https://modal.com/gpu-glossary/readme

 
GPU Glossary
GPU Glossary
Terminal Light green Light
Sign Up
TABLE OF CONTENTS
Home -
README
Device Hardware -
CUDA (Device Architecture)
Streaming Multiprocessor
SM
Core
Special Function Unit
SFU
Load/Store Unit
LSU
Warp Scheduler
CUDA Core
Tensor Core
Streaming Multiprocessor Architecture
Texture Processing Cluster
TPC
Graphics/GPU Processing Cluster
GPC
Register File
L1 Data Cache
GPU RAM
Device Software -
CUDA (Programming Model)
Streaming ASSembler
SASS
Parallel Thread eXecution
PTX
Compute Capability
Thread
Warp
Cooperative Thread Array
Kernel
Thread Block
Thread Block Grid
Memory Hierarchy
Registers
Shared Memory
Global Memory
Host Software -
CUDA (Software Platform)
CUDA C++ (programming language)
NVIDIA GPU Drivers
nvidia.ko
CUDA Driver API
libcuda.so
NVIDIA Management Library
NVML
libnvml.so
nvidia-smi
CUDA Runtime API
libcudart.so
NVIDIA CUDA Compiler Driver
nvcc
NVIDIA Runtime Compiler
NVIDIA CUDA Profiling Tools Interface
CUPTI
NVIDIA Nsight Systems
CUDA Binary Utilities
Contributors
/readme

README

 ######+ ######+ ##+   ##+
##+----+ ##+--##+##|   ##|
##|  ###+######++##|   ##|
##|   ##|##+---+ ##|   ##|
+######++##|     +######++
 +-----+ +-+      +-----+
 ######+ ##+      ######+ #######+#######+ #####+ ######+ ##+   ##+
##+----+ ##|     ##+---##+##+----+##+----+##+--##+##+--##++##+ ##++
##|  ###+##|     ##|   ##|#######+#######+#######|######++ +####++
##|   ##|##|     ##|   ##|+----##|+----##|##+--##|##+--##+  +##++
+######++#######++######++#######|#######|##|  ##|##|  ##|   ##|
 +-----+ +------+ +-----+ +------++------++-+  +-++-+  +-+   +-+


We wrote this glossary to solve a problem we ran into working with
GPUs here at Modal : the documentation is fragmented, making it
difficult to connect concepts at different levels of the stack, like
Streaming Multiprocessor Architecture , Compute Capability , and nvcc
compiler flags .

So we've read the PDFs from NVIDIA , lurked in the good Discords ,
and even bought dead-tree textbooks to put together a glossary that
spans the whole stack in one place.

This glossary, unlike a PDF or a Discord or a book, is a hypertext
document -- all pages are inter-linked with one another, so you can
jump down to read about the Warp Scheduler so you can better
understand the threads that you came across in the article on the
CUDA programming model .

You can also read it linearly. To navigate between pages, use the
arrow keys, the arrows at the bottom of each page, or the table of
contents (in the sidebar on desktop or in the hamburger menu on
mobile).

Home
Something seem wrong?
Or want to contribute?
Email: glossary@modal.com
Device Hardware ?