Latest posts tagged with #MLIR on Bluesky
Just created our first #MLIR plugin for #cleflang and while it's within a narrow focus it has wide implications: MLKit style flat closures that can be lowered to standard LLVM. #fsharp #fstar #ocaml #dotnet github.com/FidelityFram...
My PhD student Gabriel had a busy time at #SC25 and has written up his experiences, especially presenting a couple of papers leveraging #MLIR for #FPGAs. One at the LLVM workshop on a Fortran+OpenMP flow for #Xilinx #FPGAs and another at H2RC workshop on a Fortran intrinsics flow for AI engines
Thanks to Jeremy Kun for his #mlir tutorial! 💙We forked and retooled for WinOS w/his blog as docs in the repo. Will go through and update for 2025 using his tutes as a guide and make adjustments. Plans are for MacOS & Linux with CMake - then Bazel afterward. 🎄#fsharp github.com/speakeztech/...
The #LLVM developer room is back for the 12th consecutive year at #FOSDEM, on January 31st!
We're looking for presentations on all aspects of #LLVM, #MLIR and more.
See CFP for details discourse.llvm.org/t/cfp-fosdem....
Deadline for submissions is November 30th.
I hope to see many of you at FOSDEM!
Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR
#MLIR #OpenCL #Testing #Package
hgpu.org?p=30291
This is one of our "summation" posts unpacking a unique mechanism in the Firefly compiler. With #MLIR supporting delimited continuations and interaction nets (through the DCont and Inet dialects) we're able to contemplate optimal machine code from high level #fsharp. speakez.tech/blog/dcont-i...
«LLVM для AI». Крис Латтнер и язык программирования Mojo Крис Латтнер (Chris Lattner) — создатель CPU-компилятора LLVM и со...
#Крис #Латтнер #GPU-программирование #LLVM #MLIR #Swift #Modular #AI #Mojo #OpenXLA #TritonLang
Origin | Interest | Match
MLIR Compiler Framework Boosts Control‑Flow Performance on CGRAs
An MLIR‑based compilation framework improves control‑flow handling on coarse‑grained reconfigurable arrays, delivering up to 2.1× speedup over prior software techniques. Read more: getnews.me/mlir-compiler-framework-... #mlir #cgra
We are looking for a C++ expert with compiler and MLIR experience to join us in Munich to build the infrastructure that powers AI across Apple's ecosystem.
Let me know if you have questions
Apply: jobs.apple.com/en-us/detail...
#Apple #Compilers #CPlusPlus #MLIR #AI #Munich
🧬 The DNA of #AI needs restructuring. More than a business opportunity, it's engineering necessity and moral imperative. #python #pytorch #MachineLearning #fsharp #dotnet #mlir #llvm #cpp #clang @nextsilicon.com @groq.com @tenstorrent.bsky.social @sambanova.bsky.social
speakez.tech/blog/escapin...
Great fun and a great crowd at @codescarolina.bsky.social
#Java #ruby #dotnet #csharp #fsharp #COBOL #erlang #elm #cpp #mlir #llvm #cpp #clang #rustlang #golang #fstar #ai #machinelearning #verification #fstar #elm #haskell
Doka Studio with MLiR - Mario Marini @ Doka - 30 Aug feat. MLiR, Mario Marini
#SESH #MLiR #MarioMarini
#fsharp #cpp #mlir #llvm #AI #iot #webassembly #systemsprogramming #softwaredevelopment speakez.tech/blog/alloyrx...
💸 #AI acceleration should be a commodity, not a monopoly. 💰Our design for the Fidelity framework uses interaction nets to target GPU & CPU/SIMD via #MLIR. No opaque vendor APIs that sacrifice accuracy, efficiency or safety. Just functional code → silicon. #FSharp #LLVM speakez.tech/blog/speed-a...
Thesis: Using Deep Reinforcement Learning for Automatic Code Optimization in the MLIR Compiler
#Performance #Physics #QCD #MLIR
hgpu.org?p=30054
Heading to the #LLVM / #MLIR Meetup in #Bristol on July 2?
Connect with our Senior Compiler Engineer, Kavan Bickerstaff, & learn more about what we’re building.
👉 flow-computing.com
#Compilers #ParallelComputing #FlowComputing #PPU #CPU #HPC #DeepTech #ParallelProcessing #SoftwareInfrastructure
🧬 Gene samples nearly melted because someone mixed °F and °C. 🫠 With #AI proliferating, every system is now safety-critical. F# units of measure catch these potential errors at compile time with ZERO runtime cost. New #fsharp #mlir #llvm #systemsprogramming #aisafety blog: speakez.ai/blog/danger-...
We're refactoring the Firefly compiler and Alloy library *again*, and so took a sidebar to update one of our blog entries that discuss this interlinked components of the Fidelity framework. #fsharp #systemsprogramming #dotnet #mlir #llvm #clang speakez.ai/blog/buildin...
A major advantage is Mojo's ability to target multiple GPU architectures through MLIR, offering hardware flexibility for developers. #MLIR 5/6
🚀Another entry from our open archive - a novel design to discover, parse and 'tree-shake' F# libraries at source level through #mlir #llvm. It might change how you think about modern #compilers. #fsharp
#functionalprogramming #performance #opensource #dotnet #rust #tech speakez.ai/blog/source-...
