yapanuwan
/
DVR-jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Not trying to use tensor cores for compatibility

This commit is contained in:
ysyapa 2023-03-16 17:58:32 -04:00
parent a082f140c1
commit 4778bd70d6
1 changed files with 1 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
GPU.jl
View File

@ -29,17 +29,8 @@ vectorDims(H::HOperator)::Dims = tuple(fill(H.N, H.d * (H.n - 1))...)
"cuTENSOR contraction and accumulation (C = A * B + C)"
function contract_accumulate!(C::CuTensor, A::CuTensor, B::CuTensor)::CuTensor
# https://docs.nvidia.com/cuda/cutensor/api/cutensor.html#cutensorcontraction
compute_type = if eltype(C) == ComplexF32
CUTENSOR.CUTENSOR_COMPUTE_TF32
elseif eltype(C) == ComplexF64
CUTENSOR.CUTENSOR_COMPUTE_64F
else
eltype(C)
end
CUTENSOR.contraction!(one(eltype(C)), A.data, A.inds, CUTENSOR.CUTENSOR_OP_IDENTITY, B.data, B.inds, CUTENSOR.CUTENSOR_OP_IDENTITY,
one(eltype(C)), C.data, C.inds, CUTENSOR.CUTENSOR_OP_IDENTITY, CUTENSOR.CUTENSOR_OP_IDENTITY,
compute_type=compute_type)
one(eltype(C)), C.data, C.inds, CUTENSOR.CUTENSOR_OP_IDENTITY, CUTENSOR.CUTENSOR_OP_IDENTITY)
return C
end