Micro CPU benchmarks: isolating the FPU

But you can't compare an Intel PC with an Apple. The software might not be optimised the right way." Indeed, it is clear that the Final Cut Pro, owned by Apple, or Adobe Premiere, which is far better optimised for the Intel PC, are not very good choices to compare the G5 with the x86 world.

So, before we start with application benchmarks, we performed a few micro benchmarks compiled on all platforms with the same gcc 3.3.3 compiler.

The first one is flops. Flops, programmed by Al Aburto, is a very floating-point intensive benchmark. Analyses show that this benchmark contains:
  • 70% floating point instructions;
  • only 4% branches; and
  • Only 34% of instructions are memory instructions.
Note that some of those 70% FP instructions are also memory instructions. Benchmarking with Flops is not real world, but isolates the FPU power.

Al Aburto, about Flops:
" Flops.c is a 'C' program which attempts to estimate your systems floating-point 'MFLOPS' rating for the FADD, FSUB, FMUL, and FDIV operations based on specific 'instruction mixes' (see table below). The program provides an estimate of PEAK MFLOPS performance by making maximal use of register variables with minimal interaction with main memory. The execution loops are all small so that they will fit in any cache."
Flops shows the maximum double precision power that the core has, by making sure that the program fits in the L1-cache. Flops consists of 8 tests, and each test has a different, but well known instruction mix. The most frequently used instructions are FADD (addition), FSUB (subtraction) and FMUL (multiplication). We used gcc -O2 flops.c -o flops to compile flops on each platform.

MODULE FADD FSUB FMUL FDIV Powermac G5 2.5 GHz Powermac G5 2.7 GHz Xeon Irwindale 3.6 GHz Xeon Irwindale 3.6 w/o SSE2* Xeon Galatin 3.06 GHz Opteron 250 2.4 GHz
1 50% 0% 43% 7% 1026 1104 677 1103 1033 1404
2 43% 29% 14% 14% 618 665 328 528 442 843
3 35% 12% 53% 0% 2677 2890 532 1088 802 1955
4 47% 0% 53% 0% 486 522 557 777 988 1856
5 45% 0% 52% 3% 628 675 470 913 995 1831
6 45% 0% 55% 0% 851 915 552 904 1030 1922
7 25% 25% 25% 25% 264 284 358 315 289 562
8 43% 0% 57% 0% 860 925 1031 910 1062 1989
Average: 926 998 563 817 830 1545

The results are quite interesting. First of all, the gcc compiler isn't very good in vectorizing. With vectorizing, we mean generating SIMD (SSE, Altivec) code. From the numbers, it seems like gcc was only capable of using Altivec in one test, the third one. In this test, the G5 really shows superiority compared to the Opteron and especially the Xeons.

The really funny thing is that the new Xeon Irwindale performed better when we disabled support for the SSE-2, and used the "- mfpmath=387" option. It seems that the GCC compiler makes a real mess when it tries to optimise for the SSE-2 instructions. One can, of course, use the Intel compiler, which produces code that is up to twice as fast. But the use of the special Intel compiler isn't widespread in the real world.

Also interesting is that the 3.06 GHz Xeon performs better than the Xeon Irwindale at 3.6 GHz. Running completely out of the L1-cache, the high latency (4 cycles) of the L1-cache of Irwindale hurts performance badly. On the Galatin Xeon, which is similar to Northwood, Flops benefits from the very fast 2-cycle latency.

The conclusion is that the Opteron has, by far, the best FPU, especially when more complex instructions such a FDIV (divisions) are used. When the code is using something close to the ideal 50% FADD/FSUB and 50% FMUL mix and is optimised for Altivec, the G5 can roll its muscles. The normal FPU is rather mediocre though.

Micro CPU benchmarks: isolating the Branch Predictor

To test the branch prediction, we used the benchmark " Queens". Queens is a very well known problem where you have to place n chess Queens on an n x n board. The catch is that no single Queen must be able to attack the other. The exhaustive search strategy for finding a solution to placing the Queens on a chess board so they don't attack each other is the algorithm behind this benchmark, and it contains some very branch intensive code.

Queens has about:
  • 23% branches
  • 45% memory instructions
  • No FP operations
On a PIII, the Branch misprediction rate is up to 19%! (Typical: 9%) Queens runs perfectly in the L1-cache.

RUN TIME (sec)
Powermac G5 2.5 GHz 134.110
Xeon Irwindale 3.6 GHz 125.285
Opteron 250 2.4 GHz 103.159

At 2.7 GHz, the G5 was just as fast as the Xeon. It is pretty clear that despite the enormous 31 stage pipeline, the fantastic branch predictor of the "Xeon Pentium 4" is capable of keeping the damage to a minimum. The Opteron's branch predictor seems to be at the level of G5's: the branch misprediction penalty of the G5 is 30% higher, and the Opteron does about 30% better.

The G5 as workstation processor

It is well known that the G5 is a decent workstation CPU. The G5 is probably the fastest CPU when it comes to Adobe After Effects and Final Cut Pro, as this kind of software was made to be run on a PowerMac. Unfortunately, we didn't have access to that kind of software.

First, we test with Povray, which is not optimised for any architecture, and single-threaded.

Povray
Seconds
Dual Opteron 250 (2.4 GHz) 804
Dual Xeon DP 3.6 GHz 1169
Dual G5 2.5 GHz PowerMac 1125
Dual G5 2.7 GHz PowerMac 1049

Povray runs mostly out of the L2- and L1-caches and mimics almost perfectly what we have witnessed in our Flops benchmarks. As long as there are little or no Altivec or SSE-2 optimisations present, the Opteron is by far the fastest CPU. The G5's FPU is still quite a bit better than the one of the Xeon.

The next two tests are the only 32 bit ones, done in Windows XP on the x86 machines.

Lightwave 8.0
Raytrace
Lightwave 8.0
Tracer Radiosity
Dual Opteron 250 (2,4 GHz) 47 204
Dual Xeon DP 3,6 GHz 47.3 180
Dual G5 2,5 GHz PowerMac 46.5 254

The G5 is capable of competing in one test. Lightwave rendering engine has been meticulously optimised for SSE-2, and the " Netburst" architecture prevails here. We have no idea how much attention the software engineers gave Altivec, but it doesn't seem to be much. This might of course be a result of Apple's small market share.

Cinema 4D
Cinebench
Dual Opteron 250 (2.4 GHz) 630
Dual Xeon DP 3.6 GHz 682
Dual G5 2.5 GHz PowerMac 638
Dual G5 2.7 GHz PowerMac 682

Maxon has invested some time and effort to get the Cinema4D engine running well on the G5 and it shows. The G5 competes with the best x86 CPUs.

Benchmark configuration The G5 as Server CPU
Comments Locked

116 Comments

View All Comments

  • exdeath - Friday, June 3, 2005 - link

    Wow look at a 2.4 GHz Opteron clean house.

    I'd like to see what a 2.6 GHz FX-55 with unregistered memory would do ;) I'll be fair and say keep it at 2.6 GHz stock ;)
  • bersl2 - Friday, June 3, 2005 - link

    Right. GCC 4.0 has an all new optimization framework, including autovectorization:

    http://gcc.gnu.org/projects/tree-ssa/vectorization...
  • Pannenkoek - Friday, June 3, 2005 - link

    It is well known that GCC 3.3 can't vectorize code. However, GCC 4 should be able to, eventually if not already.

    The small cache of the G5 would hamper its server performance I'd reckon, regardless of other factors.
  • jimbailey - Friday, June 3, 2005 - link

    I'm curious if you rebuilt Apache and MySQL from source. Apple has added significant amount of optimization to gcc and I would love to know if it has been included in this test. I don't doubt the results though. The trade off for using the Mach micro-kernel is well known.
  • rubikcube - Friday, June 3, 2005 - link

    Johan, I agree that all the facts point to your conclusions being accurate. I would bet all the money in the world that you are correct. However, this hypothesis is easily confirmed by running mysql on a G5 running linux.
  • Olaf van der Spek - Friday, June 3, 2005 - link

    > In Unix, this is done with a Syscall, and it results in two context switches (the CPU has to swap out one process for another)

    Does it?
    As far as I know it doesn't. The page tables don't need to be swapped and neither does the CPU state. The CPU gets access to the kernel-data because it goes to kernel-mode, but that doesn't require a full context switch I think.
  • WileCoyote - Friday, June 3, 2005 - link

    Tough crowd...
  • Eug - Friday, June 3, 2005 - link

    Of the stuff I understand, I agree with your conclusions, but I think it's reasonable to state that running Linux on the G5 yourself would have been the most definitive test.

    Anyways, I like fusion food. :)
  • cHodAXUK - Friday, June 3, 2005 - link

    Great article, very educational read and it was very interesting to see what is holding the G5 back. IBM/Apple really need to address these issues, people are paying alot of money for G5's that are dilvering nowhere near the level of performance that they *theoretically* should be.
  • Netopia - Friday, June 3, 2005 - link

    WOW... great article.

    I too would like to see Yellow Dog (Or FC4) loaded on the G5 for a true head-to-head. I hope you have the time with the box to get 'er done!

    Joe

Log in

Don't have an account? Sign up now