taco

taco copied to clipboard

How to generate cuda kernel with python bindings?

3

I would like to use pytaco to generate cuda kernels, but cannot find relevant information in this [doc](http://tensor-compiler.org/docs/), so I was wondering if pytaco can generate cuda kernels, if yes,...

gxiaotian

Graceful handling of under-sized sparse tensor shapes

1

Taco dies with a fatal exception if input shapes don't line up perfectly. But I don't think this is always an error. If I add two matrices together, it works...

Infinoid

I created two classes: LowererImplC and LowererImplCUDA. They implement lowerForall, lowerWhere and helper functions called by them separately for CPU code and CUDA code. This is the starting point of...

zhang677

Remove bound as a relation node in the provenance graph. Instead, tag the indexVar with information about the bound.

manya-bansal

Compilation error for MTTKRP with dense matrices and DCSR output

1

On the master branch (as well as the web interface), for the MTTKRP example, the following data formats lead to compilation error: ``` A: DCSR B:CSF D:Dense Array C:Dense Array...

amirsh

Compilation error for TTM with CSF,CSC as input formats and CSF output

4

On the master branch (as well as the web interface), for the TTM example, the mentioned data formats lead to the following compilation error: ``` /var/folders/43/fyr6y1h116q7yw4m8vczbq440000gq/T/taco_tmp_8eTr18/wz1tmu3amdu1.c:195:11: error: use of undeclared...

amirsh

qcd.mul1 fails on Apple M1

2

I installed Taco on Apple M1 Max using: ``` mkdir build cd build cmake -DCMAKE_BUILD_TYPE=Release -DPYTHON=ON .. ``` And tested using `ctest`. All tests pass, except: ```console $ ctest -R...

certik

Uncaught exception when fusing sparse dimensions

4

Got an uncheck exception when fusing sparse dimensions. Does fuse only work for dense dimensions? ``` remywang@m16 build % ./bin/taco "q = r(i,j) * s(i,j)" -f=r:ss -s="fuse(i,j,f)" libc++abi: terminating with...

remysucre

Serialization Support

2

Hi! Are there any plans to add serialization support TACO tensors? We're interested in using TACO's einsum as a kernel for distributed sparse tensor operations using [Ray](https://github.com/ray-project/ray/). For this to...

elibol

Is DIA or ELL currently supported ? can you provide an example?

4

Hi, I am trying to generate code for Spmv kernel when the matrix is in DIA or ELL formats. I wonder if the current version support DIA or ELL formats...

boyrealmadred