CPU与GPU比赛。 [英] The CPU vs the GPU contest.
问题描述
你好,
在本次比赛中,CPU将面向GPU。
哪个处理器能够更快地执行代码/概念? br />
// cpu / serial概念代码是:
var
mTable:整数数组的数组;
mRowCount:整数;
mColumnCount:整数;
程序AllocateTable;
begin
mRowCount:= 8000;
mColumnCount:= 9000;
SetLength(mTable,mRowCount,mColumnCount);
end;
程序WorkToDo;
var
vRowIndex1:整数;
vRowIndex2:整数;
vColumnIndex:整数;
vValue1:整数;
vValue2:整数;
开始
vRowIndex1:= 5;
vRowIndex2:= 8;
vValue1:= 5;
vValue2:= 10;
//计算可以在GPU上并行完成。
for vColumnIndex:= 0 to mColumnCount-1 do
begin
mTable [vRowIndex1,vColumnIndex]:=(mTable [vRowIndex1,
vColumnIndex] * vValue1) - (mTable [vRowIndex2,vColumnIndex] * vValue2);
结束;
结束;
对于cpu:
可以制作MMX / XMM / SIMD / SSE / SSE2版本。
对于gpu:
可以制作OpenGL或DirectX版本。
这是CPU与之间的较量GPU因此互相帮助
允许。
我的测试系统将是:
X2 3800+和两个GTX 7900 512 MB卡。
^^^代码可能会针对此系统进行大量优化或类似^^^。
替代测试系统可能是:
奔腾III 450 mhz和FX5200 128 MB内存。
^^^可以忽略。
代码可以是ASM,C / C ++或Delphi。
再见,
Skybuck。
" Skybuck Flying" < sp ** @ hotmail.comwrote in message
news:eo ********** @ news4.zwoll1.ov.home.nl ...
< blockquote class =post_quotes>
>
// cpu / serial概念代码是:
var
mTable:整数数组的数组;
mRowCount:整数;
mColumnCount:整数;
过程AllocateTable;
开始
mRowCount:= 8000;
mColumnCount:= 9000;
SetLength(mTable,mRowCount,mColumnCount);
结束;
程序WorkToDo;
var
vRowIndex1:整数;
vRowIndex2:整数;
vColumnIndex:整数;
vValue1:整数;
vValue2:整数;
开始
vRowIndex1:= 5;
vRowIndex2:= 8;
vValue1:= 5;
vValue2:= 10;
//计算可以在GPU上并行完成。
for vColumnIndex:= 0到mColumnCount-1做
开始
mTable [vRowIndex1,vColumnIndex]:=(mTable [vRowIndex1,
vColumnIndex] * vValue1) - (mTable [vRowIndex2,vColumnIndex] *
vValue2);
end;
end;
#1)感谢您将Pascal(或类似内容)发布到C语言组。
#2)你是阿基米德钚吗?
--------------------------------- ---------------------------
David T. Ashley(d ... @ e3ft.com)
http://www.e3ft.com (咨询主页)> http://www.dtashley.com (个人主页)
< a rel =nofollowhref =http://gpl.e3ft.comtarget =_ blank> http://gpl.e3ft.com (GPL出版物和项目)
David T. Ashley写道:
" Skybuck Flying" < sp ** @ hotmail.comwrote in message
#1)感谢您将Pascal(或类似内容)发布到C语言组。
#2)你是阿基米德钚吗?
Skybuck是一个飞行的疯子。请参阅:
http://groups.google.com/group/alt.l...6e8caff4d1a9cb
http://groups.google.com/group/alt.l...d694f9f550dbdd
不要给他任何关注。
P?¥Fri,2007年1月12日07:29:05 +0100,skrev Evenbit< nb ******** @ charter.net>:
Skybuck是一个飞行的疯子。请参阅:
http://groups.google.com/group/alt.l...6e8caff4d1a9cb
http://groups.google.com/group/alt.l...d694f9f550dbdd
别给他任何关注。
更好的SkyBuck然后是HLA。这家伙很有趣,对他来说不那么难。
他在做什么我相信是讽刺。他的全名只是一个嘲讽。
他可能过度了,但他实际上更有趣的是那些做他所做的事情的人。真实的。 />
和SkyBuck真的是一个非常有趣的名字。还有讽刺,我相信。
-
Funn 1a ?? 10 av omlag 89 700 000 som inneheldt" Disaster"
/>
Funn 1a ?? 10 av omlag 2 470 000 000 som inneheldt M
Hello,
In this contest the CPU will face the GPU.
Which processor will execute the code/concept faster ?
// cpu/serial concept code is:
var
mTable : array of array of integer;
mRowCount : integer;
mColumnCount : integer;
procedure AllocateTable;
begin
mRowCount := 8000;
mColumnCount := 9000;
SetLength( mTable, mRowCount, mColumnCount );
end;
procedure WorkToDo;
var
vRowIndex1 : integer;
vRowIndex2 : integer;
vColumnIndex : integer;
vValue1 : integer;
vValue2 : integer;
begin
vRowIndex1 := 5;
vRowIndex2 := 8;
vValue1 := 5;
vValue2 := 10;
// calculations could be done in parallel on GPU.
for vColumnIndex := 0 to mColumnCount-1 do
begin
mTable[ vRowIndex1, vColumnIndex ] := (mTable[ vRowIndex1,
vColumnIndex ] * vValue1) - (mTable[ vRowIndex2, vColumnIndex ] * vValue2);
end;
end;
For cpu:
MMX/XMM/SIMD/SSE/SSE2 version could be made.
For gpu:
OpenGL or DirectX version could be made.
This is a contest between the CPU and GPU thus helping each other is
allowed.
My test system will be:
X2 3800+ and two GTX 7900 512 MB cards.
^^^ Code may be heavily optimized for this system or similiar ^^^.
Alternative test system could be:
Pentium III 450 mhz and FX5200 with 128 MB ram.
^^^ can be ignored.
Code can be in ASM, C/C++ or Delphi.
Bye,
Skybuck.
"Skybuck Flying" <sp**@hotmail.comwrote in message
news:eo**********@news4.zwoll1.ov.home.nl...>
// cpu/serial concept code is:
var
mTable : array of array of integer;
mRowCount : integer;
mColumnCount : integer;
procedure AllocateTable;
begin
mRowCount := 8000;
mColumnCount := 9000;
SetLength( mTable, mRowCount, mColumnCount );
end;
procedure WorkToDo;
var
vRowIndex1 : integer;
vRowIndex2 : integer;
vColumnIndex : integer;
vValue1 : integer;
vValue2 : integer;
begin
vRowIndex1 := 5;
vRowIndex2 := 8;
vValue1 := 5;
vValue2 := 10;
// calculations could be done in parallel on GPU.
for vColumnIndex := 0 to mColumnCount-1 do
begin
mTable[ vRowIndex1, vColumnIndex ] := (mTable[ vRowIndex1,
vColumnIndex ] * vValue1) - (mTable[ vRowIndex2, vColumnIndex ] *
vValue2);
end;
end;#1)Thanks for posting Pascal (or something similar) to a C-language group.
#2)Are you Archimedes Plutonium?
------------------------------------------------------------
David T. Ashley (d...@e3ft.com)
http://www.e3ft.com (Consulting Home Page)
http://www.dtashley.com (Personal Home Page)
http://gpl.e3ft.com (GPL Publications and Projects)
David T. Ashley wrote:"Skybuck Flying" <sp**@hotmail.comwrote in message
#1)Thanks for posting Pascal (or something similar) to a C-language group.
#2)Are you Archimedes Plutonium?Skybuck is a flying loony. See:
http://groups.google.com/group/alt.l...6e8caff4d1a9cb
http://groups.google.com/group/alt.l...d694f9f550dbdd
Don''t give him any attention.
P?¥ Fri, 12 Jan 2007 07:29:05 +0100, skrev Evenbit <nb********@charter.net>:
Skybuck is a flying loony. See:
http://groups.google.com/group/alt.l...6e8caff4d1a9cb
http://groups.google.com/group/alt.l...d694f9f550dbdd
Don''t give him any attention.Better SkyBuck then HLA. The guy is funny, dont be so hard on him.
What he is doing I belive is sarcasm. His whole name is just a taunt.
He is maybe overdoing it, but he is actually more entertaining then the
guys that does what he does, for real.
And "SkyBuck" is really a very funny name. Also sarcasm, I belive.
--
Funn 1a??10 av omlag 89 700 000 som inneheldt "Disaster"
Funn 1a??10 av omlag 2 470 000 000 som inneheldt M
这篇关于CPU与GPU比赛。的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!