vchuravy/GPUifyLoops.jl issues and pull requests

#108 - Install TagBot as a GitHub Action

Pull Request - State: closed - Opened by JuliaTagBot over 4 years ago

#107 - add experimental print functionality

Pull Request - State: open - Opened by vchuravy over 4 years ago

#106 - Slower than CUDA kernels

Issue - State: open - Opened by simonbyrne over 4 years ago

#105 - Fix CI Issues

Pull Request - State: closed - Opened by lcw over 4 years ago - 10 comments

#104 - Overdub print/println

Issue - State: open - Opened by charleskawczynski over 4 years ago - 5 comments

#103 - CPU exceptions/assertions?

Issue - State: open - Opened by simonbyrne over 4 years ago

#102 - Add read only load function

Pull Request - State: closed - Opened by lcw over 4 years ago - 7 comments

#101 - contextualize docs don't much signature

Issue - State: open - Opened by simonbyrne almost 5 years ago

#100 - Use occupancy API to suggest launch configuration

Issue - State: open - Opened by maleadt almost 5 years ago

#99 - Laplacian stencil example

Pull Request - State: open - Opened by ali-ramadhan almost 5 years ago - 2 comments
Labels: DO NOT MERGE

#98 - Broken test now passes

Pull Request - State: open - Opened by miguelraz almost 5 years ago - 4 comments

#97 - Add signature function

Pull Request - State: closed - Opened by lcw almost 5 years ago

#96 - Force specialization of contexualize on length of vararg

Pull Request - State: closed - Opened by vchuravy about 5 years ago

#95 - Using Cthulhu with GPUifyLoops on the GPU

Issue - State: closed - Opened by mwarusz about 5 years ago - 1 comment

#94 - Method definition overwritten warning

Issue - State: open - Opened by simonbyrne about 5 years ago - 1 comment
Labels: upstream

#93 - fixes from hackathon

Pull Request - State: open - Opened by simonbyrne about 5 years ago - 10 comments

#92 - CPU thread support?

Issue - State: open - Opened by simonbyrne about 5 years ago - 4 comments

#91 - Allow users to disable fp contract optimizations ?

Issue - State: open - Opened by mwarusz about 5 years ago - 1 comment

#90 - Support dynamic launch configuration

Pull Request - State: closed - Opened by ali-ramadhan over 5 years ago - 1 comment

#89 - don't overdub simple functions

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#88 - correctly call pure function with varargs

Pull Request - State: closed - Opened by vchuravy over 5 years ago

#87 - GPUifyLoops boundschecking on SubArray

Issue - State: open - Opened by ChrisRackauckas over 5 years ago

#86 - Change `Device` to `Backend` or something similar ?

Issue - State: open - Opened by mwarusz over 5 years ago

#85 - Stencil abstraction does not work on GPU

Issue - State: open - Opened by ali-ramadhan over 5 years ago

#84 - fix inferrability of cpu shmem arrays

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 4 comments

#83 - `@shmem` with integer results in `Any`

Issue - State: closed - Opened by jkozdon over 5 years ago - 2 comments

#82 - Return of ODESolution type fails

Issue - State: open - Opened by ChrisRackauckas over 5 years ago - 2 comments

#81 - Stencil abstraction

Pull Request - State: open - Opened by vchuravy over 5 years ago - 6 comments
Labels: needs tests, needs docs

#80 - recursion limitation in axes

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#79 - setindex! to an MArray with non-literals fails

Issue - State: closed - Opened by ChrisRackauckas over 5 years ago - 1 comment

#78 - Returning something else makes it go boom!

Issue - State: closed - Opened by ChrisRackauckas over 5 years ago - 1 comment

#77 - Possible fabs float range issue?

Issue - State: open - Opened by ChrisRackauckas over 5 years ago - 2 comments

#76 - Fix typo in README

Pull Request - State: closed - Opened by DilumAluthge over 5 years ago

#75 - fixup! guard against undefined variables

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#74 - guard against undefined variables

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#73 - Inlining Failure?

Issue - State: closed - Opened by ChrisRackauckas over 5 years ago - 8 comments

#72 - don't overdub pure functions

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#71 - avoid wrapping kernel in closure

Pull Request - State: closed - Opened by vchuravy over 5 years ago

#70 - don't overdub IntrinsicFunctions

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#69 - name kernels

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#68 - use the fallback on the GPU

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 3 comments

#67 - Support for ranges

Issue - State: closed - Opened by ChrisRackauckas over 5 years ago - 3 comments

#66 - v0.2.4 broke things but not sure what

Issue - State: closed - Opened by ali-ramadhan over 5 years ago - 4 comments

#65 - Add `device` convenience function

Pull Request - State: closed - Opened by mwarusz over 5 years ago - 7 comments

#64 - [WIP] Add support for ROCm

Pull Request - State: open - Opened by jpsamaroo over 5 years ago - 3 comments

#63 - Better handling of pure functions, also overdub CPU functions

Pull Request - State: open - Opened by vchuravy over 5 years ago - 5 comments

#62 - Better error experience

Issue - State: open - Opened by vchuravy over 5 years ago - 4 comments

#61 - Fixing scratch when there are no GPU dims

Pull Request - State: closed - Opened by jkozdon over 5 years ago - 6 comments

#60 - Cassetteify pow

Pull Request - State: closed - Opened by jkozdon over 5 years ago - 2 comments

#59 - GPUifty CuArray of Static Arrays

Issue - State: open - Opened by ChrisRackauckas over 5 years ago - 1 comment

#58 - Fix multid indexing for MArrays in CUDA

Pull Request - State: closed - Opened by jkozdon over 5 years ago - 16 comments

#57 - update tests to be more resilent to failure

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#56 - make sure that MArray are noted as Local AS

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 5 comments

#55 - use contract for fadd, fmul, fsub

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#54 - Launching a CUDA kernel with an OffsetArray{CuArray} does not work.

Issue - State: closed - Opened by ali-ramadhan over 5 years ago - 4 comments

#53 - add reflection function to overdub list, due to at_pure constraints

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#52 - Out of bounds addressing with StaticArrays

Issue - State: closed - Opened by lcw over 5 years ago - 3 comments

#51 - Register v0.2.2

Issue - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#50 - Remove CUDAnative in global scope dependency

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#49 - disable 265 fix if not requested during precompile time

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 3 comments

#48 - don't force inline everything

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 7 comments
Labels: DO NOT MERGE

#47 - honour noinline

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 3 comments

#46 - Compile-time regression

Issue - State: closed - Opened by ali-ramadhan over 5 years ago - 31 comments

#45 - Add basic kernel for timing @launch

Pull Request - State: closed - Opened by lcw over 5 years ago

#44 - Remove CUDAnative in global scope dependency

Pull Request - State: closed - Opened by lcw over 5 years ago - 3 comments

#43 - Remove CUDAnative in global scope dependency

Pull Request - State: closed - Opened by lcw over 5 years ago

#42 - try to create better alignment information for the GPU

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#41 - Fix deprecations

Pull Request - State: closed - Opened by femtocleaner[bot] over 5 years ago - 1 comment

#40 - Allow @shmem without @cuStaticSharedMem defined

Pull Request - State: closed - Opened by lcw over 5 years ago - 3 comments

#39 - warn on to low Julia version

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#38 - Dispatch to device index function

Issue - State: open - Opened by vchuravy over 5 years ago - 2 comments
Labels: enhancement, help wanted

#37 - wrap pesudo calls into do_not_verify

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 3 comments

#36 - use 1 self argument and nargs to place self-call

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 3 comments

#35 - simplify self reference

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#34 - Update README to reflect current state of the code

Pull Request - State: closed - Opened by lcw over 5 years ago - 1 comment

#33 - update invariant correctly

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 4 comments

#32 - Add `prefetch` test

Pull Request - State: closed - Opened by YingboMa over 5 years ago - 1 comment

#31 - loop unroll expects MDNodes

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#30 - do redefinition test outside testset

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#29 - add loopinfo and unroll macro

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment

#28 - Contextualize example doesn't seem to work

Issue - State: closed - Opened by charleskawczynski over 5 years ago - 5 comments

#27 - Fuse multiply-add

Issue - State: open - Opened by vchuravy over 5 years ago - 2 comments
Labels: enhancement, help wanted, performance

#26 - Efficiently zero-out scratch/shmem

Issue - State: open - Opened by vchuravy over 5 years ago
Labels: enhancement, help wanted, performance

#25 - Fix typo in docs

Pull Request - State: closed - Opened by lcw over 5 years ago

#24 - switch from Val{:CPU} to proper types

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 8 comments

#23 - Remove Requires from test target

Pull Request - State: closed - Opened by lcw over 5 years ago

#22 - Requesting an example program

Issue - State: closed - Opened by willow-ahrens over 5 years ago - 2 comments

#21 - Abstract host interface

Issue - State: open - Opened by lcw over 5 years ago - 2 comments
Labels: enhancement, help wanted

#20 - add launch function

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 23 comments

#19 - make CI beautiful

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 5 comments

#18 - Example showing 3D stencil calculations with a divergence

Pull Request - State: open - Opened by ali-ramadhan over 5 years ago - 2 comments

#17 - Error tagging new release

Issue - State: closed - Opened by attobot over 5 years ago

#16 - start writing some docs

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 2 comments

#15 - LocalMemory macro

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 1 comment
Labels: help wanted, needs tests, needs docs

#13 - Example showing 3D stencil calculations.

Pull Request - State: closed - Opened by ali-ramadhan over 5 years ago - 7 comments

#12 - Best way to GPUify nested loops over multi-dimensional arrays?

Issue - State: closed - Opened by ali-ramadhan over 5 years ago - 3 comments

#11 - `@scratch` bug

Issue - State: closed - Opened by lcw over 5 years ago - 1 comment

#5 - add prefetch

Pull Request - State: open - Opened by vchuravy over 5 years ago - 12 comments

#4 - Add cassette based contextualize

Pull Request - State: closed - Opened by vchuravy over 5 years ago - 28 comments
Labels: needs tests, needs docs

#3 - Fix host hack for when CUDA not present

Issue - State: closed - Opened by jkozdon over 5 years ago - 2 comments
Labels: help wanted

GitHub / vchuravy/GPUifyLoops.jl issues and pull requests