[…] //www.morningcaffee.com/article/a-history-of-early-microcontrollers-part-1-calculator-chips-came-f&#8230;[& # 8230;] < / p > //www.morningcaffee.com/article/a-history-of-early-microcontrollers-part-9-the-general-instruments-pic1650/#comment-82799 traneusee 2023年1月7日星期六00:49:07 +0000 //www.morningcaffee.com/?post_type=article&p=98432#comment-82799 In reply to <a href="//www.morningcaffee.com/article/a-history-of-early-microcontrollers-part-9-the-general-instruments-pic1650/#comment-82795">Brane212</a>. I have only written the one small 16F84 program I discussed above, where speed was not critical. The 16F84 instruction set, as published by Microchip, has conditional skips but not conditional branches. The Parallax assembler I used, does have conditional branches, synthesized from conditional skips and gotos by the assembler. I mostly used conditional branches, and a few times used conditional skips.

在回复Brane212.

我只写了我上面讨论的一个小16F84程序，其中速度不是关键。由Microchip公司发布的16F84指令集有条件跳过，但没有条件分支。我使用的视差汇编器确实有条件分支，由汇编器从条件跳过和goto合成。我主要使用条件分支，有几次使用条件跳过 //www.morningcaffee.com/article/developing-the-worlds-first-commercially-available-rf-device-with-an-open-source-chip/#comment-82797 马克斯Maxfield Thu, 05 Jan 2023 21:28:14 +0000 //www.morningcaffee.com/?post_type=article&p=98755#comment-82797 In reply to <a href="//www.morningcaffee.com/article/developing-the-worlds-first-commercially-available-rf-device-with-an-open-source-chip/#comment-82796">pdillien</a>. Hi Paul -- it's great to hear from you as always -- you make a good point about the hardware from Lime Microsystems being open-source (and they really do have some awesome products) -- but, like you, I'm guessing they used commercial tools to design their devices.

在回复pdillien.

Hi Paul —It& #8217;s很高兴收到你的来信—你说的很好，Lime Microsystems的硬件是开源的(他们确实有一些很棒的产品)—但是，像你一样，我猜他们使用商业工具来设计他们的设备 //www.morningcaffee.com/article/developing-the-worlds-first-commercially-available-rf-device-with-an-open-source-chip/#comment-82796 pdillien 周四，2023年1月5日21:16:13 +0000 //www.morningcaffee.com/?post_type=article&p=98755#comment-82796 Hi Max Some while ago, I did some work for a UK company that has been producing open source RF chips since 2009. It was the world's first company to integrate a full SDR and is called Lime Microsystems (https://limemicro.com/). They offer both the devices and SDR boards for sale. These are actually highly capable devices and boards, and being open source hardware allow those clever RF gurus to use them in all sorts of amazing ways. However, I don't know for certain, but I guess Lime used commercial tools for the chip design rather than open source design tools. There is a range of SDR boards starting at $159 (https://www.crowdsupply.com/lime-micro/limesdr-mini#products) ranging up to a full software-enabled network-in-a-box based on LimeSDR that forms an open source small cell.

Hi Max
Some while ago, I did some work for a UK company that has been producing open source RF chips since 2009. It was the world’s first company to integrate a full SDR and is called Lime Microsystems (https://limemicro.com/). They offer both the devices and SDR boards for sale. These are actually highly capable devices and boards, and being open source hardware allow those clever RF gurus to use them in all sorts of amazing ways. However, I don’t know for certain, but I guess Lime used commercial tools for the chip design rather than open source design tools.

There is a range of SDR boards starting at $159 (https://www.crowdsupply.com/lime-micro/limesdr-mini#products) ranging up to a full software-enabled network-in-a-box based on LimeSDR that forms an open source small cell.

在回复traneusee.

你显然没有用它做过复杂的代码，那是为了运行得快。没有条件分支，只有条件指令跳过。
执行必须快速运行的条件循环，依赖于多个条件会变得非常快 //www.morningcaffee.com/article/a-history-of-early-microcontrollers-part-9-the-general-instruments-pic1650/#comment-82794 Brane212 周四，2023年1月05日07:57:12 +0000 //www.morningcaffee.com/?post_type=article&p=98432#comment-82794 In reply to <a href="//www.morningcaffee.com/article/a-history-of-early-microcontrollers-part-9-the-general-instruments-pic1650/#comment-82788">Max Maxfield</a>. I don't have a problem with writing tight asm code, but PIC is truly moronic on many aspects, even latest PIC16 generation. Just one example - shadowed index registers. One would expect that there are two set of registers, which interchange their position, so that one set is useable as INDX,INDY in interrupt, while their inactive aprt is accessible somewhere high in FSR map ( say IND_SAVEDX, IND_SAVEDY). Doing it that way would be reasonable. Slim implementation ( nos special HW resources needed) which would bring also simple, fast transition ton interrupt and back - no need to care about index registers. One would only have to set IND_SAVEDX/Y once during the chip powerup/initialization. MC ofcourse used most moronic way possible - core actually copies INDX/Y into IND_SAVEDX/Y at each interrupt and vice versa at the return. This not only needs some time or extra data paths for data transfer, it only means that if one want to use INDX/Y registers during the interrupt, one has to set them DURING EACH INTERRUPT. Keep in mind, this is late PIC16 core, after bazzilion iterations.

在回复Max Maxfield。我写紧凑的asm代码没有问题，但PIC在许多方面确实是低能的，甚至是最新的PIC16一代。只有一个例子–阴影索引寄存器。人们会期望有两组寄存器，它们交换了它们的位置，因此一组寄存器可用作中断中的INDX,INDY，而它们的非活动部分可在FSR映射的高位置访问(例如IND_SAVEDX, IND_SAVEDY)。那样做是合理的。薄的实现(不需要特殊的HW资源)，这也将带来简单，快速的转换中断和返回–不需要关心索引寄存器。
在芯片上电/初始化时，只需要设置一次IND_SAVEDX/Y。

MC当然用了最低能的方式–实际上，core在每次中断时都将INDX/Y复制到IND_SAVEDX/Y中，反之亦然。这不仅需要一些时间或额外的数据路径来进行数据传输，这只意味着如果想在中断期间使用INDX/Y寄存器，就必须在每次中断期间设置它们。请记住，这是PIC16的后期核心，经过了大量的迭代 //www.morningcaffee.com/article/does-224-microchip-announces-polarfire-2-you-do-the-math/#comment-82793 Brane212 2023年1月5日星期四06:01:27 +0000 //www.morningcaffee.com/?post_type=article&p=98676#comment-82793 BTW, why do all of FPGA manufacturers chomp process advances as their own doing ? They are to to get into more advanced manufacturing process, which brings certain speed/power advacnes by default. So, why do all of these guys go into great length to show the speedups/powerdowns taht follow natively from a process change ? This would be easier to swallow if they simply stated what did they managed to achieve above the expected improvement from newer process alone... BTW，为什么所有的FPGA制造商都把工艺进步作为自己的事情?他们是为了进入更先进的制造工艺，这在默认情况下带来了一定的速度/功率进步。那么，为什么所有这些家伙都花了很大的篇幅来显示流程更改本身带来的加速/功率下降?

此外，你没有关于Polarfire’s真正的问题–破烂的补丁工具，昂贵的价格和陈旧的SERDES。他们可以做12 Gbps，但只有PCIev2。在PCIE5发布的时候，花这么多美元购买芯片，只是为了通过PCIev2连接到PC上，这似乎是亵渎神明，并将其锁定在如此多的用途之外。

Some time ago someone asked them on forums why can’t they do multispeed SERDES lanes, so that one could have either, for example one (up to) PCIev5 lane, another that could to PCIev4, anotzher two that could do PCIev3 etc.

This way, one could use modern, fast PCIe versions ( even if narrow) without overloading internal routing or braching the cost ceiling (only one lane is really fast).

MC answered that something like that is in the plans.

在回复Max Maxfield。

听起来你在那儿写了篇文章，Max.