https://hg.paper.us.eu.org/vec/ en-us test/test_arith.h revision history https://hg.paper.us.eu.org/vec/log/31cee67540b5/test/test_arith.h
we also need saturated add sub mul etc]]> Paper <paper@tflc.us> Sat, 09 Aug 2025 15:55:59 -0400 https://hg.paper.us.eu.org/vec/log/7955bed1d169/test/test_arith.h
no x86 intrinsics just yet, but I did add altivec since it's
(arguably) the simplest :)]]> Paper <paper@tflc.us> Wed, 30 Apr 2025 18:36:38 -0400 https://hg.paper.us.eu.org/vec/log/c6e0df09b86f/test/test_arith.h Paper <paper@tflc.us> Mon, 28 Apr 2025 16:31:59 -0400 https://hg.paper.us.eu.org/vec/log/55cadb1fac4b/test/test_arith.h
need to test it with old gcc though. :)]]> Paper <paper@tflc.us> Sun, 27 Apr 2025 02:49:53 -0400 https://hg.paper.us.eu.org/vec/log/4b5a557aa64f/test/test_arith.h
the sample benchmark performs about 3x as well with optimizations
disabled :)]]> Paper <paper@tflc.us> Sat, 26 Apr 2025 01:04:35 -0400 https://hg.paper.us.eu.org/vec/log/677c03c382b8/test/test_arith.h Paper <paper@tflc.us> Fri, 25 Apr 2025 17:40:55 -0400 https://hg.paper.us.eu.org/vec/log/8b5e0974fd41/test/test_arith.h Paper <paper@tflc.us> Fri, 25 Apr 2025 17:40:46 -0400 https://hg.paper.us.eu.org/vec/log/bf6ad516f1e6/test/test_arith.h Paper <paper@tflc.us> Fri, 25 Apr 2025 17:40:33 -0400 https://hg.paper.us.eu.org/vec/log/c6c99ab1088a/test/test_arith.h
agh, this time I added a few more implementations (and generally
made the code just a little faster...)]]> Paper <paper@tflc.us> Thu, 24 Apr 2025 00:54:02 -0400 https://hg.paper.us.eu.org/vec/log/92156fe32755/test/test_arith.h
the signed average function is wrong; it needs to round up the number
when only one of them is odd, but that doesn't necessarily seem to be
true because altivec is weird, and that's what we need to emulate the
quirks for. ugh.

also the altivec backend uses the generic functions instead of fallbacks
because it does indeed use the exact same memory structure as the generic
implementation...]]> Paper <paper@tflc.us> Sun, 24 Nov 2024 11:15:59 +0000 https://hg.paper.us.eu.org/vec/log/e26874655738/test/test_arith.h
I keep finding things that are broken...

The problem NOW was that vec would unintentionally build some
functions with extended instruction sets, which is Bad and would
mean that for all intents and purposes the CPU detection was
completely broken.

Now vec is no longer header only either. Boohoo. However this gives
a lot more flexibility to vec since we no longer want or need to
care about C++ crap.

The NEON and Altivec implementations have not been updated which
means they won't compile hence why they're commented out in the
cmake build file.]]> Paper <paper@tflc.us> Sun, 24 Nov 2024 02:52:40 -0500 https://hg.paper.us.eu.org/vec/log/41dd962abdd1/test/test_arith.h
this is stupid, but whatever]]> Paper <paper@tflc.us> Wed, 20 Nov 2024 12:02:15 -0500 https://hg.paper.us.eu.org/vec/log/e05c257c6a23/test/test_arith.h
ALSO!! now intrinsics are enabled at runtime, depending on what is
detected. altivec *should* still work but I only tested compiling
it.

the major version has been updated to 2.0 for this...]]> Paper <paper@tflc.us> Wed, 20 Nov 2024 04:10:37 -0500 https://hg.paper.us.eu.org/vec/log/53197dbf4e8e/test/test_arith.h Paper <paper@tflc.us> Tue, 19 Nov 2024 15:54:38 -0500 https://hg.paper.us.eu.org/vec/log/d1d5d767004c/test/test_arith.h Paper <paper@tflc.us> Mon, 18 Nov 2024 15:44:09 -0500 https://hg.paper.us.eu.org/vec/log/6ff0b7a44bb6/test/test_arith.h
eventually this could be expanded to add floating point stuff
as well]]> Paper <paper@tflc.us> Mon, 18 Nov 2024 13:52:09 -0500 https://hg.paper.us.eu.org/vec/log/945d410803f8/test/test_arith.h Paper <paper@tflc.us> Wed, 23 Oct 2024 20:07:08 -0400 https://hg.paper.us.eu.org/vec/log/75ab77f874e2/test/test_arith.h Paper <paper@tflc.us> Wed, 23 Oct 2024 10:13:25 -0400 https://hg.paper.us.eu.org/vec/log/3c5545b1568f/test/test_arith.h Paper <paper@tflc.us> Tue, 22 Oct 2024 23:27:15 -0400 https://hg.paper.us.eu.org/vec/log/f12b5dd4e18c/test/test_arith.h Paper <paper@tflc.us> Tue, 22 Oct 2024 22:39:05 -0400