23 February 2017, 12:48 | #21 |
Registered User
Join Date: Mar 2009
Location: moon
Posts: 373
|
The Playstation has rather ugly 3D graphics due to lack of perspective correction (textures get warped) and low precision in the vertex position output from the geometry transformation (moving triangles stutter). Hombre could very well have produced better graphics, but would also be more expensive with its 100+ MHz CPU compared to Playstation's 33 Mhz one. If Commodore had gotten it out in a timely manner, it might have competed quite favourably against the PC though, as 3DFX Voodoo wasn't released until 1996. I don't think it would be possible for Commodore to use custom graphics chips designed in-house after that however. They would have to use third-party graphics cores like most successful arcade machines and game consoles have done ever since.
|
24 February 2017, 02:44 | #22 | ||||
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Quote:
Quote:
Quote:
Quote:
Let's evaluate the PA-RISC 7150 (introduced in 1994) with SIMD. It was based on the PA-RISC 7100 using the same fab process but with improved circuit design to allow 125MHz. The PA-RISC was one of the first general purpose processors to include an SIMD called MAX which processed only 32 bits as 2x16 bit data at one time using a single instruction (1.9x to 2.7x fps speedup claimed for MPEG video, convolve 512x512, zoom 512x512 and H.261 video). MAX-2 could process 64 bits as 4x16 bit data at one time using a single instruction (likely 2x the performance of 32 bit MAX). The PA-RISC 7100@99MHz (L1: 256kB ICache/256kB DCache) without SIMD could decode MPEG 320x240 video at 18.7 fps. My 68060@75MHz (L1: 8kB ICache/8kB DCache) using the old RiVA 0.50 decodes MPEG video between 18-22fps (average ~20fps). An update to the new RiVA 0.52 works now giving 21-29 fps (average is ~26fps with more 68060 optimization possible). Note that the PA-RISC 7100 was introduced in 1992 and used in technical and graphical workstations and computing servers while the 68060 was introduced in 1994 for desktop and embedded applications (less demanding and lower cost applications). The PA-RISC 7100LC@60MHz (L1: 32kB ICache/32kB DCache) introduced in 1994 with SIMD (initially 32 bit MAX but may have been upgraded to MAX-2 later?) could do 26fps decoding 320x240 MPEG. MAX not only improved the performance (finally better than the 68060 at MPEG fps) but improved the code density by replacing many RISC instructions allowing the cache sizes to be reduced tremendously. The PA-RISC 7100LC@80MHz (L1: 128kB ICache/128kB DCache) with MAX SIMD could do 33fps decoding 320x240 MPEG. The Apollo Core 68k@78MHz should be about the same performance, if not a little better, without using an SIMD (the Apollo Core with SIMD is likely twice as fast as the PA-RISC 7100LC@80MHz in MPEG decoded fps). As we can see, the PA-RISC had unimpressive performance even with an SIMD and lots of resources. http://www.ee.princeton.edu/~rblee/H...dMicroproc.pdf There were other 3D graphics chips which went on to use an SIMD processor in a somewhat similar configuration like the Broadcom VideoCore with ARM CPU as used in the Raspberry Pi. High end graphics boards eventually moved on to more specialized parallel processing units but have a logic controller CPU to process the I/O and feed the specialized units. It looks like this configuration allows more parallelization than an SIMD and scales better while the SIMD can be started quicker (less latency), is easier to program (relative as still not easy to program) and can improve code density (which reduces caches needed) if general purpose enough. Could Hombre have saved C= from bankruptcy? Probably not as it was not far enough along in development. It was probably on par with the PS1 but wasn't finished so maybe would have had to compete with the PS2. Would C= have been pursuing the PA-RISC if they know now what the 68k could do as presented here? If they were smart, they would have been looking to license or buy the rights to the 68060 from Motorola (should have been cheap as it was undervalued and discarded for PPC) and perhaps add their own SIMD as it would have saved them the development effort of porting the AmigaOS to PA-RISC and they could have done it as a much prioritized effort to make a single chip Amiga (68k+custom chips) SoC. Then again, knowing C=, they would have probably tried to create a 68030 based SoC instead of 68060 based one as they lacked a tech savvy vision with good leadership. Last edited by matthey; 04 March 2017 at 01:40. |
||||
24 February 2017, 10:19 | #23 | |
Registered User
Join Date: Mar 2009
Location: moon
Posts: 373
|
Quote:
While history has shown that it wasn't necessary to abandon CISC for RISC, I doubt Commodore had the technical resources to develop 68k into something that would remain competetive. They certainly didn't have the money. |
|
24 February 2017, 10:26 | #24 |
Registered User
Join Date: Jan 2010
Location: >
Posts: 2,881
|
I read somewhere a few years ago Hombre was more on par with the Saturn than the PS1, but again people are comparing different markets, the budget computer market was not the console market, 16-computer markets co-existed with 16-bit console markets, and the same could have happened with Hombre/CD64 and PS1/Saturn.
But Commodore even if they survived didn't have the right management to take the Amiga through the 90's anyway. |
24 February 2017, 11:53 | #25 | |
Registered User
Join Date: Mar 2009
Location: moon
Posts: 373
|
Quote:
No doubt about that, but it's interesting to imagine what realistically could have happened with less wonky management. |
|
24 February 2017, 11:59 | #26 |
Registered User
Join Date: Jan 2010
Location: >
Posts: 2,881
|
No but people still wanted a cheap computer that could play games at that time, Pentium PC's were still too expensive, people only jumped to the PS1 in 95/96 when they saw no future with the Amiga brand, if Commodore had a capable 3D machine in 95 i have no doubt it would have sold well in that marketplace.
|
24 February 2017, 19:04 | #27 | |||||||
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Quote:
Quote:
Quote:
Quote:
Quote:
Quote:
Quote:
Last edited by matthey; 24 February 2017 at 19:14. |
|||||||
24 February 2017, 21:17 | #28 |
Registered User
Join Date: Mar 2009
Location: moon
Posts: 373
|
|
24 February 2017, 22:11 | #29 | ||
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Quote:
Quote:
Intel was able to ramp up development using the cash flow provided by the PC economies of scale. They made mistakes (Pentium 4) but trial and error and research with persistence took them to the top. Motorola bet on PPC (68060 was not clocked up or improved as it would have competed with PPC) right as RISC was discovering that clock speeds were not unlimited, all the complexity could not be moved into compilers and code density might be important after all. CISC found ways to improve with different techniques and could use some of the same techniques as RISC. CISC became a lower clocked but more powerful variant of RISC with innate code compression which was more powerful than the original unlimited clock speed super simplified RISC philosophy. Last edited by matthey; 24 February 2017 at 22:18. |
||
25 February 2017, 00:12 | #30 |
Registered User
Join Date: Mar 2009
Location: moon
Posts: 373
|
From what you say, it seems like we agree that Intel had CISC expertise, and not only "at that time" (mid-90s). They wouldn't be able to design or produce their CPUs otherwise.
|
25 February 2017, 02:15 | #31 |
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Intel had knowledge to design and fab chips including CISC processors. C= owned MOS Technologies had knowledge to design and fab chips including CISC processors which was more advanced than that of Intel (MOS 6502 was superior to Intel 8080 and Motorola 6800). Chuck Peddle came from MOS and persuaded Jack Tramiel to make computers and not just calculators. Chuck Peddle worked on the Motorola 6800 which he considered the first microprocessor (not Intel 4004 or 8008 which he considered "calculator chips"). He left Motorola when they were not interested in making a low cost 6800 and created the 6501 and 6502. MOS had 70% fab success rates compared to 70% failure rates which allowed them to bring the cost of the 6502 down to $25 (every chip designer had their own fab at that time). It was so cheap that people thought it was a scam but it was Chuck's vision to mass produce them to be used everywhere. He also went on to develop the first personal computer in the C= PET which beat Apple to market (by 6 months) after deciding not to buy them for $150,000. My point is that C= had more CISC expertise with MOS and Chuck Peddle (he made the microprocessor affordable and created the first personal computer) than Intel did at the time C= bought MOS. Intel was behind MOS, Motorola and TI in their chip technology. Intel was behind at the time the 68000 came out. It was about the time of the 80286 and 80386 that Intel was catching up in technology fast using the cash flow from the PC. It is here where they were learning modern CISC techniques (same as Motorola) like pipelining and caches which did not exist before. Motorola was becoming a CISC expert too (68060) but jumped the fence to what looked like greener pastures with RISC. It is a little confusing depending on which time period is looked at but Intel was far from the leader in microprocessor technology (which was CISC) in the 8 bit era and half way through the 16 bit era. They were playing catch up and were lucky IBM chose an inferior Intel processor for their PC or they may not have even survived. Yes, Intel turned it around and was the world experts in modern CISC by the mid-90s.
|
25 February 2017, 04:09 | #32 |
Registered User
Join Date: Mar 2009
Location: moon
Posts: 373
|
So the question is, did Commodore still have enough technical resources in the mid-90s to purchase 68k from Motorola and keep up with the Pentium? Sounds unlikely to me...
|
25 February 2017, 05:47 | #33 |
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Probably not because of lack of earlier leadership and lack of vision in the top executive positions. C= had legendary employee talent and impressive technology ahead of its time but found a way to squander it. C= did not have the philosophy where they would have even tried to keep up with the Pentium. More likely they would have tried to cost reduce an Amiga SoC and mass produce it for the low end of the market. They were good at cost reducing but did not understand the idea of competing in performance and features. Even with a 68060+AGA SoC for <$100 in the late 90s, would the custom chips have been upgraded or be an even bigger liability than they had become in the mid-90s (no chunky support let alone 3D support)? Would C= have found some way to bottleneck performance with not enough fast memory or lack of HD? I expect the only way C= would have adapted is under different ownership and management.
|
25 February 2017, 07:28 | #34 | |
Unregistered User
Join Date: Nov 2005
Location: Tasmania
Age: 42
Posts: 893
|
No 3D support? Are you sure about that? I'm pretty sure line drawing and flood filling are features of the Agnus chip, which would mean that there IS in fact 3D support features in the Amiga's chipset.
Ok, so it's nowhere near as complex as more modern 3D hardware, and textures are out. But polygons are polygons and 3D is 3D and the Amiga does in fact support this at the hardware level all the way back to the Amiga 1000. Quote:
|
|
25 February 2017, 16:59 | #35 | |||
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Quote:
Quote:
Quote:
|
|||
26 February 2017, 03:02 | #36 | |
Registered User
Join Date: Sep 2007
Location: Stockholm
Posts: 4,332
|
Quote:
You also seem to forget Intel's super-CISCy processor, the iAPX 432. |
|
27 February 2017, 18:38 | #37 |
Posts: n/a
|
Thanks everyone for the replies, I've learnt a lot :-)
|
27 February 2017, 21:20 | #38 | ||
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Quote:
Quote:
Intel learned a lot from trial and error. This iAPX (432) mistake is hardly an example of Intel Expertise with CISC but rather a good example to the contrary. This is the kind of project that could bankrupt a company as it likely cost much more than the 8080 to 8086 upgrade project where they were lucky with IBM choosing the 8088 (8086 variant). IMO, Intel was no expert even up to the Pentium days. They were lucky again that texture mapped "desktop" gaming was pushing PC sales where energy efficiency wasn't important. Let's compare the Pentium and 68060. Pentium@75MHz 80502, 3.3V, 0.6um, 3.2 million transistors, 9.5W max 68060@75MHz 3.3V, 0.6um, 2.5 million transistors, ~5.5W max* * estimate based on 68060@50MHz 3.9W max, 68060@66MHz 4.9W max The 68060 integer performance is known to be a little better at the same clock speed than the Pentium despite more conservative MIPS numbers from Motorola (perhaps due to inferior 68k compilers). The Pentium had higher theoretical FPU performance at the same clock speed despite its inferior FPU stack based ISA because the 68060 did not have a fully pipelined FPU but more common mixed FPU and integer code reduced this Pentium advantage. The 68060 is using ~42% less power to give similar performance with the most comparable chips chosen. Both processors are in order superscalar with only 8kB ICache and 8kB DCache. This is similar to the in order superscalar Intel Atom which Intel was trying to get down to the energy efficiency of ARM and actually did (OoO Cortex A9 while outperforming it) according to this article. https://research.cs.wisc.edu/vertica...-struggles.pdf What if a CPU design based on the 68060 used 42% less power than the Atom processor that beat the very common ARM Cortex A9? What if Motorola abandoned and sabotaged (by anti-marketing and not clocking up) the 68060 without recognizing its full potential? What if ARMv8 is making a mistake for embedded and mobile by going bigger when it is unnecessary and smaller is faster? P.S. I wanted to compare the PPC 601@75MHz 3.3V, 0.6um, 2.8 million transistors but could no longer find power dissipation numbers. The PPC 601 was considerably slower at the same clock speed than the 68060 and Pentium despite having twice the caches (32kB unified L1). The shallow pipeline OoO PPC is generally power efficient and the base CPU is small in transistor count but this advantage is lost with larger caches and memory power requirements and transistor counts necessary to add performance. IBM created the PPC 405GP embedded CPU with CodePack code compression but this style of code compression still requires a large L1 ICache which CISC innate compression does not. Last edited by matthey; 27 February 2017 at 21:27. |
||
27 February 2017, 22:32 | #39 | |
Registered User
Join Date: May 2016
Location: Philadelphia, USA
Posts: 67
|
Quote:
As for TDP/power consumption - somewhat meaningless in this case -- the Pentium was a more aggressive design with more transistors intended for higher performance. Keep in mind Intel also had the Pentium Pro released on November 1995, which was leaps and bounds ahead of the 68060 and early PPCs.. IMO Motorola's biggest problem was itself -- it kept pricing the 68000, and 68020/030 at exorbitant prices, didn't sell high clock speed versions of the 68K or '020 because of worry it would compete with the '030 (i.e. later 68K and 020's had a LOT of margin left in them), which in the case of our dear Amiga prevented lower end increments from improving enough to stay relevant. (An A500+/A600 with a 68020@ 25 mhz, and an A1200 with a 68030 @ 32mhz certainly wouldn't have hurt market share). The 68000 was already 6 years old by the time the A1000 launched... The Amiga had epic engineering going for it, but EVERYTHING else going against it.. . |
|
27 February 2017, 23:05 | #40 | |||
Banned
Join Date: Jan 2010
Location: Kansas
Posts: 1,284
|
Quote:
Quote:
Quote:
I agree. The biggest factor was the economies of scale from the PC boom and then 3D gaming boom putting huge cash flows in the Intel sales and wiping out their past mistakes. The RISC hype was at full steam which sold CPUs for high end computers while the 68060 did not get much attention. The 68060 was an excellent design and better suited for embedded, laptop and mid-range desktop use than either the Pentium or RISC. Sadly, the 68060 was a successful design which was mis-managed (ironically by Motorola which lived on embedded sales) and mis-marketed (practically anti-marketed by Motorola). |
|||
Currently Active Users Viewing This Thread: 1 (0 members and 1 guests) | |
Thread Tools | |
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
"Voices8" 8 Channel Soundtracker "DemoSongI" song - "This is the Amiga with 8 Voices" | DemosongIHunter | request.Music | 45 | 23 May 2022 20:07 |
General "Chunky to Planar" via "AKIKO" on AMIGA CD32 ? | Nibbler | support.Other | 14 | 12 December 2015 16:17 |
"Lincs Amiga User Group aka "LAG" Meeting Confirmed for Sat 2nd of March" | rockape | News | 2 | 21 February 2013 22:46 |
"Reminder "Lincs Amiga User Group aka "LAG" Meet Sat 5th of January 2013" | rockape | News | 4 | 30 January 2013 00:06 |
"Lincs Amiga User Group aka "LAG" meet confirmed on Saturday the 5th of January 2013" | rockape | News | 2 | 06 November 2012 20:16 |
|
|