Commit Graph

22 Commits

Author SHA1 Message Date
Pierre Bourdon
3570c7f03a Reformat all the things. Have fun with merge conflicts. 2016-06-24 10:43:46 +02:00
Tillmann Karras
de3c01dc2a x64FPURoundMode: fix comments 2015-06-23 02:17:36 +02:00
Tillmann Karras
cefcb0ace9 Update license headers to GPLv2+ 2015-05-25 13:22:31 +02:00
Lioncash
e57201eb71 x64FPURoundMode: Make a look-up table static
Since it's only a look-up table, this doesn't need to be recreated every time the function is called.
2015-03-19 09:07:36 -04:00
Tillmann Karras
f298f00e1b Clean up the intrinsics #ifdef mess 2015-02-24 01:02:36 +01:00
Rohit Nirmal
fbc64984ca Include CommonTypes.h instead of Common.h. 2014-09-08 15:39:58 -04:00
Ryan Houdek
0c24e1dcf2 Remove the rest of x86_32 support from Common. 2014-08-03 13:49:46 -05:00
magumagu
d905cbfd5d Don't set DAZ on x86 in non-IEEE mode.
I have no idea why we were using it in the first place; it doesn't match
the behavior of PPC NI flag.
2014-06-15 03:51:51 -07:00
Shawn Hoffman
700c135386 Revert "x64FPURoundMode: always set x87 precision"
This reverts commit 9de77b7c23.
Setting x87 precision control is only supported on x86 platforms (not ARM or x64).
2014-05-10 20:21:07 -07:00
Tillmann Karras
9de77b7c23 x64FPURoundMode: always set x87 precision
Set the x87 precision, even on x64. Since we are using x87 instructions
in the JIT now, we can't guarantee that x87 precision will never
influence Dolphin on x64.
2014-05-01 01:10:00 +02:00
Tillmann Karras
ed762a3eda x64FPURoundMode: use fesetround() instead of asm 2014-05-01 01:09:55 +02:00
Tillmann Karras
d05e205a24 FPURoundMode: revert use of enums in bit-fields
The workaround of using fixed underlying types produces lots of warnings
in GCC because now the bit-fields are too small for the value range used
for conversion semantics.
2014-03-09 15:24:35 +01:00
Ryan Houdek
4f02132f93 Make our architecture defines less stupid.
Our defines were never clear between what meant 64bit or x86_64
This makes a clear cut between bitness and architecture.
This commit also has the side effect of bringing up aarch64 compiling support.
2014-03-04 09:36:59 -06:00
Tillmann Karras
315a8ba1c0 Various changes suggested by cppcheck
- remove unused variables
- reduce the scope where it makes sense
- correct limits (did you know that strcat()'s last parameter does not
  include the \0 that is always added?)
- set some free()'d pointers to NULL
2014-02-28 12:43:20 +01:00
Tillmann Karras
1a428de189 x64FPURoundMode: move things around a bit 2014-02-28 12:28:21 +01:00
Pierre Bourdon
311caef094 Merge pull request #25 from Tilka/ppc_fp
Fix non-IEEE mode
2014-02-23 04:15:37 +01:00
Pierre Bourdon
83b7bb64aa Make Common/ mostly IWYU clean (and fix errors in rest of the project detected by this change). 2014-02-22 23:37:29 +01:00
Lioncash
2afe215271 Convert all includes to relative paths. 2014-02-18 02:19:10 -05:00
Tillmann Karras
1f34ed2c25 Re-enable non-IEEE mode support 2014-02-12 23:12:16 +01:00
Tillmann Karras
db196d8c5b Jit64[IL]: fix float conversions
Floating-point is complicated...

Some background: Denormals are floats that are too close to zero to be
stored in a normalized way (their exponent would need more bits). Since
they are stored unnormalized, they are hard to work with, even in
hardware.  That's why both PowerPC and SSE can be configured to operate
in faster but non-standard-conpliant modes in which these numbers are
simply rounded ('flushed') to zero.

Internally, we do the same as the PowerPC CPU and store all floats in
double format. This means that for loading and storing singles we need a
conversion. The PowerPC CPU does this in hardware. We previously did
this using CVTSS2SD/CVTSD2SS. Unfortunately, these instructions are
considered arithmetic and therefore flush denormals to zero if non-IEEE
mode is active. This normally wouldn't be a problem since the next
arithmetic floating-point instruction would do the same anyway but as it
turns out some games actually use floating-point instructions for
copying arbitrary data.

My idea for fixing this problem was to use x87 instructions since the
x87 FPU never supported flush-to-zero and thus doesn't mangle denormals.
However, there is one more problem to deal with: SNaNs are automatically
converted to QNaNs (by setting the most-significant bit of the
fraction). I opted to fix this by manually resetting the QNaN bit of all
values with all-1s exponent.
2014-02-12 23:12:15 +01:00
Tillmann Karras
21b0252e27 Jit64: disable non-IEEE mode emulation
I give up. Merging the ppc_fp branch has caused issues in numerous games
and I can't find the bug. I'm leaving this merged to enable easy
recompilation for people who would like to play games that benefit from
non-IEEE mode emulation (e.g. Starfox Assault).
2014-01-19 09:36:08 +01:00
Jasper St. Pierre
34692ab826 Remove unnecessary Src/ folders 2013-12-31 14:03:19 -05:00