work-Groups
•  Automatic scalability across devices with different numbers of compute units"
•  Work-groups can execute in any order, concurrently or sequentially"

•  Efﬁcient cooperation between work-items of same work-group"
•  Fast shared memory and synchronization"

•  Independence between work-groups gives scalability:"
•  A kernel scales across any number of compute units"
Device with 2 compute units

Kernel
Launch

Device with 4 compute units

Unit 0

Unit 1

Unit 0

Unit 1

Unit 2

Unit 3

Work-group 0!

Work-group 1!

Work-group 0!

Work-group 0!

Work-group 1!

Work-group 2!

Work-group 3!

Work-group 2!

Work-group 3!

Work-group 1!

Work-group 4!

Work-group 5!

Work-group 6!

Work-group 7!

Work-group 4!

Work-group 5!

Work-group 2!

Work-group 6!

Work-group 7!

Work-group 3!
Work-group 4!
Work-group 5!
Work-group 6!
Work-group 7!


Work-group synchronisation
•  Always deﬁne the best N-dimensional index
space (NDRange) for your algorithms
(currently 1D, 2D and 3D index spaces are
supported)"
•  Kernels are executed across a global domain of
work-items!
•  Work-items are single points of execution and
are grouped into local work-groups!
•  Global Dimensions: 1024x1024 (whole problem space)"
•  Local Dimensions: 32x32 (work-group)"

Cannot synchronise outside "
of work-groups"


1024

1024

Synchronisation between work-items"
possible only within workgroups:"
barriers and memory fences!

Work-items and work-groups
•  A kernel is a function executed in each point of a problem
domain (for each work-item)"
•  Number of work items = 4096 (16 work-groups, 256 workitems each):"
get_group_id(0) = 2

DEVICE

__kernel void !
__global float *C,!
int N)!
{!
!
if (index < N)!
}!

get_global_id(0) = 1792

NDRANGE
0

1

2

3

4

…

15

get_global_size(0) = 4096

0

1

get_num_groups (0) = 16

…

WORK GROUP

255
WORK ITEM

get_local_size(0) = 256

get_local_id(0) = 255

Work-items and work-groups in 2D
•  Number of work items to execute 128 x 128 = 16384:" (A kernel is executed in each point of a problem domain)
get_group_id(0),get_group_id(1)

DEVICE
0,0 1,0 2,0

…

7,0

0,0 1,0 2,0
0,1

1,1

0,2

0,2

…

1,1

…

15,0
4,1

…

2,2

3,4

.
0,7
get_global_size(0)
get_global_id(0),get_global_id(1)

7,7

0,15
get_local_size(0)
get_local_id(0),get_local_id(1)

get_local_size(1)

get_global_size(1)

0,1

WORK ITEMS

WORK GROUP

NDRANGE

OpenCL Memory Model
•  Address spaces"
• 
• 
• 
• 

Private: read/write access for work-item only"
Local: read/write access for entire work-group"
Global/Constant: visible to all work-groups"
Host: accessible by the CPU"

•  Synchronisation"

Private
Memory!

Private
Memory!

Private
Memory!

Private
Memory!

Work Item1

Work ItemJ

Work Item1

Work ItemJ

PE!

PE!

PE!

PE!

Compute Unit 1
Local Memory!

•  All Synchronisation for all memory accesses
must be done explicitly"

Compute Unit N
Local Memory!

Global/Constant Memory!

Compute Device

Memory management is Explicit!
You must move data from host à global à local … and back"


Host Memory!

Host

OpenCL Programming

• 
• 
• 
• 

How to deﬁne the platform"
How to execute code on the platform"
How to move data around in memory"
How to write (and build) programs"

OpenCL Language and API Highlights
•  Platform Layer API (called from host)"
•  Abstraction layer for diverse computational resources"
•  Query, select and initialise compute devices"
•  Create compute contexts and work-queues"

•  Runtime API (called from host)"
•  Launch compute kernels"
•  Set kernel execution conﬁguration"
•  Manage scheduling, compute, and memory resources"

•  OpenCL language"
•  To write C-based compute kernels for execution on a compute device"
•  Includes rich set of build-in functions"
•  Can be compiled JIT/Online or ofﬂine"

OpenCL Language Highlights
•  Function qualifiers"

__kernel void !
__global float *C,!
int N)!
{!

•  __kernel qualifier declares a function as a kernel"

•  Address space qualifiers"

!
if (index < N)!
}!

•  __global, __local, __constant, __private"

•  Work-item functions"
•  get_work_dim(), get_global_id(), get_local_id(), get_group_id(), get_local_size()"

•  Image functions"
•  Images must be accessed through built-in functions"
•  Read/writes performed through sampler objects from host or defined in source"

•  Synchronisation functions"
•  Barriers – all work-items within a work-group must execute the barrier function
before any work-item in the work-group can continue"

OpenCL Framework: Overview
•  Platform layer: platform query and context creation"
•  Compiler for OpenCL C"
•  Runtime: memory management and command execution within a context"
CPU!

GPU!
CONTEXT!
KERNELS!

PROGRAMS!

__kernel void !
addVector(!
__global float *A,!
__global float *C)!
{!
int i = get_global_id(0);!
C[i] = A[i]+B[i];!
}!

GPU binary!

addVector!

CPU binary!

MEMORY OBJECTS!
BUFFERS!

IMAGES!

arg[0] value!

IN
ORDER!
QUEUE!

OUT OF
ORDER
QUEUE!

arg[1] value!
arg[2] value!

COMPILE CODE!

COMMAND QUEUES!

CREATE ARGS AND DATA!


COMPUTE DEVICE

SEND TO EXECUTION!

OpenCL Framework: Objects Types
• 
• 
• 
• 
• 
• 
• 

cl_platform_id
"– identifier for a specific platform"
cl_device_id
"– identifier for a specific compute device "
cl_context
"– handle for a compute context"
cl_command_queue "– handle for a command queue (for a compute device)"
cl_mem
"– handle for a memory resource (managed by context)"
cl_program
"– handle for a program resource (library of kernels)"
cl_kernel
"– handle for a compute kernel "

•  All object types are opaque handles"
•  Enables cross-platform compatibility for complex data types"

•  All objects are reference counted and garbage collected"
•  When reference count reaches zero, object is deallocated"


OpenCL Framework: Platform Layer
•  To query platform information:"
•  clGetPlatformIDs() à obtain the list of platforms available"
•  clGetPlatformInfo() à platform proﬁle, version, name, vendor, extensions"

•  To query Devices: "
•  clGetDeviceIDs() à obtain the list of devices available on platform"
•  clGetDeviceInfo() à type, capabilities, vendor, name, etc."

•  Create an OpenCL context for one or more devices"
One or more devices!
cl_device_id!

Context!

cl_context!

Memory and device code shared by these devices!
cl_mem

!cl_program!

Command queues to send commands to these devices!
cl_command_queue!


Context creation: platform IDs
•  SIMPLE EXAMPLE get the platform ID:!
"

// get ﬁrst OpenCL platform ID available"
cl_platform_id platform;"
err = clGetPlatformIDs(1, &platform, NULL);"

cl_int clGetPlatformIDs(!
cl_uint num_entries,"
cl_platform_id *platforms,"
cl_uint *num_platforms)"

•  Get all platform IDs:!
"

// get number of OpenCL platforms available"
cl_int err;"
cl_uint num_platforms;"
std::vector<cl_platform_id> platformIDs;"
err = clGetPlatformIDs(NULL, NULL, &num_platforms);
if (err != CL_SUCCESS) { … }
platformIDs.resize(num_platforms);
// get all OpenCL platform IDs
err = clGetPlatformIDs(num_platforms, &platformIDs[0], NULL);


If NULL, the arguments are ignored

Context creation: device IDs
•  SIMPLE: get ﬁrst GPU associated with the platform:"
"

cl_device_id device;"
err = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 1, &device, NULL);"

•  Get all platform IDs:"
"

cl_uint nDevices;"
cl_device_type deviceType;"
vector<cl_device_id> deviceIDs;"
"

cl_int clGetDeviceIDs(!
cl_platform_id platform,"
cl_device_type device_type,"
cl_uint num_entries,"
cl_device_id *devices,"
cl_uint *num_devices)"
DEVICE TYPE:!

if (platformIDs.size() == 0) {"
CL_DEVICE_TYPE_CPU"
// get number of device IDs for default platform"
CL_DEVICE_TYPE_GPU"
CL_DEVICE_TYPE_ACCELERATOR"
err = clGetDeviceIDs(NULL, deviceType, 0, NULL, &nDevices); "
CL_DEVICE_TYPE_DEFAULT"
} else {"
CL_DEVICE_TYPE_ALL"
// get number of device IDs for selected platform"
err = clGetDeviceIDs(platformIDs[selectedPlatform], deviceType, 0, NULL, &nDevices); "
}"
deviceIDs.resize(nDevices);"
if (platformIDs.size() == 0) {"
// get default device IDs of default platform"
err = clGetDeviceIDs(NULL, deviceType, nDevices, &deviceIDs[0], NULL); "
} else {"
// get device IDs of selected platform"
err = clGetDeviceIDs(platformIDs[selectedPlatform], deviceType, nDevices, &deviceIDs[0], NULL); "
}"

Context creation
•  SIMPLE EXAMPLE: create context object!
"

cl_context context;"
context = clCreateContext(NULL, 1, &device, NULL, NULL, NULL);"

•  Create OpenCL context for few devices:!
"

cl_int err;"
cl_context context;
context = clCreateContext(NULL, deviceIDs.size(), &deviceIDs[0], NULL, NULL, &err);
if (err != CL_SUCCESS) { … }
cl_context clCreateContext(!
const cl_context_properties *properties,"
cl_uint num_devices,"
const cl_device_id *devices, "
void CL_CALLBACK *pfn_notify,"
void *user_data,"
cl_int *errcode_ret)"

cl_contet_properties_enum:!
CL_CONTEXT_PLATFORM"
CL_CONTEXT_D3D10_DEVICE_KHR"
CL_GL_CONTEXT_KHR"
CL_EGL_DISPLAY_KHR"
..."
…"


Error Handling and Resource Deallocation
•  Error handling:"
•  All host functions return an error code"
•  Context error callback"
•  The callback function may be called asynchronously by OpenCL and it is the applicationʼs
responsibility to ensure that the callback function is thread-safe"

•  Resource deallocation"
•  Reference counting API: clRetain*(), clRelease*()"
• 
• 
• 
• 
• 
• 

clRetainContext();"
clReleaseContext();"
clRetainMemObject();"
clReleaseMemObject();"
clRetainKernel();"
clReleaseKernel();"


OpenCL C
•  Derived from ISO C99!
•  Features added to the language:!
•  Work-items and work-groups"
•  Vector types"
•  Synchronisation"
•  Address space qualiﬁers"
•  Also includes a large set of built-in functions:!
•  Image manipulation"
•  Work-item manipulation"
•  Math functions"


OpenCL C
Language Restrictions:!
•  No functions deﬁned in C99 standard headers"
•  No recursion supported"
•  Pointers to function are not permitted"
•  Pointers to pointers allowed within a kernel, but not as an argument"
•  No variable length arrays and structures"
•  Bit ﬁelds are not supported"
•  Writes to a pointer to a type less than 32 bits are not supported*"
•  Double types are not supported, but reserved"
•  3D Image writes are not supported"
"

"
*Some restrictions are addressed through extensions

"


OpenCL C Optional Extensions
•  Extensions are optional features exposed through OpenCL"
•  The OpenCL working group has already approved many extensions to the
OpenCL speciﬁcation:"
• 
• 
• 
• 
• 
• 

Double precision ﬂoating-point types"
Built-in functions to support doubles"
Atomic functions*"
Byte-addressable stores (write to pointers to types < 32 bits)*"
3D Image writes"
Built-in functions to support half types"

* New core features in OpenCL 1.1


OpenCL C: Data Types
•  Scalar data types"
•  char, uchar, short, ushort, int, uint, long, ulong, ﬂoat"
•  bool, intptr_t, ptrdiff_t, size_t, uintptr_t, void, half (storage)"

•  Image types"
•  Image2d_t, image3d_t, sampler_t, event_t"

•  Vector data types"
• 
• 
• 
• 
• 

Vector lengths 2, 3*, 4, 8, 16 (char2, ushort4, int8, ﬂoat16, double2^, …)"
Endian safe"
Aligned at vector length"
Vector operations"
Built-in function "

* New core features in OpenCL 1.1
^ Double is optional type in OpenCL

OpenCL C: Synchronisation Primitives
•  Built-in functions to order memory operations and synchronise execution:"
•  mem_fence(CLK_LOCAL_MEM_FENCE and/or CLK_GLOBAL_MEM_FENCE)"
•  Waits until all reads/writes to local and/or global memory made by calling work-item prior to
mem_fence() are visible to all threads in the work-group"

•  barrier(CLK_LOCAL_MEM_FENCE and/or CLK_GLOBAL_MEM_FENCE)"
•  Waits until all work-items in the work-group have reached this point and calls mem_fence
(CLK_LOCAL_MEM_FENCE and/or CLK_GLOBAL_MEM_FENCE)"

•  Used to coordinate accesses to local or global memory shared among workitems "


OpenCL Runtime

• 
• 
• 
• 

Command queues creation and management"
Device memory allocation and management"
Device code compilation and execution"
Event creation and management
(synchronisation and proﬁling)"

Kernel Compilation
•  We use cl_program object that encapsulates some source code and its last
successful build (it may contain several kernel functions): "
•  clCreateProgramWithSource() à creates a program object for a context, and loads
the source code speciﬁed by the strings array into the program object"
•  clCreateProgramWithBinary() à create program objects and loads the binary there"
•  clBuildProgram() à compiles and links a program executable from program source
or binary"

•  Weʼll use also cl_kernel object which encapsulates the values of the kernelʼs
arguments used when the kernel is executed: "
•  clCreateKernel() à creates a kernel object from successfully compiled program "
•  clSetKernelArg() à sets the argument value for a speciﬁc argument of a kernel"


Kernel Compilation
•  Write a kernel:"
"

const char* src = ”__kernel void vectorMul(__global const float *a,n” "
”
__global const float *b,n” "
”
__global float *c,n” "
”
int numElements)n”"
”{n”"
"
”
int i = get_global_id(0);n”"
"
”
if (i < numElements)n”"
”
c[i] = a[i]*b[i];n”"
”}n”;"

•  Create program:

"

cl_program program = "
clCreateProgramWithSource(context, 1, &src, NULL, NULL); "

•  Build program and create kernel:

cl_program clCreateProgramWithSource(!
cl_context context,"
cl_uint count,"
const char **strings,"
const size_t *lengths,"
cl_int clBuildProgram(!
cl_program program,"
cl_uint num_devices,"
const cl_device_id *device_list,"
const char *options;"
void CL_CALLBACK *pfn_notify,"
void *user_data)"

"

clBuildProgram(program, 0, NULL, NULL, NULL, NULL); "
cl_kernel kernel = clCreateKernel(program, ”vectorMul”, NULL);"

•  Set kernel arguments:

"

clSetKernelArg(kernel, 0, sizeof(cl_mem), (void*)&devSrcA); "
clSetKernelArg(kernel, 1, sizeof(cl_mem), (void*)&devSrcB);
clSetKernelArg(kernel, 2, sizeof(cl_mem), (void*)&devDst);
clSetKernelArg(kernel, 3, sizeof(cl_int), (void*)&numElements); "
"


-cl-opt-disable, !
-cl-mad-enable!
…"
cl_kernel clCreateKernel(!
cl_program program,"
const char *kernel_name,"

Memory Objects
•  Memory objects (cl_mem) are categorized into two types:"
•  Buffer objects"
•  Image objects!

•  Memory objects can be copied to host memory, from host memory, or to other
memory objects"
•  Kernels take memory objects as input, and output to one or more memory
objects"
•  Regions of a memory object can be accessed by host by mapping them into
the host address space"


Memory Objects: Buffer Object
•  A buffer object stored a one-dimensional collection of elements (1D array)"
•  Elements of a buffer object can be:"
•  Scalar data type (such as an int, ﬂoat)"
•  Vector data type"
•  User-deﬁned structure"

•  Elements in a buffer are stored in sequential fashion and can be accessed
using pointer by a kernel executing on a device"
•  Data is stored in the same format as it is accessed by the kernel"


Memory Objects: Image Object
•  Image object stores a two- or three-dimensional texture, frame-buffer or
image"
•  Can be created from existing OpenGL texture or render-buffer"
•  The elements of an image object are selected from a list of predefined image
formats"
•  Image elements are always a 4-component vector (each component can be a
float or signed/unsigned integer) in a kernel"
•  Accessed within device via built-in functions (storage format not exposed to
application)"
•  Sampler objects are used to configure how built-in functions sample images
(addressing modes, filtering modes)"


Command Queue
•  Memory, program and kernel objects à created using a context"
•  Operations on objects performed using a command-queue"
•  The command-queue used to schedule commands for execution on a device"
•  En-queuing functions: clEnqueue*()"
•  Multiple queues can execute on the same device"

•  Modes of execution:"
•  In-order: Each command in the queue executes only when the proceeding
command has completed (including memory writes) "
•  Out-of-order: No guaranteed order of completion for commands"
•  CL_QUEUE_PROFILING ENABLE: enable or disable proﬁling commands in the
command-queue"


Command Queue
•  Create command queue for a specific device"
cl_command_queue queue = clCreateCommandQueue(context, device, 0, NULL); "
cl_command_queue clCreateCommandQueue(!
cl_device_id device,"
cl_command_queue_properties properties,"

•  Properties"
•  CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE determines if command-queue are
executed in-order or out-of-order. If set, the commands are executed out-of-order."
•  CL_QUEUE_PROFILING_ENABLE enables or disables profiling of commands in the
command-queue. If set, the profiling of commands is enabled. "


Data Transfer between Host and Device
•  Create buffers on host and device

"

size_t size = 100000*sizeof(int);"
int *host_buffer = (int*)malloc(size); "
cl_mem devSrcA =
clCreateBuffer(context, CL_MEM_READ_WRITE, size, NULL, NULL); "
cl_mem devSrcB =
clCreateBuffer(context, CL_MEM_READ_WRITE, size, NULL, NULL);
…"

•  Write to buffer objects from host memory

"

clEnqueueWriteBuffer(queue, devSrcA, "
CL_FALSE, 0, size, host_buffer, 0, NULL, NULL); "
…"

•  Read from buffer object to host memory

"

clEnqueueReadBuffer(queue, devDst, "
CL_TRUE, 0, size, host_buffer, 0, NULL, NULL); "
…"


cl_mem clCreateBuffer(!
cl_mem_ﬂags ﬂags,"
size_t size,"
void *host_ptr,"
CL_MEM_READ_WRITE,!
CL_MEM_WRITE_ONLY,!
CL_MEM_READ_ONLY,!
…"
cl_int clEnqueueWriteBuffer(!
cl_command_queue queue,"
cl_mem buffer,"
cl_bool blocking_write,"
size_t offset,"
size_t size,"
const void *ptr,"
cl_uint num_events_in_wait_list,!
const cl_event *event_wait_list,"
cl_event *event)"

Kernel Invocation over NDRange
•  Host code invokes a kernel over an index space NDRange (1D, 2D or 3D)!
•  Work-group dimensionality matches work-item dimensionality"
•  Set number of work-items in a work-group"
size_t localWorkSize = 256;"
int numWorkGroups = (N+localWorkSize-1)/localWorkSize; // round up"
size_t globalWorkSize = numWorkGroups * localWorkSize; // must be divisible by localWorkSize

•  Enqueue kernel"
clEnqueueNDRangeKernel("
queue, kernel 1, NULL, &globalWorkSize, &localWorkSize, 0, NULL, NULL); "


cl_int clEnqueueNDRangeKernel(!
cl_command_queue queue,"
cl_kernel kernel,"
Cl_uint work_dim,"
cont size_t *global_work_offset,"
cont size_t *global_work_size,"
cont size_t *local_work_offset,"
cl_uint num_events_in_wait_list,!
const cl_event *event_wait_list,"
cl_event *event)"

Command Synchronisation
•  Queue barrier command: clEnqueueBarrier()"
•  Commands after the barrier start executing only after all commands before the
barrier have completed"

•  Events: a cl_event object can be associated with each command"
•  Commands return evens and obey event waitlist"
•  clEnqueue*(…, num_events_in_waitlist, *event_waitlist, *event);"

•  Any commands (or clWaitForEvents()) can wait on events before executing"
•  Event object can be queried to track execution status of associated command and
get proﬁling information"

•  Some clEnqueue*() calls can be optionally blocking"
•  clEnqueueReadBuffer(…, CL_TRUE, …);"


Synchronisation: Queues & Events
•  You must explicitly synchronise between queues"
•  Multiple devices each have their own queue (possibly multiple queues per device)"
•  Use events to synchronise kernel executions between queues"


OpenCL Resources
•  OpenCL at Khronos"
•  http://www.khronos.org/opencl (spec, registry, man, forums, reference card)"

•  NVIDIA OpenCL website, forum"
•  http://www.nvidia.com/object/cuda_opencl_new.html"
•  http://developer.nvidia.com/object/opencl.html (drivers, proﬁler, code samples)"

•  AMD Developer Central"
•  http://developer.amd.com/gpu/atistreamsdk/pages/default.aspx"

•  Intel OpenCL SDK"
•  http://software.intel.com/en-us/articles/intel-opencl-sdk/"

•  IBM OpenCL Development Kid for Linux on Power"
•  http://www.alphaworks.ibm.com/tech/opencl"

•  OpenCL Studio"
•  http://www.opencldev.com (develop, visualize, prototype UIs)"


Earth Science and Resource Engineering
Tomasz P Bednarz
3D Visualisation Engineer
Mining Technology Team
Mobile: +61 429 153 274
Email: tomasz.bednarz(_at_)csiro.au
Web: www.tomaszbednarz.com

Acknowledgments
Mark Harris, Derek Gerstmann, Mike Houston, Justin Hensley, Jason Young, Dominik Behr, Con Caris,
John Taylor, Khronos Group, AMD, NVIDIA and all others for sharing publicly their GPGPU knowledge
(this presentation is based on)

Thank you …

Contact us
Phone: 1300 363 400 or +61 3 9545 2176
Email: enquiries@csiro.au Web: www.csiro.au

Introduction to OpenCL, 2010

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Viewers also liked

Viewers also liked (20)

Similar to Introduction to OpenCL, 2010

Similar to Introduction to OpenCL, 2010 (20)

More from Tomasz Bednarz

More from Tomasz Bednarz (16)

Recently uploaded

Recently uploaded (20)

Introduction to OpenCL, 2010