Still needs to point (fullpath) to the microkernel.

We're getting somewhere.

Missed a typo in the ops table.

Only works for scratch_seq right now.

Refactor the tilings to become generic to N dimensions, and interfacing
with the newly added layouts.

The main idea for this version of tilings is to provide an index into a
partitioning of a source layout into sub-layouts of smaller sizes.

[feature] add padded layouts

See merge request !80

Merge of padded layouts implementation from @videau, which provides a
way to extend a layout in any dimension by using a neutral element.

[feature] extend dma to support custom operators

See merge request !79

Some operators will need an extra argument (like transforms).

Change the DMA generic API to allow for a custom function pointer to
perform a specific request. Requires us to change a bit the underlying
management structures.

[feature] add area options on mmap

See merge request !78

## Change area mmap interface to include implementation specific options.

### Summary of changes in mmap interface
Previous mmap interface was:
```
int aml_area_mmap(struct aml_area *area, void*ptr, size_t size);
```
First, in this interface, the purpose of ptr is fuzzy as it is implementation specific and neither
the user nor aml generic interface knows what to do with it in a generic way.
Second, this interface does not allow for extensive options. In particular, linux mmap allow
multiple arguments that cannot be elegantly passed with this interface.
Instead we aml_mmap replace with this new interface:
```
int aml_area_mmap(struct aml_area *area, size_t size, struct aml_area_options *options);
```
Where the last field clearly state it is used for options and can always be NULL so that it can explicitly be used without knowledge of options implementation.

Area cuda

See merge request !76

New area allow to allocate data on cuda devices.
Allocation optionally include the ability to map
host memory on device memory. See cuda area
documentation.

Includes libtool helper to link cuda device object files
with the remaining of the library.

An additional error code has been added to aml errors for handling busy cuda devices
Also, all CI stages as been set not to run on branches name starting with wip.

Remove dma va args

Closes #49

See merge request !77

Now that only one type of request is allowed (layouts), remove va_args
for the DMA API, making it significantly cleaner.

Fix #49.

Remove support for direct pointers in a DMA request, with the goal to
remove va_args in the entire DMA API soon. As scratchs still work with
pointers, also modify scratchs to convert tiles in layouts.

This reverts commit 04315e6e.

Not needed since vector doesn't contain the actual inner type.

Improve speed and exhaustiveness of the unit tests.

See merge request !74

Various fixes related to dma API, missing validation on arguments,
pthread management and so on.

Unit tests were missing a few corner cases on dense_create. In
particular, there was a bug in the handling of the NULL pitch.

The bitmap tests were slowing down the entire pipeline, while at the
same time missing important checks on the inputs. This version is a bit
more exhaustive, while also speeding up the test by only checking the
corner-cases (first bits, last bits, partial ranges, overlapping
ranges).

Fix vector resize issue on async requests

Closes #48

See merge request !75

Since vector resize can cause pointers into the vector to become
invalid, this patch introduces a level of indirection for DMAs and
Scratchs, using uuid on the user-side of a request to index into the
request vector.

We need the vector type used for all our "command queues" to be able to
maintain pointers to the inner data structure across reallocs of the
vector itself. The resulting change just uses independent callocs for
each pointer to a data element.

[refactor] redesign DMAs to support layouts

Closes #46

See merge request !73

Refactor the DMA API to work on layouts internally. The resulting code
ends up simpler for most cases, as long as we add a generic copy
function.

One things missing:
- a good API to expose the collection of copy functions we have.

One question not solved:
- should the DMA ask for a copy function on each operation ?

Add inner-malloc utils

Closes #45

See merge request !69