OpenGL核心配置文件在OS X上令人难以置信的速度下降 [英] OpenGL core profile incredible slowdown on OS X
问题描述
我向引擎添加了一个新的GL渲染器，该渲染器使用了核心配置文件.虽然它可以在Windows 和/或nvidia卡上正常运行，但在OS X上却要慢10倍(3 fps而不是30 fps).奇怪的是，我的兼容性配置文件渲染器运行正常.
I added a new GL renderer to my engine, which uses the core profile. While it runs fine on Windows and/or nvidia cards, it is like 10 times slower on OS X (3 fps instead of 30). The weird thing is, that my compatibility profile renderer runs fine.
我使用Instruments和GL profiler收集了一些跟踪记录:
I collected some traces with Instruments and the GL profiler:
https://www.dropbox.com/sh/311fg9wu0zrarzm/31CGvUcf2q
它表明应用程序将时间花在glDrawRangeElements上. 我尝试了以下操作:
It shows that the application spends its time in glDrawRangeElements. I tried the following things:
- 改为使用glDrawElements(无效)
- 翻转剔除(不影响速度)
- 禁用某些GL_DYNAMIC_DRAW缓冲区(无效)
- 绘制时在VAO之后绑定索引缓冲区(无效)
- 将索引转换为4个字节(无效)
- 使用GL_BGRA纹理(无效果)
我没有尝试过将顶点对齐到16字节边界和/或将索引转换为4字节，但是很严重的是，如果那是个问题，那为什么为什么要使用标准允许吗?
What I didn't try is to align my vertices to 16 byte boundary and/or convert indices to 4 byte, but seriously, if that would be the issue then why the hell does the standard allow it?
我正在创建这样的上下文:
I'm creating the context like this:
NSOpenGLPixelFormatAttribute attributes[] =
{
NSOpenGLPFAColorSize, 24,
NSOpenGLPFAAlphaSize, 8,
NSOpenGLPFADepthSize, 24,
NSOpenGLPFAStencilSize, 8,
NSOpenGLPFADoubleBuffer,
NSOpenGLPFAAccelerated,
NSOpenGLPFANoRecovery,
NSOpenGLPFAOpenGLProfile, NSOpenGLProfileVersion3_2Core,
0
};
NSOpenGLPixelFormat* format = [[NSOpenGLPixelFormat alloc] initWithAttributes:attributes];
NSOpenGLContext* context = [[NSOpenGLContext alloc] initWithFormat:format shareContext:nil];
[self.view setOpenGLContext:context];
[context makeCurrentContext];
尝试以下规格:
- radeon 6630M，OS X 10.7.5
- radeon 6750M，OS X 10.7.5
- geforce GT 330M，OS X 10.8.3
您有什么想法我可能做错了吗?再次，它与兼容性配置文件一起正常工作(虽然不使用VAO).
Do you have any ideas what I might do wrong? Again, it works fine with the compatibility profile (not using VAOs though).
更新:已向Apple报告.
UPDATE: reported to Apple.
更新:Apple并没有对此问题表示怀疑……无论如何，我创建了一个很小的测试程序，它实际上是很好的.现在，我将调用堆栈与Instruments进行了比较，发现使用引擎时， glDrawRangeElements 会执行两个调用:
UPDATE: Apple doesn't give a damn to the problem...anyway I created a small test program which is actually good. Now I compared the call stack with Instruments, and found out that when using the engine, glDrawRangeElements does two calls:
- gleDrawArraysOrElements_ExecCore
- gleDrawArraysOrElements_Entries_Body
在测试程序中，它仅调用第二个.现在，第一个调用的功能类似于即时模式渲染(gleFlushPrimitivesTCLFunc，gleRunVertexSubmitterImmediate)，因此显然会导致速度下降.
while in the test program it calls only the second. Now the first call does something like an immediate mode render (gleFlushPrimitivesTCLFunc, gleRunVertexSubmitterImmediate), so obviously casues the slowdown.
推荐答案
最后，我能够重现减速情况.这简直太疯狂了……这显然是由于在"my_Position"属性上调用 glBindAttribLocation 引起的.现在，我做了一些测试:
Finally, I was able to reproduce the slowdown. This is just crazy... It is clearly caused by glBindAttribLocation being called on the "my_Position" attribute. Now I did some testing:
- 默认为1(由 glGetAttribLocation 返回)
- 如果我将其设置为零，就没有问题
- 如果将其设置为1，渲染会变慢
- 如果我将其设置为更大的数字，它将再次变慢
- 1 is default (as returned by glGetAttribLocation)
- if I set it to zero, theres no problem
- if I set it to 1, the rendering becomes slow
- if I set it to any larger number, it is slow again
很明显，我重新链接了程序(检查代码).在实现中这不是问题，我也使用正常"值对其进行了测试.
Obviously I relink the program (check code). It is not a problem in the implementation, I tested it with "normal" values too.
测试程序:
https://www.dropbox.com/s/dgg48g1fwgyc5h0/SLOWDOWN_REPRO.zip
如何复制:
- 使用XCode打开
- 打开common/glext.h(请勿打扰该名称)
- 将GLDECLUSAGE_POSITION常量从0修改为1
- 编译并运行=>慢
- 变回零=>好
这篇关于OpenGL核心配置文件在OS X上令人难以置信的速度下降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！
