Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Elmer who wrote (163554)	4/5/2002 12:38:17 PM
From: wanna_bmw	Read Replies (2) \| Respond to of 186894

Elmer, there is a ton of great commentary in that article, but I just wanted to highlight one section. I'd really like to see the AMDroids refute this, as I'm sure they will - attacking every line methodically, and giving reasons why this guy doesn't know what he's talking about. All the while, they will completely ignore the fact that they worshipped this guy when he criticized the micro-architecture a year ago last December. <ggg> "Sleazy Marketing Targeting Stupid People While I certainly support educating people to the fact that CLOCK SPEED IS NOT EVERYTHING (you just knew that was coming) the marketing tactic used by AMD to number their processors slightly above the true clock speed is misleading. A 1.33 GHz Athlon XP is called the Athlon XP 1500. Makes you believe it is a 1.5 GHz chip, yet it most cases the chip runs slower than AMD's older Athlon Thunderbird 1400. This sleazy numbering scheme has also allowed AMD to pull another trick that we've all seen them pull over the past 6 months, and that is to use a big number increase to hide a rather small clock speed increase. In October they launched the Athlon XP 1500, 1600, 1700, and 1800 models, followed in November by the 1900, then in January the 2000, and most recently the 2100. That's a lot of chips and a lot of numbers. But look at how they dumb it down to take advantage of most people's poor math skills: The 1500 is a 1.33 GHz chip. Each subsequent "100" increase in part number corresponds to a 66 or 67 MHz instead in true clock speed. For example, the 1800 runs at 1.53 GHz, and the 2100 runs at 1.73 GHz clock speed. While 2100/1500 = 1.4, which would imply a 40% increase in speed since October, the actual clock speeds - 1.73/1.33 = 1.3 - only indicate a 30% speed increase from the 1500 part to the 2100 part. In other words, AMD has sneaked in a whole 10% phantom speed increase that isn't there! Add to that the fact that AMD was already shipping the 1400 MHz Athlon already, and this 40% marketed speed increase really translates into just 23%. Also if you do the math, i.e. 66/1600, each 66 MHz increase in speed from one part to the next is really only about a 4% real increase. 4%, that's it. Looking at AMD's wholesale pricing on their web site, each extra 4% increase in speed translates into a whopping 20% hike in the price. The XP2100 (the 1.73 GHz chip) literally costs $81 more than the XP2000 (the 1.67 GHz chip) costs, and that extra $81 for 4% more speed is a bad tradeoff. If you look at past history, CPU clock speeds usually go up in 50, 66, 100, 133, or 200 MHz increments. You'd go from 450 to 500 MHz. Or 667 to 733 MHz. Or 1.1 to 1.2 GHz. In each case, the speed increase from one model of chip to the next was on the order of about a 10% speed increase. And the Pentium 4 for example, has recently been released in 200 MHz increments - 2.0 GHz, 2.2 GHz, and 2.4 GHz which is also on the order of 10% each time. But since last summer AMD has only responded in turn with a lousy 4% increase each time while raising the price significantly each time. This is so not like AMD to be having like this based on how they successfully gained market share with the Athlon the last few years with large and significant speed increases at a low cost. I was lukewarm to this dumb numbering scheme back in October, and seeing how they exploit it just plain pisses me off. It doesn't take a math whiz to see that AMD is playing games with the numbers." wbmw

To: Elmer who wrote (163554)	4/5/2002 12:55:22 PM
From: wanna_bmw	Read Replies (1) \| Respond to of 186894

Elmer, here is another very interesting find! Apparently, doubling the L2 cache was not the only change that Intel made to the Northwood core! I am now looking forward to running Constantine's C++ benchmark. ------------------------------- Not just a clock speed increase One thing that was a pleasant surprise with the new Pentium 4 Northwood processors is that they do offer slightly more speed at the same clock speed than earlier Pentium 4 processors, showing once again that CLOCK SPEED IS NOT EVERYTHING! There is actually about a 5% to 10% jump in performance for most tests between the old Willamette core processors (i.e. the .18 micron Pentium 4 with the 256K L2 cache) and the Northwood (the .13 micron Pentium 4 with 512K L2 cache), even at the same 2.0 GHz clock speed. Part of this boost is partly due of course to the larger 512K on-chip L2 cache. But as I found in recent testing, it is also due to the fact that certain machine language instructions are actually faster in the new processor. Specifically instructions having to do with branching and jumping through indirect pointers are several clock cycles faster. These are the types of instructions that directly affect the speed of things like, well, emulators (which use a lot of table dispatches), C++ programs (similarly due to a lot of indirect calls through vtables), and even DLL calls in standard Windows programs. Intel has finally started fixing the chip by reducing the clock cycle counts on common instructions. AMD on the other hand, as I said, the instruction timings have been virtually unchanged for over 2 years. This is good and bad. Good in terms of "if it ain't broke don't fix it", since the Athlon is already very efficient. But bad in terms of that there are known instruction sequences that cause the Athlon to run slower than say, an equivalent Pentium III. Sequences having to do with resolving two memory addresses for example. Or code that is mostly running from L2 cache. The Athlon's L2 cache appears to have a 20 clock cycle latency, versus 3 cycles on the Pentium 4 and 4 cycles on the Pentium III. The Pentium 4 now not only has MORE on-chip cache, but it has FASTER on-chip cache. That's a huge blow to the Athlon. The current Pentium 4 is now almost right at the specified 80% level of efficiency they planned for it. All in all, between the final 2.0 GHz .18 micron Pentium 4, and today's 2.4 GHz .13 micron Pentium 4, Intel has delivered about a 25% to 30% measured performance increase in the space of only 3 months. wbmw