Microsoft didn't release Windows NT 3.51 for the PowerPC until June, not long after IBM and Motorola fixed problems with the bug-delayed PowerPC 604 chip. Since we first tested the PowerPC systems, performance has improved dramatically. While the speed increase comes partly from refinements in Motorola's compiler technology, it's mostly due to the switch from first-generation 601 chips to the second-generation 604.
From BYTEmark results at the same clock speed, the 604 comes out roughly 30 percent faster than the 601. While both chips are 32-bit implementations of the 64-bit PowerPC architecture, the 604 is more superscalar than the 601. It can do more work per clock cycle. Here are some major differences between the two chips:
POWERPC 601
POWERPC 604
========================================================================
2.8 million transistors 3.6 million transistors
Three independent execution units Six independent execution units
Dispatches up to 3 instructions per Dispatches up to 4 instructions per
clock clock
Completes up to 3 instructions Completes up to 5 instructions per
per clock clock
Static branch prediction Dynamic branch prediction
32-KB unified cache Separate 16-KB instruction and
data caches
Eight-way set associative cache Four-way set associative cache
Flexible C++
Matthew Wilson
My approach to software engineering is far more pragmatic than it
is
theoretical--and no language better exemplifies this than C++.
BYTE Digest editors every month analyze and evaluate the best articles from Information Week, EE Times, Dr. Dobb's Journal, Network Computing, Sys Admin,
and dozens of other CMP publications—bringing
you critical news and information about wireless communication,
computer security, software development, embedded systems,
and more!