几个硬件问题，大家快来帮忙看看
- 主题发起人 陪你去看龙卷风
- 开始时间
泛蓝
新手上路
- 注册
- 2003-04-15
- 消息
- 2,560
- 荣誉分数
- 1
- 声望点数
- 0
AMD 939pin Athlon 64处理器释疑
根据Theinquire的报道，AMD计算机产品部门技术市场经理Mike Goddard在Athlon 64发布会后的技术座谈会上表示，AMD之所以会推出939pin的Athlon 64处理器，原因在于940pin Athlon 64处理器要求主机板厂商采用6-9层PCB来生产配套的主机板产品，而939pin Athlon 64处理器的配套主机板只需要4层PCB即可，让主机板厂商的生产成本得以降低，并且939pinAthlon 64处理器，支持普通的DDR内存，940pin的Athlon 64处理器必须采用 ECC Registerd DDR内存。
根据Theinquire的报道，AMD计算机产品部门技术市场经理Mike Goddard在Athlon 64发布会后的技术座谈会上表示，AMD之所以会推出939pin的Athlon 64处理器，原因在于940pin Athlon 64处理器要求主机板厂商采用6-9层PCB来生产配套的主机板产品，而939pin Athlon 64处理器的配套主机板只需要4层PCB即可，让主机板厂商的生产成本得以降低，并且939pinAthlon 64处理器，支持普通的DDR内存，940pin的Athlon 64处理器必须采用 ECC Registerd DDR内存。
泛蓝
新手上路
- 注册
- 2003-04-15
- 消息
- 2,560
- 荣誉分数
- 1
- 声望点数
- 0
PCI Express means death of AGP standard
Intel Developer Forum All change, here comes a new gravy train
By Mike Magee in San Jose: 星期四 20 二月 2003, 00:28
A PANEL OF Intel specialists working on the PC Express specifications confirmed today that when products are released it means the death of the AGPx spec, with rev eight being the last.
While PCI Express means X16 next generation graphics delivering 4GBs per second per direction, that may mean that when Nvidia releases its PCI Express card, you'll have to buy a whole new PC to plug it into.
PCI Express products are due to ship in the second half of next year, with other radical changes happening in the notebook and server segments too. The specs are far advanced and Microsoft is very likely to take full advantage of some of its new futures, probably with Longhorn.
Bala Cadambi, who heads up the PCI Express initiative, said that the new specification will run fine with existing BIOSes and drivers, and software, but it has "a lot of features software can take advantage of".
Those include isochronous support for streaming media for TV tuners, for graphics and for cameras.
The first release of products also means an X or greater IO performance for Gigabit Ethernet, and 1394, with 250MBs per second per direction.
The notebook PC will see the death of the old PCMCIA form factor, with new cards, codenamed oddly enough Newcards, taking their place. Two Newcards will fit in the space of one Cardbus card, and they'll be able to use PCI Express or USB 2.0.
The advantages of the new form factor will include low wattage, a small footprint, and they'll support comms, storage, and IO migration.
On the server front, PCI Express will let adaptors connect directly to the MCH without a bridge, offering lower latency, lower cost, and fewer pins. Bandwidth will kick off at 10Gb from launch day, while in the future vendors will offer server modules which allow additional connectivity to be installed much like "inserting a cartridge into a VCR".
Intel itself will have two chipsets supporting Enterprise PCI Express ? Lindenhurst and Twin Castle.
Intel Developer Forum All change, here comes a new gravy train
By Mike Magee in San Jose: 星期四 20 二月 2003, 00:28
A PANEL OF Intel specialists working on the PC Express specifications confirmed today that when products are released it means the death of the AGPx spec, with rev eight being the last.
While PCI Express means X16 next generation graphics delivering 4GBs per second per direction, that may mean that when Nvidia releases its PCI Express card, you'll have to buy a whole new PC to plug it into.
PCI Express products are due to ship in the second half of next year, with other radical changes happening in the notebook and server segments too. The specs are far advanced and Microsoft is very likely to take full advantage of some of its new futures, probably with Longhorn.
Bala Cadambi, who heads up the PCI Express initiative, said that the new specification will run fine with existing BIOSes and drivers, and software, but it has "a lot of features software can take advantage of".
Those include isochronous support for streaming media for TV tuners, for graphics and for cameras.
The first release of products also means an X or greater IO performance for Gigabit Ethernet, and 1394, with 250MBs per second per direction.
The notebook PC will see the death of the old PCMCIA form factor, with new cards, codenamed oddly enough Newcards, taking their place. Two Newcards will fit in the space of one Cardbus card, and they'll be able to use PCI Express or USB 2.0.
The advantages of the new form factor will include low wattage, a small footprint, and they'll support comms, storage, and IO migration.
On the server front, PCI Express will let adaptors connect directly to the MCH without a bridge, offering lower latency, lower cost, and fewer pins. Bandwidth will kick off at 10Gb from launch day, while in the future vendors will offer server modules which allow additional connectivity to be installed much like "inserting a cartridge into a VCR".
Intel itself will have two chipsets supporting Enterprise PCI Express ? Lindenhurst and Twin Castle.
泛蓝
新手上路
- 注册
- 2003-04-15
- 消息
- 2,560
- 荣誉分数
- 1
- 声望点数
- 0
My 400 MHz beats your 400 MHz
Well, in the DDR2 price, higher price does buy you higher latency, therefore, in theory, lower performance! The best DDR2-400 DIMMs available initially can only provide 3-3-3 basic latency figures, compared to 2-2-2 for the top DDR-400 DIMMs. Why is that so? Before looking at the actual DIMMs in actual DDR2 systems, two possibilities come to mind. First, the DDR2 memory uses 4-bit prefetch, i.e. every 4 bits from a memory array that actually runs at 100 MHz are channeled, or multiplexed, to one bit on the external memory data bus, which effectively runs at 400 MHz (200 MHz x 2). In DDR2, with 2-bit prefetch, every 4 bits from a memory array that actually runs faster, at 200 MHz, are multiplexed to one bit on the external 400 MHz memory data bus. So, yes, if current DDR400 DIMMs used 4-bit prefetch instead, their data rate could support a DDR2-800 speed!
And vice versa, a slower internal memory array will definitely add to the both read and write latency. But why is the memory array slower? Well, if using the same process, a lower 1.8 v voltage surely won't help increase the speed - overclockers know jolly well that, to increase speed, voltage needs to go up, not down. Stepping down from 2.5 v in DDR to 1.8 v in DDR2 does reduce power and heat, and improve reliability, however it also reduces the speed (inclusive latency) of the memory array - so 4-bit prefetch was needed to even get DDR2-400 data rates, not to mention future DDR2-533 etc.
From www.theiquire.net
Well, in the DDR2 price, higher price does buy you higher latency, therefore, in theory, lower performance! The best DDR2-400 DIMMs available initially can only provide 3-3-3 basic latency figures, compared to 2-2-2 for the top DDR-400 DIMMs. Why is that so? Before looking at the actual DIMMs in actual DDR2 systems, two possibilities come to mind. First, the DDR2 memory uses 4-bit prefetch, i.e. every 4 bits from a memory array that actually runs at 100 MHz are channeled, or multiplexed, to one bit on the external memory data bus, which effectively runs at 400 MHz (200 MHz x 2). In DDR2, with 2-bit prefetch, every 4 bits from a memory array that actually runs faster, at 200 MHz, are multiplexed to one bit on the external 400 MHz memory data bus. So, yes, if current DDR400 DIMMs used 4-bit prefetch instead, their data rate could support a DDR2-800 speed!
And vice versa, a slower internal memory array will definitely add to the both read and write latency. But why is the memory array slower? Well, if using the same process, a lower 1.8 v voltage surely won't help increase the speed - overclockers know jolly well that, to increase speed, voltage needs to go up, not down. Stepping down from 2.5 v in DDR to 1.8 v in DDR2 does reduce power and heat, and improve reliability, however it also reduces the speed (inclusive latency) of the memory array - so 4-bit prefetch was needed to even get DDR2-400 data rates, not to mention future DDR2-533 etc.
From www.theiquire.net
