CUDA v5.4.2

Diff since v5.4.1

Merged pull requests:

• Fix and test the legacy memory pool. (#2402) (@maleadt)

CUDA v5.4.1

Diff since v5.4.0

Merged pull requests:

• Fixup Enzyme: Mark CuArray as noalias (#2401) (@wsmoses)

CUDA v5.4.0

Diff since v5.3.5

Merged pull requests:

• Support CUDA 12.5 (#2392) (@maleadt)
• Mark cuarray as noalias (#2395) (@wsmoses)
• Update Julia wrappers for CUDA v12.5 (#2396) (@amontoison)
• Enable correct pool access for cublasXt. (#2398) (@maleadt)
• More fine-grained CUPTI version checks. (#2399) (@maleadt)

Closed issues:

• CUTENSOR breaks after device_reset! (#2319)
• cuBLASXt's xt_gemm! incompatible with stream-ordered allocated memory (#2320)
• Add helper function to recompile CUDA stack (#2364)

CUDA v5.3.5

Diff since v5.3.4

Merged pull requests:

• Avoid constructing MulAddMuls on Julia v1.12+ (#2277) (@dkarrasch)
• CompatHelper: bump compat for LLVM to 7, (keep existing compat) (#2365) (@github-actions[bot])
• Enzyme: allocation functions (#2386) (@wsmoses)
• Tweaks to prevent context construction on some operations (#2387) (@maleadt)
• Fixes for Julia 1.12 / LLVM 17 (#2390) (@maleadt)
• CUBLAS: Make sure CUBLASLt wrappers use the correct library. (#2391) (@maleadt)
• Backport: Enzyme allocation fns (#2393) (@wsmoses)

Closed issues:

• Indexing a view uses scalar indexing (#1472)
• EnzymeCore is an unconditional dependency. (#2380)
• cuBLASLt wrappers ccall into cuBLAS (#2388)
• generic_trimatmul! error (#2389)

CUDA v5.3.4

Diff since v5.3.3

Merged pull requests:

• Add Enzyme Forward mode custom rule (#1869) (@wsmoses)
• Handle cache improvements (#2352) (@maleadt)
• Fix cuTensorNet compat (#2354) (@maleadt)
• Optimize array allocation. (#2355) (@maleadt)
• Change type restrictions in cuTENSOR operations (#2356) (@lkdvos)
• Bump julia-actions/setup-julia from 1 to 2 (#2357) (@dependabot[bot])
• Suggest use of 32 bit types over 64 instead of just Float32 over Float64 [skip ci] (#2358) (@Zentrik)
• Make generic_trimatmul more specific (#2359) (@tgymnich)
• Return the currect memory type when wrapping system memory. (#2363) (@maleadt)
• Mark cublas version/handle as non-differentiable (#2368) (@wsmoses)
• Enzyme: Forward mode sync (#2369) (@wsmoses)
• Enzyme: support fill (#2371) (@wsmoses)
• unsafe_wrap: unconditionally use the memory type provided by the user. (#2372) (@maleadt)
• Remove external_gvars. (#2373) (@maleadt)
• Tegra support with artifacts (#2374) (@maleadt)
• Backport Enzyme extension (#2375) (@wsmoses)
• Add note about --check-bounds=yes (#2378) (@Zinoex)
• Test Enzyme in a separate CI job. (#2379) (@maleadt)
• Fix tests for Tegra. (#2381) (@maleadt)
• Update Project.toml [remove EnzymeCore unconditional dep] (#2382) (@wsmoses)

Closed issues:

• Native Softmax (#175)
• CUSOLVER: support eigendecomposition (#173)
• backslash with gpu matrices crashes julia (#161)
• at-benchmark captures GPU arrays (#156)
• Support kernels returning Union{} (#62)
• mul! falls back to generic implementation (#148)
• \ on qr factorization objects gives a method error (#138)
• Compiler failure if dependent module only contains a japi1 function (#49)
• copy!(dst, src) and copyto!(dst, src) are significantly slower and allocate more memory than copyto!(dest, do, src, so[, N]) (#126)
• Calling Flux.gpu on a view dumps core (#125)
• Creating CuArray{Tracker.TrackedReal{Float64},1} a few times causes segfaults (#121)
• Guard against exceeding maximum kernel parameter size (#32)
• Detect common API misuse in error handlers (#31)
• rand and friends default to Float64 (#108)
• \ does not work for least squares (#104)
• ERROR_ILLEGAL_ADDRESS when broadcasting modular arithmetic (#94)
• CuIterator assumes batches to consist of multiple arrays (#86)
• Algebra with UniformScaling Uses Generic Fallback Scalar Indexing (#85)
• Document (un)supported language features for kernel programming (#13)
• Missing dispatch for indexing of reshaped arrays (#556)
• Track array ownership to avoid illegal memory accesses (#763)
• NVPTX i128 support broken on LLVM 11 / Julia 1.6 (#793)
• Support for sm_80 cp.async: asynchronous on-device copies (#850)
• Profiling Julia with Nsight Systems on Windows results in blank window (#862)
• sort! and partialsort! are considerably slower than CPU versions (#937)
• mul! does not dispatch on Adjoint (#1363)
• Cross-device copy of wrapped arrays fails (#1377)
• Memory allocation becomes very slow when reserved bytes is large (#1540)
• Cannot reclaim GPU Memory; CUDA.reclaim() (#1562)
• Add eigen for general purpose computation of eigenvectors/eigenvalues (#1572)
• device_reset! does not seem to work anymore (#1579)
• device-side rand() are not random between successive kernel launches (#1633)
• Add EnzymeRules support for CUDA.jl (for forward mode here) (#1811)
• cusparseSetStream_v2 not defined (#1820)
• Feature request: Integrating the latest CUDA library "cuLitho" into CUDA.jl (#1821)
• KernelAbstractions.jl-related issues (#1838)
• lock failing in multithreaded plan_fft() (#1921)
• CUSolver finalizer tries to take ReentrantLock (#1923)
• Testsuite could be more careful about parallel testing (#2192)
• Opportunistic GC collection (#2303)
• Unable to use local CUDA runtime toolkit (#2367)
• Enzyme prevents testing on 1.11 (#2376)

CUDA v5.3.3

Diff since v5.3.2

Merged pull requests:

• Rework context handling (#2346) (@maleadt)
• fix kernel launch logic (#2353) (@xaellison)

Closed issues:

• Excessive allocations when running on multiple threads (#1429)
• Fix and test multigpu support (#2218)
• Bitonic sort exceeds launch resources (#2331)

CUDA v5.3.2

Diff since v5.3.1

Merged pull requests:

• Add EnzymeCore extension for parent_job (#2281) (@vchuravy)
• Consider running GC when allocating and synchronizing (#2304) (@maleadt)
• Refactor memory wrappers (#2335) (@maleadt)
• Auto-detect external profilers. (#2339) (@maleadt)
• Fix performance of indexing unified memory. (#2340) (@maleadt)
• Improve exception output (#2342) (@maleadt)
• Test multigpu on CI (#2348) (@maleadt)
• cuQuantum 24.3: Bump cuTensorNet. (#2350) (@maleadt)
• cuQuantum 24.3: Bump cuStateVec. (#2351) (@maleadt)

Closed issues:

• CuArrays don't seem to display correctly in VS code (#875)
• Task scheduling can result in delays when synchronizing (#1525)
• Docs: add example on task-based parallelism with explicit synchronization (#1566)
• Exception output from many threads is not helpful (#1780)
• Autodetect external profiler (#2176)
• LazyInitialized is not GC-safe (#2216)
• Track CuArray stream usage (#2236)
• Improve cross-device usage (#2323)
• CUBLASLt wrapper for cublasLtMatmulDescSetAttribute can have device buffers as input (#2337)
• Improve error message when assigning real valued arrray with complex numbers (#2341)
• @device_code_sass broken (#2343)
• Readme says Cuda 11 is supported but also the last version to support it is v4.4 (#2345)
• @gcsafe_ccall breaks inlining of ccall wrappers (#2347)

CUDA v5.3.1

Diff since v5.3.0

Merged pull requests:

• [CUSOLVER] Fix the dispatch for syevd! and heevd! (#2309) (@amontoison)
• Regenerate headers (#2324) (@maleadt)
• Add some installation tips to docs/README.md (#2326) (@jlchan)
• fix broadcast defaulting to Mem.Unified() (#2327) (@vpuri3)
• Diagnose kernel limits on launch failure. (#2329) (@maleadt)
• Work around a CUPTI bug in CUDA 12.4 Update 1. (#2330) (@maleadt)

Closed issues:

• Missing CUBLASLt wrappers (#2322)
• error when switching device (#2323)
• v5.3.0: regression in Zygote performance (#2333)

CUDA v5.3.0

Diff since v5.2.0

Merged pull requests:

• CuSparseArrayCSR (fixed cat ambiguitites from #1944) (#2244) (@nikopj)
• Slightly rework error handling (#2245) (@maleadt)
• cuTENSOR improvements (#2246) (@maleadt)
• Make @device_code_sass work with non-Julia kernels. (#2247) (@maleadt)
• Improve Tegra detection. (#2251) (@maleadt)
• Added few SparseArrays functions (#2254) (@albertomercurio)
• Reduce locking in the handle cache (#2256) (@maleadt)
• Mark all CUDA ccalls as GC safe (#2262) (@vchuravy)
• cuTENSOR: Fix reference to undefined variable (#2263) (@lkdvos)
• cuTENSOR: refactor obtaining compute_type as part of plan (#2264) (@lkdvos)
• Re-generate headers. (#2265) (@maleadt)
• Update to CUDNN 9. (#2267) (@maleadt)
• [CUBLAS] Use the ILP64 API with CUDA 12 (#2270) (@amontoison)
• CompatHelper: bump compat for GPUCompiler to 0.26, (keep existing compat) (#2271) (@github-actions[bot])
• Minor improvements to nonblocking synchronization. (#2272) (@maleadt)
• Add extension package for StaticArrays (#2273) (@trahflow)
• Fix cuTensor, cuTensorNet and cuStateVec when using local Toolkit (#2274) (@bjoe2k4)
• Cached workspace prototype for custatevec (#2279) (@kshyatt)
• Update the Julia wrappers for v12.4 (#2282) (@amontoison)
• Add support for CUDA 12.4. (#2286) (@maleadt)
• Test suite changes (#2288) (@maleadt)
• Fix mixed-buffer/mixed-shape broadcasts. (#2290) (@maleadt)
• Towards supporting Julia 1.11 (#2291) (@maleadt)
• Fix typo in performance tips (#2294) (@Zentrik)
• Make it possible to customize the CuIterator adaptor. (#2297) (@maleadt)
• Set default buffer size in CUSPARSE mm! functions (#2298) (@lpawela)
• Avoid OOMs during OOM handling. (#2299) (@maleadt)
• [CUSOLVER] Add tests for geqrf, orgqr and ormqr (#2300) (@amontoison)
• [CUSOLVER] Interface larft! (#2301) (@amontoison)
• Fix RNG determinism when using wrapped arrays. (#2307) (@maleadt)
• sortperm with dims (#2308) (@xaellison)
• [CUBLAS] Interface gemm_grouped_batched (#2310) (@amontoison)
• [CUSPARSE] Add a method convert for the type cusparseSpSMUpdate_t (#2311) (@amontoison)
• Avoid capturing AbstractArrays in BoundsError (#2314) (@lcw)
• Clarify debug level hint. (#2316) (@maleadt)

Closed issues:

• Failed to compile PTX code when using NSight on Win11 (#1601)
• sortperm fails with dims keyword (#2061)
• NVTX-related segfault on Windows under compute-sanitizer (#2204)
• Inverse Complex-to-Real FFT allocates GPU memory (#2249)
• cuDNN not available for your platform (#2252)
• Cannot reset CuArray to zero (#2257)
• Cannot take gradient of sort on 2D CuArray (#2259)
• Multi-threaded code hanging forever with Julia 1.10 (#2261)
• CUBLAS: nrm2 support for StridedCuArray with length requiring Int64 (#2268)
• Adjoint not supported on Diagonal arrays (#2275)
• Regression in broadcast: getting Array (Julia 1.10) instead of CuArray (Julia 1.9) (#2276)
• Release v5.3? (#2283)
• Wrap CUDSS? (#2287)
• Bug concerning broadcast between device array and unified array (#2289)
• StackOverflowError trying to throw OutOfGPUMemoryError, subsequent errors (#2292)
• BUG: sortperm! seems to perform much slower than it should (#2293)
• Multiplying CuSparseMatrixCSC by CuMatrix results in Out of GPU memory (#2296)
• BFloat16 support broken on Julia 1.11 (#2306)
• does not emit line info for debbuging/profiling (#2312)
• Kernel using StaticArray compiles in julia v1.9.4 but not in v1.10.2 (#2313)
• Using copyto! with SharedArray trigger scalar indexing disallowed error (#2317)

CUDA v4.4.2

Diff since v4.4.1

Merged pull requests:

• Added support for more transform directions (#1903) (@RainerHeintzmann)
• CuSparseArrayCSR (N dim array) with batched matmatmul (bmm) (#1944) (@nikopj)
• Add some performance tips to the documentation (#1999) (@Zentrik)
• Re-introduce the 'blocking' kwargs to at-sync. (#2060) (@maleadt)
• Adapt to GPUCompiler#master. (#2062) (@maleadt)
• Batched SVD added (gesvdjBatched and gesvdaStridedBatched) (#2063) (@nikopj)
• Use released GPUCompiler. (#2064) (@maleadt)
• Fixes for Windows. (#2065) (@maleadt)
• Switch to GPUArrays buffer management. (#2068) (@maleadt)
• Update CUDA 12 to Update 2. (#2071) (@maleadt)
• [CUSOLVER] Add generic routines (#2074) (@amontoison)
• Update manifest (#2076) (@github-actions[bot])
• Test improvements (#2079) (@maleadt)
• Rework and extend the cooperative groups API. (#2081) (@maleadt)
• Update manifest (#2082) (@github-actions[bot])
• [CUSOLVER] Add a method for geqrf! (#2085) (@amontoison)
• Fix some typos in perfomance tips (#2086) (@Zentrik)
• Improve PTX ISA selection (#2088) (@maleadt)
• Update manifest (#2090) (@github-actions[bot])
• support ChainRulesCore inplaceability (#2091) (@piever)
• Add a method inv(CuMatrix) (#2095) (@amontoison)
• Add mul!(A, B, C) where B or C is a diagonal matrix (#2096) (@amontoison)
• Add CUDA_Runtime_Discovery dependency to sublibraries. (#2097) (@maleadt)
• Handle and test zero-size inputs to RNGs. (#2098) (@maleadt)
• Add a with_workspaces function (#2099) (@amontoison)
• [CUSOLVER] Add a method for getrf! (#2100) (@amontoison)
• [CUSOLVER] Fix a typo with jobu / jobvt in gesvd (#2101) (@amontoison)
• Call exit when handling exceptions. (#2103) (@maleadt)
• Bump packages. (#2104) (@maleadt)
• Bump actions/checkout from 3 to 4 (#2106) (@dependabot[bot])
• Update manifest (#2107) (@github-actions[bot])
• Make Ref mutable on the GPU. (#2109) (@maleadt)
• CompatHelper: bump compat for CEnum to 0.5, (keep existing compat) (#2110) (@github-actions[bot])
• Small profiler improvements (#2113) (@maleadt)
• Update manifest (#2114) (@github-actions[bot])
• [CUSPARSE] Wrap new functions added with CUDA 12.2 (#2116) (@amontoison)
• [CUSOLVER] Add new methods for \ and inv (#2117) (@amontoison)
• Fix incorrect timing results for CUDA.@Elapsed (#2118) (@thomasfaingnaert)
• [CUSOLVER] Interface sparse Cholesky and QR factorizations (#2121) (@amontoison)
• Update manifest (#2123) (@github-actions[bot])
• Profiler: Show used local memory. (#2124) (@maleadt)
• Support for CUDA 12.3 (#2125) (@maleadt)
• [CUSOLVER] Add Add Xsyevdx! and Xgesvdr! (#2127) (@amontoison)
• [CUSOLVER] Add Xgesvdp (#2128) (@amontoison)
• Profiler: don't crop when rendering to a file. (#2131) (@maleadt)
• Regenerate headers for CUDA 12.3. (#2132) (@maleadt)
• [CUSPARSE] Fix a bug with triangular solves (#2134) (@amontoison)
• CompatHelper: add new compat entry for Statistics at version 1, (keep existing compat) (#2135) (@github-actions[bot])
• CompatHelper: add new compat entry for LazyArtifacts at version 1, (keep existing compat) (#2136) (@github-actions[bot])
• Profiler: Parse and visualize NVTX marker data. (#2137) (@maleadt)
• Better support for unified and host memory (#2138) (@maleadt)
• Profiler: Improve compatibility with Pluto.jl and friends. (#2139) (@maleadt)
• Avoid allocations during derived array construction. (#2142) (@maleadt)
• More performance tweaks for memory copying (#2143) (@maleadt)
• Don't use libdevice's fmin/fmax. (#2144) (@maleadt)
• Update documentation (#2146) (@maleadt)
• Fixes for sm_61 (#2151) (@maleadt)
• Update sparse factorizations (#2152) (@amontoison)
• Don't call into LLVM's fmin/fmax on <sm_80. (#2154) (@maleadt)
• Only prefect unified memory if concurrent access is possible. (#2155) (@maleadt)
• Support wrapping an Array with a CuArray without HMM. (#2156) (@maleadt)
• Sanitizer improvements. (#2157) (@maleadt)
• [CUSPARSE] Update the wrapper of cusparseSpSV_updateMatrix (#2159) (@amontoison)
• Profiler improvements: (textual) time distribution, at-bprofile. (#2162) (@maleadt)
• [CUSPARSE] Update the interface for triangular solves (#2164) (@amontoison)
• [CUSPARSE] Remove code related to old CUDA toolkits (#2165) (@amontoison)
• Detect compute-exclusive mode and adjust testing. (#2166) (@maleadt)
• expand docs on launch parameters (#2167) (@simonbyrne)
• Make CUDA.set_runtime_version force the default behavior. (#2169) (@maleadt)
• kernel docs: fix formatting, clean up awkward sentence (#2172) (@simonbyrne)
• [CUSOLVER] Don't reuse the sparse handles (#2173) (@amontoison)
• Added kronecker product support for dense matrices (#2177) (@albertomercurio)
• Update to CUTENSOR 2.0 (#2178) (@maleadt)
• Fix typos and simplify wording in performance tips docs (#2179) (@Zentrik)
• provide more information on kernel compilation error (#2180) (@simonbyrne)
• [CUSPARSE] Test CUSPARSE_SPMV_COO_ALG2 (#2182) (@amontoison)
• [CUSPARSE] Use cusparseSpMM_preprocess (#2183) (@amontoison)
• [CUSPARSE] Use cusparseSDDMM_preprocess (#2184) (@amontoison)
• Add the structures ILU0Info() and IC0Info() for the preconditioners (#2187) (@amontoison)
• [CUSOLVER] Add a structure CuSolverParameters fro the generic API (#2188) (@amontoison)
• Support more kwarg syntax with kernel launches (#2189) (@maleadt)
• Fix typo in docs/src/development/troubleshooting.md (#2193) (@jcsahnwaldt)
• NVML: Add support for clock queries. (#2194) (@maleadt)
• Fix Random.jl seeding for 1.11 (#2199) (@IanButterworth)
• Improvements to context handling (#2200) (@maleadt)
• Add a concurrent kwarg to profiling macros. (#2201) (@maleadt)
• Rework unique context management. (#2202) (@maleadt)
• Preserve the buffer type when broadcasting. (#2203) (@maleadt)
• Fixes for Windows (#2206) (@maleadt)
• Bump Aqua. (#2207) (@maleadt)
• Updates for new CUQUANTUM (#2210) (@kshyatt)
• CUSPARSE: Eagerly combine duplicate element on construction. (#2213) (@maleadt)
• CompatHelper: bump compat for BFloat16s to 0.5, (keep existing compat) (#2214) (@github-actions[bot])
• Bump the CUDA Runtime for CUDA 12.3.2. (#2217) (@maleadt)
• Default to testing with only a single device. (#2221) (@maleadt)
• Backports for v5.1 (#2224) (@maleadt)
• Take care not to spawn tasks during precompilation. (#2226) (@maleadt)
• cuTensor fixes (#2228) (@maleadt)
• Bump versions. (#2229) (@maleadt)
• Add a note about threaded for-blocks. (#2232) (@kshyatt)
• cuTENSOR plan handling changes. (#2234) (@maleadt)
• Fix dynamic dispatch issues (#2235) (@MilesCranmer)
• CUPTI: Add high-level wrappers for the callback API. (#2239) (@maleadt)
• Fixes for nightly (#2240) (@maleadt)
• CUBLAS: Support more strided inputs (#2242) (@maleadt)
• CuSparseArrayCSR (fixed cat ambiguitites from #1944) (#2244) (@nikopj)
• Slightly rework error handling (#2245) (@maleadt)
• cuTENSOR improvements (#2246) (@maleadt)
• Make @device_code_sass work with non-Julia kernels. (#2247) (@maleadt)
• Improve Tegra detection. (#2251) (@maleadt)
• Added few SparseArrays functions (#2254) (@albertomercurio)
• Reduce locking in the handle cache (#2256) (@maleadt)
• Mark all CUDA ccalls as GC safe (#2262) (@vchuravy)
• cuTENSOR: Fix reference to undefined variable (#2263) (@lkdvos)
• cuTENSOR: refactor obtaining compute_type as part of plan (#2264) (@lkdvos)
• Re-generate headers. (#2265) (@maleadt)
• Update to CUDNN 9. (#2267) (@maleadt)
• [CUBLAS] Use the ILP64 API with CUDA 12 (#2270) (@amontoison)
• CompatHelper: bump compat for GPUCompiler to 0.26, (keep existing compat) (#2271) (@github-actions[bot])
• Minor improvements to nonblocking synchronization. (#2272) (@maleadt)
• Add extension package for StaticArrays (#2273) (@trahflow)
• Fix cuTensor, cuTensorNet and cuStateVec when using local Toolkit (#2274) (@bjoe2k4)
• Cached workspace prototype for custatevec (#2279) (@kshyatt)
• Update the Julia wrappers for v12.4 (#2282) (@amontoison)
• Add support for CUDA 12.4. (#2286) (@maleadt)
• Test suite changes (#2288) (@maleadt)
• Fix mixed-buffer/mixed-shape broadcasts. (#2290) (@maleadt)
• Fix typo in performance tips (#2294) (@Zentrik)
• Make it possible to customize the CuIterator adaptor. (#2297) (@maleadt)
• Set default buffer size in CUSPARSE mm! functions (#2298) (@lpawela)
• Avoid OOMs during OOM handling. (#2299) (@maleadt)
• [CUSOLVER] Add tests for geqrf, orgqr and ormqr (#2300) (@amontoison)
• [CUSOLVER] Interface larft! (#2301) (@amontoison)
• Fix RNG determinism when using wrapped arrays. (#2307) (@maleadt)
• [CUBLAS] Interface gemm_grouped_batched (#2310) (@amontoison)
• [CUSPARSE] Add a method convert for the type cusparseSpSMUpdate_t (#2311) (@amontoison)

Closed issues:

• Element-wise conversion to Duals (#127)
• IDEA: CuHostArray (#28)
• Make Ref pass by-reference (#267)
• Failed to compile PTX code when using NSight on Win11 (#1601)
• view(data, idx) boundschecking is disproportionately expensive (#1678)
• [CUSOLVER] Add a with_workspaces function to allocate two buffers (Device / Host) (#1767)
• Trouble using nsight systems for profiling CUDA in Julia (#1779)
• dlopen("libcudart") results in duplicate libraries (#1814)
• Support for JLD2 (#1833)
• Windows Defender mis-labels artifacts as threat (#1836)
• Support Cholesky factorization of CuSparseMatrixCSR (#1855)
• Runtime not re-selected after driver upgrade (#1877)
• Failure to initialize with CUDA_VISIBLE_DEVICES='' (#1945)
• Cannot precompile GPU code with PrecompileTools (#2006)
• Evaluating sparse matrices in the REPL has a huge memory footprint (#2016)
• CUDA_SDK_jll: cuda.h in different locations depending on the platform (#2066)
• StaticArrays.SHermitianCompact not working in kernels in Julia 1.10.0-beta2 (#2069)
• Support for LinearAlgebra.pinv (#2070)
• PTX ISA 8.1 support (#2080)
• Segmentation fault when importing CUDA (#2083)
• "No system CUDA driver found" on NixOS (#2089)
• CUDA.rand(Int64, m, n) can not be used when m or n is zero (#2093)
• Miss...