TechDays

Сентябрь 5, 2022

Содержание

2. General Programming on Graphical Processing Units Quentin Ochem October 4th, 2018
3. What is GPGPU? GPU were traditionally dedicated to graphical rendering … … but their capability is
4. GPGPU Programming Paradigm Debug? Optimize data transfer? How to optimize occupancy Avoid data races? Refactor parallel
5. Why do we care about Ada? (1/2) Source: https://www.adacore.com/uploads/techPapers/Controlling-Costs-with-Software-Language-Choice-AdaCore-VDC-WP.PDF
6. Why do we care about Ada (2/2) Signal processing Machine learning Monte-carlo simulation Trajectory prediction Cryptography
7. Available Hardware NVIDIA GeForce / Tesla / Quadro AMD Radeon Intel HD NVIDIA Tegra ARM Mali
8. Ada Support
9. Three options Interfacing with existing libraries “Ada-ing” existing languages Ada 2020
10. Interfacing existing libraries Already possible and straightforward effort “gcc –fdump-ada-specs” will provide a first binding of
11. “Ada-ing” existing languages CUDA – kernel-based language specific to NVIDIA OpenCL – portable version of CUDA
12. CUDA Example (Device code) procedure Test_Cuda (A : out Float_Array; B, C : Float_Array) with Export
13. CUDA Example (Host code) A, B, C : Float_Array; begin -- initialization of B and C
14. OpenCL example Similar to CUDA in principle Requires more code on the host code (no call
15. OpenACC example (Device & Host) procedure Test_OpenACC is A, B, C : Float_Array; begin -- initialization
16. Ada 2020 procedure Test_Ada2020 is A, B, C : Float_Array; begin -- initialization of B and
17. Lots of other language considerations Identification of memory layout (per thread, per block, global) Thread allocation
18. A word on SPARK X_Size : 1000; Y_Size : 10; Data : array (1 .. X_Size
20. Скачать презентацию

Слайд 2

General Programming on Graphical Processing Units
Quentin Ochem
October 4th, 2018

Слайд 3

What is GPGPU?
GPU were traditionally dedicated to graphical rendering …
… but

their capability is really vectorized computation
Enters General Programming GPU (GPGPU)

Слайд 4

GPGPU Programming Paradigm
Debug?
Optimize data transfer?
How to optimize occupancy
Avoid data races?
Refactor parallel

algorithms?

Слайд 5

Why do we care about Ada? (1/2)
Source: https://www.adacore.com/uploads/techPapers/Controlling-Costs-with-Software-Language-Choice-AdaCore-VDC-WP.PDF

Слайд 6

Why do we care about Ada (2/2)
Signal processing
Machine learning
Monte-carlo simulation
Trajectory prediction
Cryptography
Image

processing
Physical simulation
… and much more!

Слайд 7

Available Hardware
NVIDIA GeForce / Tesla / Quadro
AMD Radeon
Intel HD
NVIDIA Tegra ARM Mali Qualcomm

Adreno IMG Power VR Freescale Vivante

Embedded

Desktop & Server

Слайд 8

Ada Support

Слайд 9

Three options
Interfacing with existing libraries
“Ada-ing” existing languages
Ada 2020

Слайд 10

Interfacing existing libraries
Already possible and straightforward effort
“gcc –fdump-ada-specs” will provide a

first binding of C to Ada
We could provide “thick” bindings to e.g. Ada.Numerics matrix operations

Слайд 11

“Ada-ing” existing languages
CUDA – kernel-based language specific to NVIDIA
OpenCL – portable

version of CUDA
OpenACC – integrated language marking parallel loops

Слайд 12

CUDA Example (Device code)
procedure Test_Cuda
(A : out Float_Array; B,

C : Float_Array)
with Export => True, Convention => C;
pragma CUDA_Kernel (Test_Cuda);
procedure Test_Cuda
(A : Float_Array; B, C : Float_Array)
is
begin
A (CUDA_Get_Thread_X) := B (CUDA_Get_Thread_X) + C (CUDA_Get_Thread_X);
end Test_cuda;

Слайд 13

CUDA Example (Host code)
A, B, C : Float_Array;
begin
-- initialization

of B and C
-- CUDA specific setup
pragma CUDA_Kernel_Call (Grid’(1, 1, 1), Block’(8, 8, 8));
My_Kernel (A, B, C);
-- usage of A

Слайд 14

OpenCL example
Similar to CUDA in principle
Requires more code on the host

code (no call conventions)

Слайд 15

OpenACC example (Device & Host)
procedure Test_OpenACC is
A, B, C :

Float_Array;
begin
-- initialization of B and C
for I in A’Range loop
pragma Acc_Parallel;
A (I) := B (I) + C (I);
end loop;
end Test_OpenACC;

Слайд 16

Ada 2020
procedure Test_Ada2020 is
A, B, C : Float_Array;
begin
-- initialization

of B and C
parallel for I in A’Range loop
A (I) := B (I) + C (I);
end loop;
end Test_Ada2020;

Слайд 17

Lots of other language considerations
Identification of memory layout (per thread, per

block, global)
Thread allocation specification
Reduction (ability to aggregate results through operators e.g. sum or concatenation)
Containers
Mutual exclusion
…

Слайд 18

A word on SPARK
X_Size : 1000;
Y_Size : 10;
Data

: array (1 .. X_Size * Y_Size) of Integer;
begin
for X in 1 .. X_Size loop
for Y in 1 .. Y_Size loop
Data (X + Y_Size * Y) := Compute (X, Y);
end loop;
end loop;

{X = 100, Y = 1}, X + Y * Y_Size = 100 + 10 = 110
{X = 10, Y = 10}, X + Y * Y_Size = 10 + 100 = 110

TechDays

Содержание

General Programming on Graphical Processing UnitsQuentin OchemOctober 4th, 2018

What is GPGPU?GPU were traditionally dedicated to graphical rendering …… but

GPGPU Programming ParadigmDebug?Optimize data transfer?How to optimize occupancyAvoid data races?Refactor parallel

Why do we care about Ada? (1/2)Source: https://www.adacore.com/uploads/techPapers/Controlling-Costs-with-Software-Language-Choice-AdaCore-VDC-WP.PDF

Why do we care about Ada (2/2)Signal processingMachine learningMonte-carlo simulationTrajectory predictionCryptographyImage

Available HardwareNVIDIA GeForce / Tesla / QuadroAMD RadeonIntel HDNVIDIA Tegra ARM Mali Qualcomm

Ada Support

Three optionsInterfacing with existing libraries“Ada-ing” existing languagesAda 2020

Interfacing existing librariesAlready possible and straightforward effort“gcc –fdump-ada-specs” will provide a

“Ada-ing” existing languagesCUDA – kernel-based language specific to NVIDIAOpenCL – portable

CUDA Example (Device code)procedure Test_Cuda (A : out Float_Array; B,

CUDA Example (Host code) A, B, C : Float_Array;begin -- initialization

OpenCL exampleSimilar to CUDA in principleRequires more code on the host

OpenACC example (Device & Host)procedure Test_OpenACC is A, B, C :

Ada 2020procedure Test_Ada2020 is A, B, C : Float_Array;begin -- initialization

Lots of other language considerationsIdentification of memory layout (per thread, per

A word on SPARK X_Size : 1000; Y_Size : 10; Data

Похожие презентации