HN user

compilercreator

149 karma
Posts15
Comments33
View on HN
Modern GPU 13 years ago

Is it CUDA only or can we submit code written in OpenCL, DirectCompute or C++ AMP etc?

The ways of Wayland 13 years ago

Don't disagree with you overall, but I do have one nitpicl. There is nothing proprietary about the Boost license. Boost license is quite similar to MIT license.

About the N9, there is almost no relationship between Meego+Maemo hybrid on N9 and Tizen, except for use of the Linux kernel, despite some claims otherwise. APIs and most of the libraries appear to be very different. For example, Qt was the primary native API the N9 but is not supported in the official SDK for Tizen. Tizen is instead supporting Bada's native APIs.

Further, the critically acclaimed UI on the N9 was a proprietary solution developed by Nokia and Tizen has a different user interface.

Octave for Android 13 years ago

Which BLAS though? The reference BLAS implementation? That will have terrible performance. Would be interested to see if something better like ATLAS or OpenBLAS can be compiled for it. Recent versions of ATLAS do work on ARM Linux, so wondering if those can be easily ported to Android.

Qt Quick has many advantages over traditional Qt widgets:

1. It provides a simple JSON-like declarative syntax for defining UI layouts, and is quite easy to write new layouts for different use cases (desktop, tablet, netbook etc)

2. Very easy to do animations

3. Qt Quick is fully OpenGL accelerated in Qt 5 and beyond. While this KDE release is not using Qt 5, it provides a good transition path for the future.

Hi. Author here. Your name is quite famous in the GPGPU community, and it is great to hear that you now work on RSC. My experience does not compare to yours and I do hope my post is seen in a positive light. Would love to discuss the issues in depth sometime.

Anyway if you were to ignore everything in the post except one item, that would be to please fix gather/scatter in RSC. A parallel computing API without proper gather/scatter is simply not very useful, irrespective of whether it is on desktop or mobile.

I will keep following RSC and look forward to the developments you are hinting at.

Building Firefox OS 13 years ago

Blackberry 10 Cascades is also based on QML syntax, though they implemented their own rendering engine instead of the QML implementation in Qt4.

Well it is about to be available in about 2 months. From Intel: "The Intel Xeon Phi coprocessor 5110P is shipping today with general availability on Jan. 28 with recommended customer price of $2,649."

I disagree about KDE4 not being customizable. While the earlier iterations of KDE4 (such as 4.1) were lacking in options, newer iterations like KDE 4.8/4.9 are really customizable. See also Linus Torvalds' recent post where he also praises the configurability of KDE4, saying that it may even be too configurable.

Prepare to be surprised. The die size estimate for the Epiphany IV is 10mm-sq according to Adapteva. It is more appropriate to compare it to embedded GPUs than desktop GPUs in die size, power and performance.

For example, one particular embedded 40nm GPU design that I know about can deliver about 25 GFlops or so in the same die area.

I have backed this project. This is an interesting startup, with some good solid technology behind it. They have managed to design and tape out a chip with just a 2m dollar budget so far. The main draw of their architecture is not its peak, but rather its efficiency, both in terms of perf/watt and perf/die area. You can look at their manuals on the site.

Hoping their funding drive succeeds. I am liking the fact that ISA is being fully documented and we will have a fully open-source toolchain to work with the system.

(Disclaimer: Not associated with Adapteva in any way).