unknown
c1ccc32408
deprecated MASK_XOR (old, broken, meant only to avoid multiplying)
2015-01-27 21:26:42 -05:00
unknown
95cf462dfb
force dummy buffer allocations for LWC2, native SWC2 wraparound
2015-01-21 15:10:18 -05:00
unknown
a4a7f4bd8e
forgot to modernize a few types
2015-01-18 16:39:59 -05:00
unknown
c42ac84651
Correct VCH sign flag comparison on -32768.
2015-01-18 12:56:16 -05:00
unknown
74b3ee72ce
Force two-dimensional merging in VCL.
2015-01-17 22:29:44 -05:00
unknown
9c49dc4fff
abolish SSSE3 configurator for byte-wise shuffling
2014-12-13 16:34:48 -05:00
unknown
699896f677
install new pointer types to distinguish mem. reference from decl.'s
2014-12-08 23:47:50 -05:00
unknown
ac4fb238da
temporarily supporting the SSSE3 superset for early experiments
2014-11-16 15:46:54 -05:00
unknown
bfd74741f9
force vectorization of unsigned multiply, overflow and VMADL clamp
2014-10-28 20:50:10 -04:00
unknown
55ad9ad9d8
optimized VMADN with static overflow, carry and multiply-add
2014-10-28 15:35:05 -04:00
unknown
6d17d19dc6
correspond VMUDM intrinsics to multiply-accumulate variation
2014-10-26 23:58:18 -04:00
unknown
5cce9f457e
new algorithm for mixed signed * unsigned factorization
2014-10-23 16:45:01 -04:00
unknown
ef09b4eb5d
redesign VMUDN with carry and overflow/underflow SSE logic
2014-10-22 22:45:34 -04:00
unknown
f810a85e31
refer unsigned overflow to `negative' mask
2014-10-21 19:58:10 -04:00
unknown
c7a468e3d7
corresponding optimizations to VMUDL (same multiply, diff. clamp)
2014-10-21 00:05:26 -04:00
unknown
9dbdcc490c
restyled some optimization and fix 48-bit MADD sign-extension
2014-10-20 22:25:01 -04:00
unknown
b832e39a92
merged bi-arch VMULF template into optimized SIMD mulf
2014-10-20 00:57:40 -04:00
unknown
d768f51077
more direct multiply-add high operation without bi-arch template
2014-10-18 22:27:08 -04:00
unknown
79c5aa0cf4
removed bi-arch template for VMUDH
2014-10-17 22:43:43 -04:00
unknown
291e7fb10b
remove bi-arch template for VMUDL as mudl was greatly simplified in SSE
2014-10-17 19:02:02 -04:00
unknown
9490ea8e20
fix annoying "unused local variable" warnings ifndef ARCH_MIN_SSE2
2014-10-17 02:24:03 -04:00
unknown
2e1e9edf75
cut SHUFFLE_VECTOR to only 2 arguments with pre-loaded VT
2014-10-17 02:23:08 -04:00
unknown
f05e2d603e
globalize the shuffle macro for a future shot at SMC in su.c
2014-10-17 00:50:30 -04:00
unknown
158a4d0b60
pass only 2 XMM operands, w/ no return slot ifndef ARCH_MIN_SSE2
2014-10-16 00:43:37 -04:00
unknown
fd765856fc
regulate (temporarily?) that $vd begins as a zero'd vector
2014-10-15 00:55:40 -04:00
unknown
c550a19a8a
fail paste kthxbai
2014-10-14 23:05:24 -04:00
unknown
e8e87ce602
some new flexible intrinsic macros for vector operations
2014-10-14 17:59:00 -04:00
unknown
9bfe2c20c3
new SSE2 shuffling template for later staticization
2014-10-14 14:21:54 -04:00
unknown
91ba902637
removed extra load/store from old scalar SHUFFLE_VECTOR template
2014-10-14 04:53:49 -04:00
unknown
7d80d7d115
fix macro re-definition warning in GCC (already in my_types.h)
2014-10-10 01:38:41 -04:00
unknown
f1481dd39b
restructured modular layout of the source, dropped some optional features
2014-10-09 16:45:55 -04:00
unknown
d5692be247
dissolved VU arguments into higher-level SIMD vector call stacks
2014-10-07 00:33:15 -04:00
unknown
d24da458c6
clip test optimizations, fixes Wrestlemania 2000 clamped -(-32768)
2014-09-24 15:30:32 -04:00
unknown
a68b3251ed
Harvest Moon 64 regression from 2013/9/11--broken zero-upper wrapping
2014-08-14 14:22:33 -04:00
unknown
d1f7688deb
force copy alignment better to low GCC 4.8.1 compiler intelligence
2014-08-13 08:03:38 -04:00
unknown
3c9c183b47
if vector_copy() on shuffled vector, force ST alignment for compiler
2014-08-13 07:12:19 -04:00
unknown
93a6648926
more MSVC compliance (lack of implicit type conversion, force alignment)
2014-08-13 07:07:42 -04:00
unknown
1125d4a9d6
some MSVC compliance changes, force literal immediate syntax
2014-08-13 07:00:49 -04:00
unknown
861b636ced
forgot to update the modification date
2014-08-13 00:08:15 -04:00
unknown
9d760917a1
Merge branch 'master' of https://github.com/cxd4/rsp
2014-08-12 22:21:58 -04:00
unknown
5cae28f628
Quake64 fix, delay shared register file writeback until after set NOTEQUAL
2014-08-12 22:19:44 -04:00
Sven Eckelmann
4392ebde42
Add an explicit public domain dedication statement
...
The process of dedicating a piece of work under the public domain is not the
same under different legal systems. It is possible that different rights are
given away depending on the origin. Sometimes even the dedication of the work
under public domain is not possible at all. CC0 tries to provide an explicit
way to waive all rights to still provide a secure way for other parties to use
this work [1] and provides a fallback when parts of the license may be judged
invalid under any jurisdiction.
[1] http://creativecommons.org/about/cc0
2013-12-17 13:36:56 +01:00
Sven Eckelmann
05696fde5a
Replace long with (u)int32_t for systems with sizeof(long) > 4
...
This only affects long's which are used on an 64-bit system. The zilmar spec
with its DWORD is not touched because on 32 bit it is always 32 bit for common
systems. On Win64 systems it is also 32 bit because Microsoft adopted LLP64.
All other systems seem to use LP64 (IL32LP64), ILP64 or SILP64.
ILP64 and SILP64 would also need to have shorts and int (when the code expects
32 bit) to be changed to (u)int*_t counterparts. This is not done in here.
2013-12-12 12:53:27 +01:00
Sven Eckelmann
0faed67a64
Fix vector divides on systems with sizeof(long) > 4
...
The wrong div operations result in wrong transformations in many roms.
This regression was introduced in 87210c71a5
2013-12-12 00:34:19 +01:00
unknown
92469fafc1
fetched wrong file for debugging VCE, fix signed acc logs
2013-12-04 19:05:39 -05:00
unknown
fdc611e6d4
staticized CPU loop PC updates to iterate within J/B
2013-12-04 18:16:28 -05:00
unknown
ec693a456d
decided to implement the VRSQ op, with a warning
2013-12-01 20:38:23 -05:00
unknown
87210c71a5
cleanups and rewrites to the vector divide class
2013-11-26 19:15:19 -05:00
unknown
0b8b2ad900
restored old (surprisingly faster) small VU operand allocation
2013-11-26 13:22:37 -05:00
unknown
8607b1625d
fixed jittery 3-D textures bug in World Driver Championship
2013-11-25 18:18:00 -05:00
