Bahasa Indonesia
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어

#gpuprogramming hasil pencarian

tatavishnurao's profile picture. 20, AI Engineer(GPU Poor); ai research intern @ startup | Sharing about my learnings, research & real-world insights
Vishnu
@tatavishnurao
7 Nov

Day 2 of #GPUProgramming: >read an article about shared memory >learnt about registers……..Global memory >almost blacked out from elaboration of L1 & L2 iykyk >”repetition”to digest what I just learnt for about 900k milliseconds

tatavishnurao's tweet image. Day 2 of #GPUProgramming: >read an article about shared memory >learnt about registers……..Global memory >almost blacked out from elaboration of L1 & L2 iykyk >”repetition”to digest what I just learnt for about 900k milliseconds
1
0
2
0
136
taras_y_sereda's profile picture. in search of true posterior
taras sereda 🇺🇦
 @taras_y_sereda
6 Agu 2024

"Need better CUDA textbooks. 'Programming Massively Parallel Processors' is a good intro. I've created C/CUDA C implementations for first 3 chapters. Check book & my GitHub repo for details. #CUDA #GPUprogramming"

taras_y_sereda's tweet image. "Need better CUDA textbooks. 'Programming Massively Parallel Processors' is a good intro. I've created C/CUDA C implementations for first 3 chapters. Check book & my GitHub repo for details. #CUDA #GPUprogramming"
2
0
0
0
107
shlok_fx's profile picture. 2nd Year UG @bitspilaniindia Machine learning, GPU kernels | Ex - VFX artist in Hollywood
Shlok
 @shlok_fx
8 Feb

"10 days into CUDA, and I’ve earned my first badge of honor! 🚀 From simple kernels to profiling, every day is a step closer to mastering GPU computing. Onward to 100! #CUDA #GPUProgramming #100DaysOfCUDA"

shlok_fx's tweet image. "10 days into CUDA, and I’ve earned my first badge of honor! 🚀 From simple kernels to profiling, every day is a step closer to mastering GPU computing. Onward to 100! #CUDA #GPUProgramming #100DaysOfCUDA"
1
0
3
0
155
yasunrik's profile picture. 趣味アカウント。Cloudflare, VTuber, Graphics, Programming, AI, Claude, Unity, C#, Python, Delphi, C++, aws, Anime, Manga, Gaussian Splatting, UofU, Ph.D.
ヤスリ
 @yasunrik
2 Jun

Each common operation is implemented as its own .cu file—modular. intriguing. #CUDA #NVIDIA #GPUProgramming #libcudf

yasunrik's tweet image. Each common operation is implemented as its own .cu file—modular. intriguing. #CUDA #NVIDIA #GPUProgramming #libcudf
0
0
1
0
38
LearnInShadows's profile picture. Sharing My Learning Journey One Layer at a Time.
ShadowMaster
@LearnInShadows
19 Nov

Day 3 of GPU programming At this rate I'll be writing custom inference kernels for AI by next month. The gap between PyTorch abstractions and bare metal isn't as wide as it seemed. #CUDA #GPUProgramming #MachineLearning

LearnInShadows's tweet image. Day 3 of GPU programming At this rate I'll be writing custom inference kernels for AI by next month. The gap between PyTorch abstractions and bare metal isn't as wide as it seemed. #CUDA #GPUProgramming #MachineLearning
LearnInShadows's tweet image. Day 3 of GPU programming At this rate I'll be writing custom inference kernels for AI by next month. The gap between PyTorch abstractions and bare metal isn't as wide as it seemed. #CUDA #GPUProgramming #MachineLearning
LearnInShadows's profile picture. Sharing My Learning Journey One Layer at a Time.
ShadowMaster
@LearnInShadows
18 Nov

Day 2 of GPU programming Never knew addition needs so much code 😂 Starting to get the hang of program_id. Used Gemini 3.0 to generate pseudocode since I'm new to GPU programming and didn't want full code. Lets hope this momentum continues

LearnInShadows's tweet image. Day 2 of GPU programming Never knew addition needs so much code 😂 Starting to get the hang of program_id. Used Gemini 3.0 to generate pseudocode since I'm new to GPU programming and didn't want full code. Lets hope this momentum continues
LearnInShadows's tweet image. Day 2 of GPU programming Never knew addition needs so much code 😂 Starting to get the hang of program_id. Used Gemini 3.0 to generate pseudocode since I'm new to GPU programming and didn't want full code. Lets hope this momentum continues
0
0
0
0
172
0
0
0
0
130
tatavishnurao's profile picture. 20, AI Engineer(GPU Poor); ai research intern @ startup | Sharing about my learnings, research & real-world insights
Vishnu
@tatavishnurao
8 Nov

Day 3 of #GPUProgramming: >in-depth of what shared memory is capable of >read about techniques by which these concepts optimize their performance >synchronization of threads during matmul >realized it took ~1.5 hours to digest this stuff >tried to code matrix multiplication…

tatavishnurao's tweet image. Day 3 of #GPUProgramming: >in-depth of what shared memory is capable of >read about techniques by which these concepts optimize their performance >synchronization of threads during matmul >realized it took ~1.5 hours to digest this stuff >tried to code matrix multiplication…
1
0
1
0
167
asthraris's profile picture. Future Homeless \n Current Hopeless \n 2005
Aman Gupta
 @asthraris
17 Agu

⚡ Built my own graphics engine: Asthrarisine Sounds fun? Reality = invisible meshes, memory bugs & shader headaches. But here’s what made it work: #OpenGL #GraphicsEngine #GPUProgramming #GLTF #GameDev #ShaderProgramming

2
0
6
0
200
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
10 Jan 2024

#GPUProgramming - Day 07: 🔧 #CPU Hazards 101 🚧: Ever heard of #Register Renaming & Out-of-Order Execution? They tackle structural hazards, ensuring smooth sailing for instructions. Watch out for Data Hazards (#RAW, #WAR, #WAW) in #MIPS, but fear not! #COA #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 07: 🔧 #CPU Hazards 101 🚧: Ever heard of #Register Renaming & Out-of-Order Execution? They tackle structural hazards, ensuring smooth sailing for instructions. Watch out for Data Hazards (#RAW, #WAR, #WAW) in #MIPS, but fear not! #COA #LearnInPublic
hridoy_bashir's tweet image. #GPUProgramming - Day 07: 🔧 #CPU Hazards 101 🚧: Ever heard of #Register Renaming & Out-of-Order Execution? They tackle structural hazards, ensuring smooth sailing for instructions. Watch out for Data Hazards (#RAW, #WAR, #WAW) in #MIPS, but fear not! #COA #LearnInPublic
hridoy_bashir's tweet image. #GPUProgramming - Day 07: 🔧 #CPU Hazards 101 🚧: Ever heard of #Register Renaming & Out-of-Order Execution? They tackle structural hazards, ensuring smooth sailing for instructions. Watch out for Data Hazards (#RAW, #WAR, #WAW) in #MIPS, but fear not! #COA #LearnInPublic
0
0
1
0
70
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
2 Jan 2024

#GPUProgramming - Day 02: 🔄 Exploring CPU architectures! #RISC, like #ARM & #Power, opts for efficiency with many registers. #CISC, exemplified by #Intel 8086, prioritizes simplicity, offering diverse, complex instructions. RISC excels in energy efficiency. #COA #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 02: 🔄 Exploring CPU architectures! #RISC, like #ARM & #Power, opts for efficiency with many registers. #CISC, exemplified by #Intel 8086, prioritizes simplicity, offering diverse, complex instructions. RISC excels in energy efficiency. #COA #LearnInPublic
hridoy_bashir's tweet image. #GPUProgramming - Day 02: 🔄 Exploring CPU architectures! #RISC, like #ARM & #Power, opts for efficiency with many registers. #CISC, exemplified by #Intel 8086, prioritizes simplicity, offering diverse, complex instructions. RISC excels in energy efficiency. #COA #LearnInPublic
0
0
0
0
72
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
3 Jan 2024

#GPUProgramming - Day 03: 🧠 CPUs: Processors adapt with DISA. #CPU's core duo - Control Unit & Datapath. Datapath: Registers, ALU, Buses, Multiplexers – a data symphony! 🔄 Follow the Instruction Execution Cycle: Fetch ➡️Decode➡️Execute➡️Store➡️ Update PC. 🕹️ #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 03: 🧠 CPUs: Processors adapt with DISA. #CPU's core duo - Control Unit & Datapath. Datapath: Registers, ALU, Buses, Multiplexers – a data symphony! 🔄 Follow the Instruction Execution Cycle: Fetch ➡️Decode➡️Execute➡️Store➡️ Update PC. 🕹️ #LearnInPublic
hridoy_bashir's tweet image. #GPUProgramming - Day 03: 🧠 CPUs: Processors adapt with DISA. #CPU's core duo - Control Unit & Datapath. Datapath: Registers, ALU, Buses, Multiplexers – a data symphony! 🔄 Follow the Instruction Execution Cycle: Fetch ➡️Decode➡️Execute➡️Store➡️ Update PC. 🕹️ #LearnInPublic
0
0
0
0
40
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
31 Des 2023

#GPUProgramming - Day 01: 🚀 Exploring RISC architecture: Simplified, optimized instructions in one clock cycle. 🔄 Bye, CISC complexity! 🏎️ Registers rule, boosting speed. 🤖💡 Compiler-friendly design, slick pipelining for simultaneous processing! 🕵️‍♂️ #COA #RISC #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 01: 🚀 Exploring RISC architecture: Simplified, optimized instructions in one clock cycle. 🔄 Bye, CISC complexity! 🏎️ Registers rule, boosting speed. 🤖💡 Compiler-friendly design, slick pipelining for simultaneous processing! 🕵️‍♂️ #COA #RISC #LearnInPublic
0
0
0
0
49
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
11 Jan 2024

#GPUProgramming - Day 08: 🚀 Explored #computerarchitecture today! 🖥️ Control Hazards tackle branch prediction, #Pentium FDIV bug a classic example. 💡 Memory #Hierarchy is key—#RAM, #cache levels (L1, L2, L3), and storage devices play crucial roles. 🔄🌐 #Memory #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 08: 🚀 Explored #computerarchitecture today! 🖥️ Control Hazards tackle branch prediction, #Pentium FDIV bug a classic example. 💡 Memory #Hierarchy is key—#RAM, #cache levels (L1, L2, L3), and storage devices play crucial roles. 🔄🌐 #Memory #LearnInPublic
hridoy_bashir's tweet image. #GPUProgramming - Day 08: 🚀 Explored #computerarchitecture today! 🖥️ Control Hazards tackle branch prediction, #Pentium FDIV bug a classic example. 💡 Memory #Hierarchy is key—#RAM, #cache levels (L1, L2, L3), and storage devices play crucial roles. 🔄🌐 #Memory #LearnInPublic
1
0
0
0
111
tatavishnurao's profile picture. 20, AI Engineer(GPU Poor); ai research intern @ startup | Sharing about my learnings, research & real-world insights
Vishnu
@tatavishnurao
9 Nov

Day 4 of #GPUProgramming: >revised about warp behaviour & reduction basics >tried to code warp synchronisation >couldn’t do much because of semester end exams prep >well it is better to do something than nothing so that’s a wrap for today

tatavishnurao's tweet image. Day 4 of #GPUProgramming: >revised about warp behaviour & reduction basics >tried to code warp synchronisation >couldn’t do much because of semester end exams prep >well it is better to do something than nothing so that’s a wrap for today
tatavishnurao's profile picture. 20, AI Engineer(GPU Poor); ai research intern @ startup | Sharing about my learnings, research & real-world insights
Vishnu
@tatavishnurao
8 Nov

Day 3 of #GPUProgramming: >in-depth of what shared memory is capable of >read about techniques by which these concepts optimize their performance >synchronization of threads during matmul >realized it took ~1.5 hours to digest this stuff >tried to code matrix multiplication…

tatavishnurao's tweet image. Day 3 of #GPUProgramming: >in-depth of what shared memory is capable of >read about techniques by which these concepts optimize their performance >synchronization of threads during matmul >realized it took ~1.5 hours to digest this stuff >tried to code matrix multiplication…
1
0
1
0
167
0
0
1
0
345
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
9 Jan 2024

#GPUProgramming - Day 06: 🔍 Diving into computer architecture! 🖥️ Structural hazards arise when hardware resources are in high demand, causing contention among instructions. Data hazards? RAW, WAR, WAW – the battle for data paths and registers! 💡 #COA #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 06: 🔍 Diving into computer architecture! 🖥️ Structural hazards arise when hardware resources are in high demand, causing contention among instructions. Data hazards? RAW, WAR, WAW – the battle for data paths and registers! 💡 #COA #LearnInPublic
0
0
0
0
37
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
4 Jan 2024

#GPUProgramming - Day 04: 🕰️ Dive into processor architectures! 🧠 Single-cycle execution, one clock cycle per instruction, demands a versatile datapath. 🔄 Multi-cycle instructions break it down for a more intricate dance with time. ⏳ #ComputerArchitecture #LearnInPublic 🚀

hridoy_bashir's tweet image. #GPUProgramming - Day 04: 🕰️ Dive into processor architectures! 🧠 Single-cycle execution, one clock cycle per instruction, demands a versatile datapath. 🔄 Multi-cycle instructions break it down for a more intricate dance with time. ⏳ #ComputerArchitecture #LearnInPublic 🚀
hridoy_bashir's tweet image. #GPUProgramming - Day 04: 🕰️ Dive into processor architectures! 🧠 Single-cycle execution, one clock cycle per instruction, demands a versatile datapath. 🔄 Multi-cycle instructions break it down for a more intricate dance with time. ⏳ #ComputerArchitecture #LearnInPublic 🚀
0
0
0
0
42
hridoy_bashir's profile picture. Swanky Patito Feo 🐤 Geek 💻 Quantum Computing Enthusiast 0️⃣ 1️⃣ 🔄 PhysX + CompSci + Math !! (Trinity) ♥️♥️ Physics Grad @SUST CS PostGrad @DU 🇧🇩
Raihanul Bashir Hridoy
 @hridoy_bashir
5 Jan 2024

#GPUProgramming - Day 05: 🚀 Pipelining in computer architecture boosts performance by dividing instruction execution into stages. Techniques like forwarding, branch prediction, and superscalar processors enhance parallelism.💻🌐 #ComputerArchitecture #Pipelining #LearnInPublic

hridoy_bashir's tweet image. #GPUProgramming - Day 05: 🚀 Pipelining in computer architecture boosts performance by dividing instruction execution into stages. Techniques like forwarding, branch prediction, and superscalar processors enhance parallelism.💻🌐 #ComputerArchitecture #Pipelining #LearnInPublic
0
0
0
0
42
Compile_Conquer's profile picture. Building fast & efficient AI systems, from low-level CUDA kernels to distributed training frameworks. AI Systems Engineer | 3rd Year undergraduate
Aman Swar
 @Compile_Conquer
28 Feb

was getting bored ... So I made custom CUDA kernels for vector addition with 6 levels of optimization from naive implementation to shared , tiling till vectorized ops here is the link github.com/AmanSwar/Kerne… #CUDA #GPUProgramming #AI

Compile_Conquer's tweet image. was getting bored ... So I made custom CUDA kernels for vector addition with 6 levels of optimization from naive implementation to shared , tiling till vectorized ops here is the link github.com/AmanSwar/Kerne… #CUDA #GPUProgramming #AI
1
0
1
0
45
Tidak ada hasil untuk "#gpuprogramming"
Tidak ada hasil untuk "#gpuprogramming"
Tidak ada hasil untuk "#gpuprogramming"

Something went wrong.


Something went wrong.


United States Trends