[OpenJDK Rasterizer] AWT & gcc 4.8 optimization options

[Sergey Bylokhov]

On 09/12/15 09:07, Laurent Bourgès wrote:
> Hi Sergey,
>
> Do you have made some progress ?
>
> If you modify the Maskfill C code, could you explain me how it works as
> I would like implementing in the future the correct gamma correction in
> this software loop ?

 From the current source code point of view it is not an easy task to 
understand how it works. The easiest way to study it is to compile the 
jdk using this option in AWT2dLibraries.gmk

--- a/make/lib/Awt2dLibraries.gmk Tue Dec 08 19:50:14 2015 +0300
+++ b/make/lib/Awt2dLibraries.gmk Wed Dec 09 17:10:55 2015 +0300
@@ -242,7 +242,7 @@
EXCLUDES := $(LIBAWT_EXCLUDES), \
EXCLUDE_FILES := $(LIBAWT_EXFILES), \
OPTIMIZATION := LOW, \
- CFLAGS := $(CFLAGS_JDKLIB) $(LIBAWT_CFLAGS), \
+ CFLAGS := -save-temps $(CFLAGS_JDKLIB) $(LIBAWT_CFLAGS), \
DISABLED_WARNINGS_gcc := sign-compare unused-result maybe-uninitialized \
format-nonliteral parentheses, \
DISABLED_WARNINGS_clang := logical-op-parentheses extern-initializer, \

This will save result of preprocessor. Also it will save an assembler 
code which can be useful to investigate how the compiler optimize the 
code, especially in case of vectorization.

When you take a look to the code after preprocessor you will be able to 
understand the DSL which is used in the AlphaMacros.h for the 
"DEFINE_ALPHA_MASKBLIT"


There are a bunch of files in the 
java.desktop/share/native/libawt/java2d/loops/. Some of them have the 
general code like LoopMacros.h, AlphaMacros.h, others have 
implementation for a some specific types.


For example take a look to the IntRgb.c
It have 2 parts:
- The array IntRgbPrimitives, which contain the list of supported 
operations(it will register the functions which should be called in 
MaskBlit.c for some particular types). For example it contains 
REGISTER_ALPHA_MASKBLIT from/to a different types.
- Definitions of the functions like DEFINE_SRCOVER_MASKBLIT(IntArgb, 
IntRgb, 4ByteArgb); This macros provide a function which will support 
the maskblit IntArgb->IntRgb;

So to understand how it work you need to trace these calls:
- MaskBlit.java -> MaskBlit(.....)
- MaskBlit.c -> *pPrim->funcs.maskblit
- The function which is generated from the DEFINE_SRCOVER_MASKBLIT for a 
particular type.

Note that if for some reason we have no specific implementation of 
DEFINE_SRCOVER_MASKBLIT will meant that General MaskBlit from the 
MaskBlit.java will be used and it is quite slow.

I am on the road of investigation...


>
> Could you help me on this task
>
> Cheers,
> Laurent
>
> Le 27 nov. 2015 12:07, "Sergey Bylokhov" <Sergey.Bylokhov at oracle.com
> <mailto:Sergey.Bylokhov at oracle.com>> a écrit :
>  >
>  > Right now I am trying to investigate where the code is affected by
> these options, and also I am trying to investigate possibility of code
> improvement.
>  >
>  >
>  > On 27.11.15 13:28, Laurent Bourgès wrote:
>  >>
>  >> Hi,
>  >>
>  >> Just a reminder on this compiler issue.
>  >>
>  >> I tested today the impact of the proposed patch changing compiler
>  >> options for AWT on my machine (i7 gcc 4.8.4):
>  >>
>  >> Without patch (clean build - client libs):
>  >> EllipseTests-fill-true.ser                       1    25    445.220
>  >> 445.336    445.196    0.127    444.944    445.543    25
>  >>
>  >> With patch:
>  >> EllipseTests-fill-true.ser                       1    26    402.889
>  >> 403.861    403.134    0.446    402.603    404.294    26
>  >>
>  >> The impact is very important on this test (large mask fills) ~ 10%
>  >>
>  >> Sergey, could you check on gcc 4.9.2 ?
>  >>
>  >>   Laurent
>  >>
>  >> 2015-10-21 21:04 GMT+02:00 Sergey Bylokhov
> <Sergey.Bylokhov at oracle.com <mailto:Sergey.Bylokhov at oracle.com>
>  >> <mailto:Sergey.Bylokhov at oracle.com
> <mailto:Sergey.Bylokhov at oracle.com>>>:
>  >>
>  >>
>  >>     The bug was filed:
>  >> https://bugs.openjdk.java.net/browse/JDK-8140266
>  >>
>  >>     I will try a few steps before push the current solution:
>  >>     - change the code, so this option will not be necessary.
>  >>     - check other compilers, it seems gcc 4.9.2 will be default for
> jdk9.
>  >>
>  >
>  >
>  > --
>  > Best regards, Sergey.
>


-- 
Best regards, Sergey.