Code gpu with cuda - CUDA introduction

Code gpu with cuda - CUDA introduction

• 1.
  CODE GPU WITHCUDA CUDA INTRODUCTION CreatedbyMarinaKolpakova( )forcuda.geek Itseez PREVIOUS
• 2.
  OUTLINE Terminology Definition Programming model Execution model Memorymodels CUDA kernel
• 3.
  OUT OF SCOPE CUDAAPI overview
• 4.
  TERMINOLOGY Device CUDA-capable NVIDIA GPU Devicecode code executed on the device Host x86/x64/arm CPU Host code code executed on the host Kernel concrete device function
• 5.
  CUDA CUDA is aCompute Unified Device Arhitecture. CUDA includes: 1. Capable GPU hardware and driver 2. Device ISA, GPU assembler, Compiler 3. C++ based HL language, CUDA Runtime CUDA defines: programming model execution model memory model
• 6.
  PROGRAMMING MODEL Kernel isexecuted by many threads
• 7.
  PROGRAMMING MODEL Threads aregrouped into blocks Each thread has a thread ID
• 8.
  PROGRAMMING MODEL Thread blocksform an execution grid Each block has a block ID
• 9.
  EXECUTION (HW MAPPING)MODEL Single thread is executed on core
• 10.
  EXECUTION (HW MAPPING)MODEL Each block is executed by one SM and does not migrate Number of concurrent blocks that can reside on SM depends on available resources
• 11.
  EXECUTION (HW MAPPING)MODEL Threads in a block can cooperate via shared memory and synchronization There is no hardware support for cooperation between threads from different blocks
• 12.
  EXECUTION (HW MAPPING)MODEL One or multiple (sm_20+) kernels are executed on the device
• 13.
  MEMORY MODEL Thread hasits own registers
• 14.
  MEMORY MODEL Thread hasits own local memory
• 15.
  MEMORY MODEL Block hasshared memory Pointer to shared memory is valid while block is resident _ _ s h a r e d _ _ f l o a t b u f f e r [ C T A _ S I Z E ] ;
• 16.
  MEMORY MODEL Grid isable to access global and constant memory
• 17.
  BASIC CUDA KERNEL Workfor GPU threads represented as kernel kernel represents a task for single thread (scalar notation) Every thread in a particular grid executes the same kernel Threads use their threadIdx and blockIdx to dispatch work Kernel function is marked with __global__ keyword Common kernel structure: 1. Retrieving position in grid (widely named tid) 2. Loading data form GPU’s memory 3. Performing compute work 4. Writing back the result into GPU’s memory _ _ g l o b a l _ _ v o i d k e r n e l ( f l o a t * i n , f l o a t * o u t ) { i n t t i d = b l o c k I d x . x * b l o c k D i m . x + t h r e a d I d x . x ; o u t [ t i d ] = i n [ t i d ] ; }
• 18.
  KERNEL EXECUTION v oi d e x e c u t e _ k e r n e l ( c o n s t * f l o a t h o s t _ i n , f l o a t * h o s t _ o u t , i n t s i z e ) { f l o a t * d e v i c e _ i n , * d e v i c e _ o u t ; c u d a M a l l o c ( ( v o i d * * ) & d e v i c e _ i n , s i z e * s i z e o f ( f l o a t ) ) ; c u d a M a l l o c ( ( v o i d * * ) & d e v i c e _ o u t , s i z e * s i z e o f ( f l o a t ) ) ; / / 1 . U p l o a d d a t a i n t o d e v i c e m e m o r y c u d a M e m c p y ( d e v i c e _ i n , h o s t _ i n , c u d a M e m c p y H o s t T o D e v i c e ) ; / / 2 . C o n f i g u r e k e r n e l l a u n c h d i m 3 b l o c k ( 2 5 6 ) ; d i m 3 g r i d ( s i z e / 2 5 6 ) ; / / 3 . E x e c u t e k e r n e l k e r n e l < < < g r i d , b l o c k > > > ( d e v i c e _ i n , d e v i c e _ o u t ) ; / / 4 . W a i t t i l l c o m p l e t i o n c u d a T h r e a d S y n c h r o n i z e ( ) ; / / 5 . D o w n l o a d r e s u l t s i n t o h o s t m e m o r y c u d a M e m c p y ( h o s t _ o u t , d e v i c e _ o u t , c u d a M e m c p y D e v i c e T o H o s t ) ; }
• 19.
  FINAL WORDS CUDA isa set of capable GPU hardware, driver, GPU ISA, GPU assembler, compiler, C++ based HL language and runtime which enables programming of NVIDIA GPU CUDA function (kernel) is called on a grid of blocks Kernel runs on unified programmable cores Kernel is able to access registers and local memory, share memory inside a block of threads and access RAM through global, texture and constant memories
• 20.
  THE END NEXT BY /2013–2015CUDA.GEEK