Uh... since semiconductor cost is directly proportional to size, increasing the density reduces the cost for a die with the same circuits. Likewise, increasing the density also allows you to put more circuits on the same die and to run them at higher speeds, increasing performance. Moore was most defnitely talking about price and performance in his "law", he was just not spelling out every little detail for you.
Labels do not make $5 per CD, they make more like $8-9.
Proof please? According to Sony's FY2002 Financial Report, their music division made $1.2 billion in revenue, and had a net loss of $46 million. That's a profit margin of -3.8%. The current top-selling Sony CD is Pearl Jam's Riot Act which costs $13.49 on Amazon. Let's be generous and assume Amazon pays Sony that much for the CD. That would mean that, with costs amortized across their entire catalog, Sony will lose about 50 cents for each Pearl Jam CD sold. Where do you get the figure of $8-$9 per CD? Can you post financial statements from another major label which has a profit margin in the 60%-70% range you claim?
As a former employee, I think they are doomed too. Linux is only a minor problem though, the real issue is the maturity of the market and thier inability to add value to their current products. Their products will simply become a commodity.
Coca-Cola hasn't added value to their core product in a century, has substantially higher prices than their competitors (generic), operates in an extremely mature business, and yet has not trouble increasing profits.
The fastest AMD part listed in Pricewatch is the 2400+ (1.93 GHz) for $191. The equivalent Pentium 4 (2.4 GHz) is $188 (i.e. less expensive than AMD). Furthemore there are substantially faster Pentium parts available (up to 2.8 GHz now).
I wonder how much better could we be if coders knew basic math, if they know how those little bitty chips actually computed the sine of something instead of assuming it works. We would probably have rock solid operating systems without all the glitzy GUI stuf..
Huh? What's the use of sine in an OS besides to draw glitzy GUI stuff?
BMW's highest end car is $20,000 more than the second highest, and gets from 0-60 in 0.1 seconds fewer than the second highest. Yet people still flock to the more expensive car.
This has got to be a hoax. First of all, it is dated almost exactly twenty years before today, so as to set a big milestone this year. Second, I find it impossible to believe the methodology used to get retrieve the message, that a university would have 20 year old backups and still have the people around with the expertise to extract them. Finally, I find the contention that this is the origination of the smiley pretty supsicious -- the fact that it started in a single message on an isolated message board and just a decade later was on every network (e.g. Usenet, GEnie, CIS, etc.) and understood by every computer user. More likely it has sprung up independently many different times in different places, since it's a pretty obvious invention.
Why should I start paying for the show when I get it for free now? Myself, and probably 99.44% of Americans, will not. Commercials are acceptable because they are a natural break during the program. This is why Pay TV such as HBO is annoying because you are glued to TV for the whole two hours of the movie. Basically this proposal has me paying MORE - I have to buy a PVR to 'pause' (which I get for free now) and I have to pay for the show itself.
And whatever happens, don't go to the PBS/NPR model of subscription drives. Even though they only happen one week per quarter, they are infinitely more annoying than a constant but gradual stream of commercials.
Apples to apples please - when you clock the Athlon at the same clockspeed as the Intel chip, (which are possible with the new chips that AMD just released) the FPU is far faster on the Athlon chips.
Not that it matters, but P4 and Athlon performance are approximately equivalent on a per-clock basis: Athlon does 624 / 1800 MHz (0.346) "SPECfp points per megaherz" (whatever that means), and P4 does 861 / 2533 MHz (0.399). Of course since P4 can clock much faster it has better absolute FP performance.
This is what indicates a superior FPU design, not a comparison based on a ~700mhz difference in clockspeed.
Let's throw Itanium 2 into the picture, which does a whopping 1356 SPECfp at an equally astonishing 1.0 GHz, which puts it at this silly "SPECfp points per megaherz" of 1.356 - quadruple that of Athlon/P4.
Does that mean Itanium 2's FPU is four times better than Athlon?
According to Hennesy & Patterson, 2nd Edition, page 391, the total miss rate (for SPEC92) of a 8k 4-way set associative cache (like the P4's) is 2.9%. The miss rate of a 128k 4-way set associative cache (like Athlon's) is 0.6%.
The hit time for P4 is 2 cycles, and for Athlon it's 3 cycles. The L2 hit / L1 miss is ~10 cycles for both. Everything further out is approximately the same so we can ignore it for simplicity.
So, the average memory access time for P4 is (0.971 * 2) + (0.029 * 10) = 2.2 Cycles. The average memory access time for Athlon is (0.994 * 3) + (0.006 * 10) = a little over 3 cycles.
Suppose Athlon had an infinite size L1 cache (or 512 MB if you like to use numbers). The highest hit rate it could ever achieve is 100% (actually slightly less, since you cannot eliminate complulsory misses). The average memory access time would then be 3 cycles - which is higher than P4's 2.2 cycles!
The Pentium IV has other questionable design desisions that hurt performance as well. It has 8K of L1 cache, the same amount found in the ancient 486 processor, whereas the Athlon has that amount squared and doubled (128K).
Obviously you flunked your freshman-level computer architecture course. The P4 8K L1's 2-cycle load-use latency is 50% better than Athlon 128k L1's 3-cycle load-use latency (not even accounting for P4's clock speed advantage). The difference in hit rate between 8k and 128k is only about 5% meaning that it is substantially faster to go with the small/fast cache than the big/slow cache. Do the math - even an infinitely large 3-cycle load-use cache is slower than an 8k 2-cycle load-use cache.
Cache size comparisons are more meaningless than megahertz comparisons. Whenever somebody tries to justify a big cache size without looking at performance, just walk away. AMD is playing marketing games with their slow-as-molasses (but massive) L1 cache.
I won't bother to address the rest of the technical errors in your post...
I don't think there is much motivation on the part of compiler writers to optimize for this particular implementation of the x86-32 ISA.
Over 80% of new computers being shipped are P4 based. Therefore, applications will be optimized for P4. Not optimizing your application for P4 would be look a hardware vendor not releasing a Windows driver for their device.
The thing about the Athlon line of processors is the FPU, which blows the P4 away.
According to SPECfp, which is by far the most impeccable FP benchmark in the industry and supported by a huge industry consortium, the Athlon XP 2200+ scores only 624, while the 2.53 GHz Pentium 4 scores 861. What industry supported application supports your claim that Athlon has a superior FPU?
revs and horse-power if you use the car engine analogy. Just because it can get higher cycles per second doesn't mean it does "useful" work. In fact, thermodynamically speaking, you can probably measure the efficiency of a chip by its heat dissipation.
Yeah, but clock speed efficiency (IPC) in computers is meaningless -- and nobody cares about it.
According to SPECint the fastest CPU right now is Pentium 4 @ 2.53 GHz, and the second fastest is McKinley (aka Itanium 2) @ only 1 GHz. They are roughly equivalent in speed, but by IPC McKinley is much better. But so what? You can't run McKinley any faster than 1 GHz, and you can run a Pentium 4 at 2.53 GHz, so why even make the comparison?
OTOH, I don't recall for sure if the original Pentium (or derivatives, like P54C) were known as "P5". If they had, then it's already time for a name change for the successor of the P4.
P3 was the code name for the 386, and there was no confusion when people started calling the Pentium III, the "P3". Similarly, P4 was the codename for the 486, and when the Pentium 4 was released, there was no confusion. I would guess that if Intel releases a processor called "Pentium 5", the P5 as the codename for the original Pentium will have been long since forgotten.
Microsoft is a convicted monopolist only in the desktop OS market. They're not a monopoly in academia or development tools, and, in fact, Sun has higher market shares in both of those markets.
Why exactly this is a YRO article? Do people with free e-mail accounts have the "right" to never receive from any recipient besides their friends? Is/. defending the rights of spammers to flood Hotmail? I'm confused about exactly what rights are at stake here...
Slashdot Mirror
Uh ... since semiconductor cost is directly proportional to size, increasing the density reduces the cost for a die with the same circuits. Likewise, increasing the density also allows you to put more circuits on the same die and to run them at higher speeds, increasing performance. Moore was most defnitely talking about price and performance in his "law", he was just not spelling out every little detail for you.
Labels do not make $5 per CD, they make more like $8-9.
Proof please? According to Sony's FY2002 Financial Report, their music division made $1.2 billion in revenue, and had a net loss of $46 million. That's a profit margin of -3.8%. The current top-selling Sony CD is Pearl Jam's Riot Act which costs $13.49 on Amazon. Let's be generous and assume Amazon pays Sony that much for the CD. That would mean that, with costs amortized across their entire catalog, Sony will lose about 50 cents for each Pearl Jam CD sold. Where do you get the figure of $8-$9 per CD? Can you post financial statements from another major label which has a profit margin in the 60%-70% range you claim?
As a former employee, I think they are doomed too. Linux is only a minor problem though, the real issue is the maturity of the market and thier inability to add value to their current products. Their products will simply become a commodity.
Coca-Cola hasn't added value to their core product in a century, has substantially higher prices than their competitors (generic), operates in an extremely mature business, and yet has not trouble increasing profits.
You know, the old altavista.digital.com URL is still in service. I just tried it. Pretty amazing.
AMD doesn't have the equivalent of a 3GHz SMT CPU.
The fastest AMD part listed in Pricewatch is the 2400+ (1.93 GHz) for $191. The equivalent Pentium 4 (2.4 GHz) is $188 (i.e. less expensive than AMD). Furthemore there are substantially faster Pentium parts available (up to 2.8 GHz now).
I wonder how much better could we be if coders knew basic math, if they know how those little bitty chips actually computed the sine of something instead of assuming it works. We would probably have rock solid operating systems without all the glitzy GUI stuf..
Huh? What's the use of sine in an OS besides to draw glitzy GUI stuff?
BMW's highest end car is $20,000 more than the second highest, and gets from 0-60 in 0.1 seconds fewer than the second highest. Yet people still flock to the more expensive car.
This has got to be a hoax. First of all, it is dated almost exactly twenty years before today, so as to set a big milestone this year. Second, I find it impossible to believe the methodology used to get retrieve the message, that a university would have 20 year old backups and still have the people around with the expertise to extract them. Finally, I find the contention that this is the origination of the smiley pretty supsicious -- the fact that it started in a single message on an isolated message board and just a decade later was on every network (e.g. Usenet, GEnie, CIS, etc.) and understood by every computer user. More likely it has sprung up independently many different times in different places, since it's a pretty obvious invention.
Mainly to develop faster microprocessors.
Actually there were problems in going above 2.2GHz since that is negative number (using 32 bit signed). See here for example.
Why should I start paying for the show when I get it for free now? Myself, and probably 99.44% of Americans, will not. Commercials are acceptable because they are a natural break during the program. This is why Pay TV such as HBO is annoying because you are glued to TV for the whole two hours of the movie. Basically this proposal has me paying MORE - I have to buy a PVR to 'pause' (which I get for free now) and I have to pay for the show itself.
And whatever happens, don't go to the PBS/NPR model of subscription drives. Even though they only happen one week per quarter, they are infinitely more annoying than a constant but gradual stream of commercials.
Apples to apples please - when you clock the Athlon at the same clockspeed as the Intel chip, (which are possible with the new chips that AMD just released) the FPU is far faster on the Athlon chips.
Not that it matters, but P4 and Athlon performance are approximately equivalent on a per-clock basis: Athlon does 624 / 1800 MHz (0.346) "SPECfp points per megaherz" (whatever that means), and P4 does 861 / 2533 MHz (0.399). Of course since P4 can clock much faster it has better absolute FP performance.
This is what indicates a superior FPU design, not a comparison based on a ~700mhz difference in clockspeed.
Let's throw Itanium 2 into the picture, which does a whopping 1356 SPECfp at an equally astonishing 1.0 GHz, which puts it at this silly "SPECfp points per megaherz" of 1.356 - quadruple that of Athlon/P4.
Does that mean Itanium 2's FPU is four times better than Athlon?
According to Hennesy & Patterson, 2nd Edition, page 391, the total miss rate (for SPEC92) of a 8k 4-way set associative cache (like the P4's) is 2.9%. The miss rate of a 128k 4-way set associative cache (like Athlon's) is 0.6%.
The hit time for P4 is 2 cycles, and for Athlon it's 3 cycles. The L2 hit / L1 miss is ~10 cycles for both. Everything further out is approximately the same so we can ignore it for simplicity.
So, the average memory access time for P4 is (0.971 * 2) + (0.029 * 10) = 2.2 Cycles. The average memory access time for Athlon is (0.994 * 3) + (0.006 * 10) = a little over 3 cycles.
Suppose Athlon had an infinite size L1 cache (or 512 MB if you like to use numbers). The highest hit rate it could ever achieve is 100% (actually slightly less, since you cannot eliminate complulsory misses). The average memory access time would then be 3 cycles - which is higher than P4's 2.2 cycles!
BTW, Paul DeMone wrote a pretty good article about P4's L1 cache.
Since the P4 creams Athlon in SPEC (both Int and FP), that means it's not good enough for Van/AMD.
The Pentium IV has other questionable design desisions that hurt performance as well. It has 8K of L1 cache, the same amount found in the ancient 486 processor, whereas the Athlon has that amount squared and doubled (128K).
Obviously you flunked your freshman-level computer architecture course. The P4 8K L1's 2-cycle load-use latency is 50% better than Athlon 128k L1's 3-cycle load-use latency (not even accounting for P4's clock speed advantage). The difference in hit rate between 8k and 128k is only about 5% meaning that it is substantially faster to go with the small/fast cache than the big/slow cache. Do the math - even an infinitely large 3-cycle load-use cache is slower than an 8k 2-cycle load-use cache.
Cache size comparisons are more meaningless than megahertz comparisons. Whenever somebody tries to justify a big cache size without looking at performance, just walk away. AMD is playing marketing games with their slow-as-molasses (but massive) L1 cache.
I won't bother to address the rest of the technical errors in your post...
I don't think there is much motivation on the part of compiler writers to optimize for this particular implementation of the x86-32 ISA.
Over 80% of new computers being shipped are P4 based. Therefore, applications will be optimized for P4. Not optimizing your application for P4 would be look a hardware vendor not releasing a Windows driver for their device.
The thing about the Athlon line of processors is the FPU, which blows the P4 away.
According to SPECfp, which is by far the most impeccable FP benchmark in the industry and supported by a huge industry consortium, the Athlon XP 2200+ scores only 624, while the 2.53 GHz Pentium 4 scores 861. What industry supported application supports your claim that Athlon has a superior FPU?
The correct answer is:
number = 0x3ff
for i = 0 to 9:
number &= ~(1 (num[i] - 1))
return log2(number)+1
It means that a lot of people browse from work.
revs and horse-power if you use the car engine analogy. Just because it can get higher cycles per second doesn't mean it does "useful" work. In fact, thermodynamically speaking, you can probably measure the efficiency of a chip by its heat dissipation.
Yeah, but clock speed efficiency (IPC) in computers is meaningless -- and nobody cares about it.
According to SPECint the fastest CPU right now is Pentium 4 @ 2.53 GHz, and the second fastest is McKinley (aka Itanium 2) @ only 1 GHz. They are roughly equivalent in speed, but by IPC McKinley is much better. But so what? You can't run McKinley any faster than 1 GHz, and you can run a Pentium 4 at 2.53 GHz, so why even make the comparison?
OTOH, I don't recall for sure if the original Pentium (or derivatives, like P54C) were known as "P5". If they had, then it's already time for a name change for the successor of the P4.
P3 was the code name for the 386, and there was no confusion when people started calling the Pentium III, the "P3". Similarly, P4 was the codename for the 486, and when the Pentium 4 was released, there was no confusion. I would guess that if Intel releases a processor called "Pentium 5", the P5 as the codename for the original Pentium will have been long since forgotten.
the 'pay for play' concept for something you physically buy was none-too-appealing.
Then why are video rental and pay-per-view cable services thriving?
Microsoft is a convicted monopolist only in the desktop OS market. They're not a monopoly in academia or development tools, and, in fact, Sun has higher market shares in both of those markets.
Why exactly this is a YRO article? Do people with free e-mail accounts have the "right" to never receive from any recipient besides their friends? Is /. defending the rights of spammers to flood Hotmail? I'm confused about exactly what rights are at stake here...