Skip to content

CUDA: Fallback to UnsafeAtomics - #56

Open
vchuravy wants to merge 4 commits into
vc/cuda_atomicswapfrom
vc/cuda_unsafe
Open

CUDA: Fallback to UnsafeAtomics#56
vchuravy wants to merge 4 commits into
vc/cuda_atomicswapfrom
vc/cuda_unsafe

Conversation

@vchuravy

@vchuravy vchuravy commented May 13, 2025

Copy link
Copy Markdown
Member

No description provided.

@vchuravy

vchuravy commented May 13, 2025 •
edited
Loading

Copy link
Copy Markdown
Member Author

This of course does not work:

using Atomix
using UnsafeAtomics

using CUDA

function kernel(a, b)
    x = UnsafeAtomics.load(pointer(a, 1))
    UnsafeAtomics.store!(pointer(b, 1), x)
    return nothing
end


b = CUDA.zeros(Int, 1)
a = CUDA.ones(Int, 1)

@cuda kernel(a, b)

Yields

ERROR: LLVM error: Cannot select: 0x1e7845f0: ch = AtomicStore<(store seq_cst (s64) into %ir.4, addrspace 1)> 0x1e784580:1, 0x1e783a90, 0x1e784580, /home/vchuravy/.julia/packages/LLVM/xTJfF/src/interop/base.jl:39 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/ext/UnsafeAtomicsLLVM/atomics.jl:178 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/ext/UnsafeAtomicsLLVM/atomics.jl:131 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/ext/UnsafeAtomicsLLVM/internal.jl:16 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/src/core.jl:8 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/src/core.jl:2 @[ /home/vchuravy/niklas.jl:8 ] ] ] ] ] ]
  0x1e783a90: i64,ch = load<(dereferenceable invariant load (s64) from `i64 addrspace(101)* null`, addrspace 101)> 0x1da29370, TargetExternalSymbol:i64'_Z6kernel13CuDeviceArrayI5Int64Li1ELi1EES1__param_2', undef:i64
    0x1e783f60: i64 = TargetExternalSymbol'_Z6kernel13CuDeviceArrayI5Int64Li1ELi1EES1__param_2'
    0x1e783780: i64 = undef
  0x1e784580: i64,ch = AtomicLoad<(load seq_cst (s64) from %ir.2, addrspace 1)> 0x1da29370, 0x1e783a20, /home/vchuravy/.julia/packages/LLVM/xTJfF/src/interop/base.jl:39 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/ext/UnsafeAtomicsLLVM/atomics.jl:94 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/ext/UnsafeAtomicsLLVM/atomics.jl:94 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/ext/UnsafeAtomicsLLVM/internal.jl:12 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/src/core.jl:7 @[ /home/vchuravy/.julia/packages/UnsafeAtomics/vpyYB/src/core.jl:1 @[ /home/vchuravy/niklas.jl:7 ] ] ] ] ] ]
    0x1e783a20: i64,ch = load<(dereferenceable invariant load (s64) from `i64 addrspace(101)* null`, addrspace 101)> 0x1da29370, TargetExternalSymbol:i64'_Z6kernel13CuDeviceArrayI5Int64Li1ELi1EES1__param_1', undef:i64
      0x1e783860: i64 = TargetExternalSymbol'_Z6kernel13CuDeviceArrayI5Int64Li1ELi1EES1__param_1'
      0x1e783780: i64 = undef
In function: _Z6kernel13CuDeviceArrayI5Int64Li1ELi1EES1_

So seq_cst is not supported...

function kernel(a, b)
    x = UnsafeAtomics.load(pointer(a, 1), UnsafeAtomics.monotonic)
    UnsafeAtomics.store!(pointer(b, 1), x, UnsafeAtomics.monotonic)
    return nothing
end

b = CUDA.zeros(Int, 1)
a = CUDA.ones(Int, 1)

@cuda kernel(a, b)

Does work

@maleadt

maleadt commented May 13, 2025

Copy link
Copy Markdown
Member

PTX does not support atom.seq_cst. Instead, cmpxchg seq_cst is emulated as "fence.sc; atom.cas"
https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#parallel-synchronization-and-communication-instructions-atom

@vchuravy

vchuravy commented May 13, 2025

Copy link
Copy Markdown
Member Author

Yeah, the whole order business is a mess.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@vchuravy @maleadt