Re: rewrite glRotate?

I don't know if I understand this correctly.
Is that mean, that 32bit CPU makes matrix multiplication operations
faster that 256bit GPU?


CPU: 3GHz
GPU: 600Mhz

Also, you're mixing bus width with register size.
A pentium CPU has 32 bit registers but it has a
64 bit data bus.

Besides, sending the data to the GPU has a lot of
overhead - copy the data to a buffer, set up the DMA
controller, transfer the data....etc. The CPU will have
finished the multiply long before the data even gets
to the GPU.


--
<\___/>
/ O O \
\_____/ FTB. Remove my socks for email address.

.

Relevant Pages

  • acpi problems w/ DL140s in recent kernels
    ... Using 3 I/O APICs ... CPU: Trace cache: 12K uops, ... number of MP IRQ sources: ... register #01: 000F0011 ...
    (Linux-Kernel)
  • Re: 2.6.16-rc5 lost cpu
    ... CPU: Trace cache: 12K uops, ... Using specific hotkey driver ... Unable to register with parport ... Detection failed at step 5 ...
    (Linux-Kernel)
  • Re: 2.6.16-rc5 lost cpu
    ... CPU: Trace cache: 12K uops, ... Using specific hotkey driver ... Unable to register with parport ... hub 1-0:1.0: USB hub found ...
    (Linux-Kernel)
  • Irq balancing problem?
    ... then I also disabled the user-space irq balancing daemon (in ... CPU: After generic identify, caps: bfebfbff ... PCI: PCI BIOS revision 2.10 entry at 0xfd8d5, ...
    (Linux-Kernel)
  • 2.6.8.1 memory issues
    ... model name: IntelXeonCPU 2.80GHz ... mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe cid ... PCI: PCI BIOS revision 2.10 entry at 0xfc91e, ... register #01: 000F0011 ...
    (Linux-Kernel)