Re: 2016Q1: std.blas

2016-03-28 Thread 9il via Digitalmars-d-announce
On Thursday, 24 March 2016 at 10:52:39 UTC, Nordlöw wrote: On Thursday, 24 March 2016 at 09:30:04 UTC, 9il wrote: I will post Level 1 to Mir during this week. Great! http://forum.dlang.org/thread/xnqazcivzbwlpmbym...@forum.dlang.org Only summation for now :-/ --Ilya

Re: 2016Q1: std.blas

2016-03-24 Thread Nordlöw via Digitalmars-d-announce
On Thursday, 24 March 2016 at 09:30:04 UTC, 9il wrote: I will post Level 1 to Mir during this week. Great!

Re: 2016Q1: std.blas

2016-03-24 Thread 9il via Digitalmars-d-announce
On Thursday, 24 March 2016 at 08:20:30 UTC, Nordlöw wrote: On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: I will write GEMM and GEMV families of BLAS for Phobos. Is there a repo where I can track progress? I will post Level 1 to Mir during this week.

Re: 2016Q1: std.blas

2016-03-24 Thread Nordlöw via Digitalmars-d-announce
On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: I will write GEMM and GEMV families of BLAS for Phobos. Is there a repo where I can track progress?

Re: 2016Q1: std.blas

2016-03-24 Thread Nordlöw via Digitalmars-d-announce
On Saturday, 26 December 2015 at 20:51:06 UTC, Ilya Yaroshenko wrote: Related questions about LDC http://forum.dlang.org/thread/lcrquwrehuezpxxvq...@forum.dlang.org Sounds amazing. I can't wait either ;) Thanks in advance. I have some minimum square data fitting algorithms I would like to po

Re: 2016Q1: std.blas

2016-03-23 Thread paper rewriter via Digitalmars-d-announce
Whatever your reason may be for wanting to rewrite your paper it can still be a difficult task.To improve the language and structure of the original. Also, To target a different audience with your writing.

Re: 2016Q1: std.blas

2015-12-30 Thread jmh530 via Digitalmars-d-announce
On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: Hi, I will write GEMM and GEMV families of BLAS for Phobos. Cool.

Re: 2016Q1: std.blas

2015-12-27 Thread Andrei Alexandrescu via Digitalmars-d-announce
On 12/27/15 12:23 AM, Basile B. wrote: On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: - allocators support. GEMM requires small internal allocations. - @nogc nothrow pure template functions (depends on allocator) Do you mean using std.experimental.allocators and someth

Re: 2016Q1: std.blas

2015-12-27 Thread Ilya Yaroshenko via Digitalmars-d-announce
On Sunday, 27 December 2015 at 10:28:53 UTC, Russel Winder wrote: On Sat, 2015-12-26 at 19:57 +, Ilya Yaroshenko via Digitalmars-d- announce wrote: Hi, I will write GEMM and GEMV families of BLAS for Phobos. Goals:   - code without assembler   - code based on SIMD instructions   - DMD/LDC/

Re: 2016Q1: std.blas

2015-12-27 Thread Russel Winder via Digitalmars-d-announce
On Sat, 2015-12-26 at 19:57 +, Ilya Yaroshenko via Digitalmars-d- announce wrote: > Hi, > > I will write GEMM and GEMV families of BLAS for Phobos. > > Goals: >   - code without assembler >   - code based on SIMD instructions >   - DMD/LDC/GDC support >   - kernel based architecture like Open

Re: 2016Q1: std.blas

2015-12-26 Thread Ilya Yaroshenko via Digitalmars-d-announce
On Sunday, 27 December 2015 at 05:43:47 UTC, Charles McAnany wrote: On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: Hi, I will write GEMM and GEMV families of BLAS for Phobos. [...] References: [1] Anatomy of High-Performance Matrix Multiplication: http://www.cs.utexa

Re: 2016Q1: std.blas

2015-12-26 Thread Ilya Yaroshenko via Digitalmars-d-announce
On Sunday, 27 December 2015 at 05:23:27 UTC, Basile B. wrote: On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: - allocators support. GEMM requires small internal allocations. - @nogc nothrow pure template functions (depends on allocator) Do you mean using std.experiment

Re: 2016Q1: std.blas

2015-12-26 Thread Charles McAnany via Digitalmars-d-announce
On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: Hi, I will write GEMM and GEMV families of BLAS for Phobos. Goals: - code without assembler - code based on SIMD instructions - DMD/LDC/GDC support - kernel based architecture like OpenBLAS - 85-100% FLOPS comparing with

Re: 2016Q1: std.blas

2015-12-26 Thread Basile B. via Digitalmars-d-announce
On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: - allocators support. GEMM requires small internal allocations. - @nogc nothrow pure template functions (depends on allocator) Do you mean using std.experimental.allocators and something like (IAllocator alloc) as template

Re: 2016Q1: std.blas

2015-12-26 Thread Andrei Amatuni via Digitalmars-d-announce
On Saturday, 26 December 2015 at 19:57:19 UTC, Ilya Yaroshenko wrote: Hi, I will write GEMM and GEMV families of BLAS for Phobos. [...] Just want to thank you in advance. Can't wait!

Re: 2016Q1: std.blas

2015-12-26 Thread Ilya Yaroshenko via Digitalmars-d-announce
Related questions about LDC http://forum.dlang.org/thread/lcrquwrehuezpxxvq...@forum.dlang.org

2016Q1: std.blas

2015-12-26 Thread Ilya Yaroshenko via Digitalmars-d-announce
Hi, I will write GEMM and GEMV families of BLAS for Phobos. Goals: - code without assembler - code based on SIMD instructions - DMD/LDC/GDC support - kernel based architecture like OpenBLAS - 85-100% FLOPS comparing with OpenBLAS (100%) - tiny generic code comparing with OpenBLAS - abilit