devito

devito copied to clipboard

dsl: Add functionality to intersect SubDimensions

2

Introduce the ability to form a new `SubDimension` as the intersection of multiple` SubDimension`s

EdCaunt

compiler: Add fission-for-pressure subpass

1

So far, this isn't enabled by default. More experimentation required This PR also adds a new compiler flag to GNUCompiler when running on Skylake and later processors. I've tested it...

FabioLuporini

Reproducer: ``` from devito import * u = Function(name="u", grid=Grid((5, 5))) x, y = u.grid.dimensions ox, oy = u.grid.origin # Operator(Eq(u, exp(-(x-2)**2/.5 - (y-2)**2/.5)))() Operator(Eq(u, x+y))() print(u.data._gather(rank=0)) ```

FabioLuporini

We currently have a fairly ad-hic handling of multiple "grids" (Subdiomains, Grid, ...) in the operator argument processing A proper Discretization hierarchy needs to be implemented so we can easily...

mloubout

In some case the pickling leads to miss-reconstruction of `-1` with differences like ``` - loat px = -floor((-o_x + src_coords[p_src][0])/h_x) + (-o_x + src_coords[p_src][0])/h_x; + loat px = (-1)*floor((-o_x...

mloubout

misc: Add Omnitrace and Omniperf to Dockerfile.amd

13

FabioLuporini

Slicing `Data` returns incorrect results following a `transpose()`

1

As described in the title. MFE below. Consider the following numpy array operation: ``` import numpy as np a = np.zeros((4, 6)) b = a.T[::2, ::2] ``` We then have...

rhodrin

cannot increase dimensionality of MPI-distributed Data

2

I try to apply FWI for marmousi 2D model and run it using MPI. This is the setting of my acquisition geometry ```python nshots = 60 nreceivers = 80 fwi_iterations...

bening-gawitsa

Error with pyrevolve - ImportError: /lib64/libm.so.6: version `GLIBC_2.29' not found

1

Hi, I'm getting the following error when I try to import modules from Devito: ``` Python 3.10.6 (main, Oct 24 2022, 16:07:47) [GCC 11.2.0] on linux Type "help", "copyright", "credits"...

fabiomacelloni

compiler: Unified Memory Allocator

9

Hello everyone, We of SENAI CIMATEC are working in a Unified Memory Allocator to Devito trough CuPy library. The first results using this new allocator have impressive results when using...

guaacoelho