The tour traces the Polish Odra computer series built by Elwro in Wrocław, from valve-and-transistor prototypes to TTL-based third-generation machines.
Odra 1002 used 36-bit words, drum storage with 4,096 words, valve modules, and transistor modules connected by shielded coaxial cables.
Later transistor models improved steadily: Odra 1003 reached 500 additions per second, Odra 1103 5,000, and Odra 1204 60,000.
Odra 1304 became software-compatible with the British ICL1904, while Odra 1305 and 1325 adopted TTL integrated circuits and raised production above 1,000 machines.
The piece notes missing circuit diagrams, asks for corrections, and laments that Poland later lost continuity in large-scale computer production.
Models such as the PRS4a were also produced, initially with ferrite memory. I can’t remember the manufacturer, but I think it was EMAG.
They were most commonly used in mines. Using various types of software and sensors, they monitored environmental conditions in the mines. Methane monitoring, seismology, seismoacoustics, the HADES system.
ADVERTISEMENT
Commodore’s bankruptcy blamed on outdated management and 68k CPUs
Both Atari and Commodore later capitalised on this, but they too soon went bankrupt, unable to compete with the increasingly cheap PC clones from Asia.
Commodore, in particular, went bankrupt due to an anachronistic management model.
For example, they had an order for 10,000 Commodore PCs, but a manager rejected it, claiming that the PC would never catch on, and all transactions above a certain threshold had to be personally signed by Tramiel himself. Moreover, in the 1990s, PCs embarked on a frenzied race for megahertz, as Intel released a processor every two years offering ever-higher megahertz speeds; and thanks to licensing agreements, 386 and 486-class processors were manufactured by leading firms such as Texas Instruments, AMD and Ciryx, whilst Commodore and Atari clung desperately to Motorola’s 68k series processors, which were already seriously outdated by 1992. And if only Commodore had switched to Intel processors and implemented the AAA chipset (commonly known as Super AGA or SAGA) in the Amigas with a resolution of 1280x1024 at a refresh rate of 72Hz, and Hombre with a resolution of 1280x1024 – which in 1993 would have been impressive – all on a single graphics chip - PCs required two graphics cards capable of working in tandem. https://en.wikipedia.org/wiki/Advanced_Amiga_Architecture_chipset https://en.wikipedia.org/wiki/Amiga_Hombre_chipset They wouldn’t have gone bankrupt, and Amigas would still be sold under the Commodore brand.
>>21928597 A company like Optimus paid its taxes, provided jobs and guaranteed that if a customer came back with a complaint after a few months, they couldn’t just say – like some backstreet assemblers – ‘Oh, come off it, sir, I’m selling veg at the moment because it’s the season’, but if you need a new computer for Christmas, just give me a ring, pay a deposit, and I’ll knock something together for half the price of Adax’s, just no invoices >>21928661 I don’t want to go on about this, because you could write a book on the subject, and this is, after all, a piece about the Oder In any case, I personally don’t see any major marketing mistakes in Commodore’s actions. Commodore’s problem was that they didn’t understand the needs of customers requiring professional computers.
Admittedly, as early as 1977 they wanted to build such a computer, but it turned out to be a disaster, so they turned to producing toys – much like Atari, in fact.
And they were actually doing quite well at it, for a while.
So in 1981, when IBM realised that the Apple II – which had become the cornerstone of the computer revolution, finding its way not only to ordinary people but also to the US Army, the CIA, the FBI, NASA, and even as equipment for the space shuttle, and shortly afterwards the LISA appeared (NASA was its biggest customer). Furthermore, the Apple II was probably the most frequently pirated system in the history of computing. The LISA posed a threat to the mainframe computer market, where Intel, IBM and Motorola held an unchallenged monopoly.
For IBM, this was a terrible blow to its image, especially as even the new President Reagan preferred to be photographed with two ‘hippies’ rather than with anyone from IBM, a company disliked by Americans IBM decided to salvage what was left and destroy Apple through Asian partners. In this situation, Commodore, Atari and many other manufacturers had no place in the professional computer market and had to carve out a niche amongst the toys in the games market.
As for later decisions, I’m not sure whether adding an Intel processor to the Amiga in the mid-1990s would have made any difference.
The Amiga was a toy, and 99.99 per cent of its users couldn’t care less whether it was an Amiga or a Sony PlayStation – all that mattered was that they could play Quake, and they were about as interested in the Amiga’s other ‘capabilities’ as they were in last year’s snow )
So IBM was a charitable organisation and all it wanted was to give people a cheap computer
In that case, why did it sell its computers at such high prices, much higher than other American manufacturers?
a. They were better for business; businesses don’t buy things just because they’re cheaper… The PC running OS/2 was meant to fulfil a specific role within the IBM ecosystem; the fact that Microsoft did what IBM did is another story altogether. Back then, IBM was IBM – as much of a standard for corporations as tap water or electricity from the mains. b. In my view, IBM lacked a visionary on a par with Dolby, who would have sold licences, say, for $1 each.
c. IBM did not patent the PC, nor did it, until a certain point, patent mainframes or operating systems. Today, that’s a completely different story.
Added after 9 [minutes]:
gregor124 wrote:
And what happened to IBM? The first legal clone was produced in 1982; as late as 1985, IBM still employed 450,000 staff and was consistently making losses, by 1992, IBM’s workforce had shrunk to around 100,000 employees, and even massive reforms and restructuring failed to help, until finally, in 2004, it sold the remnants of its PC business to the Chinese.
Over time, it sold more, much more, and this process continues. Some might say this is a sign of weakness; others – a manifestation of adaptation and transformation. In my view, up to a certain point, IBM’s strength lay in the fact that they killed off – literally killed off – their excellent products with completely new ones, which were not mere improvements but entirely different solutions. Today, many people wonder, before making a decision, why they should pay more for the same thing. But IBM is no exception; look at the other giants of that era – HP, Sun, Oracle, ....
I’ve just been asked about the Odra in connection with this article, specifically regarding the arithmetic units in older Odra models and computers from that period in general. It turns out that serial arithmetic units were used to save on the number of transistors required. These involved single-bit operations combined with shifting the contents of registers. Such operations were slower, but the hardware was less complex. Also, for example, whilst the K-202 performed a million operations per second, it took many cycles for the arithmetic unit to complete its calculations.
Let’s see what elektrodabot knows about its predecessors
@ElektrodaBot how did serial arithmetic units work in the Odra series of computers, for example in the Odra 1305? How many cycles of the arithmetic unit were required to perform addition and multiplication in both fixed-point and floating-point versions? Were there any special versions of the arithmetic units with increased precision? If the KAR-65 computer performed 100,000 floating-point operations per second, what must the internal clock speed of the arithmetic unit have been?
I’ve just been approached regarding the Odra in connection with this material, specifically concerning the Odra arithmometer and computers from that period in general. It turns out that in order to save the required number of transistors...
Direct reply
We need to distinguish between two things here:
1. Serial arithmometers were indeed a natural solution in older machines, especially those with drum memory and shift registers , for example in the Odra 1003/1013 class. 2. The Odra 1305 was no longer a typical machine with a serial arithmetic unit . The Odra 1305 catalogue documentation specifies its operating mode as parallel, asynchronous , a 24-bit word + check bit , TTL technology and operation times: fixed-point addition 2.1 µs , fixed-point multiplication 10 µs , floating-point addition 18 µs , floating-point multiplication 29 µs . In OCR scans, the character ‘µ’ is sometimes mistakenly recognised as ‘p’, but from the context it is clear that these are microseconds. ( historiainformatyki.pl )
In other words: if we are asking about pure serial arithmetic units, then we are likely referring to earlier Odra models; if we’re asking about the Odra 1305, we should be talking about the execution time of an instruction/microprogramme, rather than a simple calculation: 1 bit = 1 cycle.
How a serial arithmetic unit worked
The serial arithmetic unit did what every pupil does today ‘on the back of a piece of paper’, only in the binary system:
- the operands were stored in shift registers, - in a single clock cycle, one bit from the first argument and one bit from the second argument, - the one-bit adder calculated the result bit and the carry, - the carry was stored in a latch and used in the next clock cycle, - after each step, the registers shifted their contents.
Schematically:
Code: text
Log in, to see the code
For an
N
-bit word:
- fixed-point addition requires at least
N
bit steps, - multiplication using the ‘shift and add’ method requires approximately
N × N
bit steps, - floating-point arithmetic adds mantissa alignment, operations on exponents, normalisation and rounding.
In Odra 1003, Kamburelis’s article describes a design featuring an arithmetic unit containing registers A, B1...B7 and the S , in which arithmetic and logical operations were performed; the memory was drum-based and had 8192 cells , and the machine word had 39 bit positions . ( pldml.icm.edu.pl )
How many cycles in a serial arithmetic unit
For a classic serial machine with a word length of
N
:
Operation
Minimum number of bit steps
For a 39-bit word, such as the Odra 1003
Fixed-point addition
N
approximately 39
Fixed-point subtraction
N
approximately 39
Fixed-point multiplication using the shift-and-add method
N²
approximately 1521
Fixed-point division using the shift-and-subtract method
N²
approximately 1500–1600
Floating-point addition
data-dependent; several passes through the mantissa
usually several dozen to several hundred steps
Floating-point multiplication
mantissa multiplication + operations on exponents + normalisation
order 1500–2000+ steps
These are the figures for a pure serial arithmetic unit , excluding instruction fetch, memory access, result write, exception handling, etc.
And what about the Odra 1305?
The Odra 1305 was a different class of design altogether. The documentation explicitly mentions parallel, asynchronous , the word 24 bits + 1 check bit , ferrite memory with a cycle time of 1.2 µs and an access time of 0.4 µs . It also states that the unit had hardware general-purpose and floating-point registers. ( historiainformatyki.pl )
For the Odra 1305, it is better to specify instruction times:
If anyone absolutely wants to convert this into ‘memory cycles’ of 1.2 µs each, the approximate result is:
Operation
Time
Memory cycle equivalent: 1.2 µs
Fixed-point addition
2.1 µs
approx. 1.75 memory cycles
Fixed-point multiplication
10.0 µs
approx. 8.3 memory cycles
Floating-point addition
18.0 µs
approx. 15 memory cycles
Floating-point multiplication
29.0 µs
approx. 24 memory cycles
But this is merely an auxiliary calculation. In an asynchronous machine, there is no single simple ‘arithmetic clock’ as we understand it today.
Fixed-point and floating-point arithmetic
In machines with a serial arithmetic unit, the difference between fixed-point and floating-point arithmetic was enormous.
Fixed-point
Addition:
Code: text
Log in, to see the code
In a serial arithmetical unit:
1. clearing the carry, 2. shifting bits from least significant to most significant, 3. sum of bits + carry, 4. storing the result, 5. overflow check.
For 39 bits: approximately 39 bit steps .
Multiplication:
Code: text
Log in, to see the code
Most commonly:
1. check the multiplier bit, 2. conditionally add the multiplier to the partial accumulator, 3. shift, 4. repeat for the next bit.
For 39 bits: approximately 39 × 39 = 1521 bit steps, plus a control overhead.
Floating-point
Floating-point addition is not simply the addition of mantissas. A typical sequence:
1. comparison of exponents, 2. shifting the mantissa of the number with the smaller exponent, 3. addition or subtraction of the mantissas, 4. normalisation of the result, 5. correction of the exponent, 6. rounding, 7. overflow/underflow check.
Therefore, floating-point addition can take many times longer than fixed-point addition.
The dominant cost is the multiplication of mantissas, which, for a serial arithmetic unit, is again of the order of
N²
.
Were there versions with increased precision?
Yes, but usually not in the sense of a ‘second, special arithmetic unit’, but rather in the sense of longer registers, word pairs or double-length modes .
The Odra 1003 specification describes, amongst other things:
- the accumulator register A : 39 bits, - multiplier register M/B7 : 39 bits, - long register AM , composed of 39 bits from register A and 38 bits from register M.
This provides a path for long operations, which are particularly necessary for double-length multiplication, division and shifts. ( pldml.icm.edu.pl )
The ICL 1900-compatible architecture, on which the Odra 1300 series was based, also featured double-precision operations and a floating-point accumulator. The ICL instruction sheet lists, amongst other things, the floating-point instructions FLOAT, FIX, FAD, FSB, FMPY and the notation
KAR-65 and the question of the arithmetic unit clock
The answer here is a little tricky: The KAR-65 did not need to have an arithmetic unit clock, as it was an asynchronous machine .
Sources on high-energy physics state that the KAR-65 operated at a speed of approximately 100,000 operations per second and used 26-bit words . ( fuw.edu.pl ) Other descriptions of Karpiński’s design explicitly indicate that it was an asynchronous computer, without a conventional clock. ( eksperymentmyslowy.pl )
However, if we consider this purely hypothetically:
Code: text
Log in, to see the code
For a 26-bit serial arithmetic unit, the absolute minimum for a single pass through a word would be:
Code: text
Log in, to see the code
But this applies only to a single simple ‘mantissa pass’ operation. For floating-point arithmetic:
- addition requires several such passes, - serial mantissa multiplication would require approximately
26 × 26 = 676
bit steps.
If a full floating-point multiplication were to be performed in 10 µs by a purely serial arithmetic unit, the required bit clock would be of the order of:
Code: text
Log in, to see the code
This is unthinkable for a machine built from the germanium transistors and diodes available at the time. Conclusion: The KAR-65 could not have achieved the claimed 100,000 operations per second as a simple, bit-serial arithmetics unit performing full floating-point multiplication using the school method in every instruction. It must have used a different architecture: asynchronous, optimised, partially parallel or specialised for the actual computational profile.
Summary
Key points:
- Serial arithmetic unit saved on components: a single one-bit adder instead of a full parallel adder. - The price of simplicity: addition takes
N
steps, multiplication takes approximately
N²
steps. - Early Odra machines , e.g. the Odra 1003, with drum memory and a 39-bit word, fit this philosophy well. - The Odra 1305 should not be lumped into the same category : the documentation specifies parallel and asynchronous operation, as well as predefined operation times. - Increased precision was achieved through long registers, word pairs and double-length modes, and not necessarily through a separate ‘high-precision arithmetic unit’. - The KAR-65 did not have a conventional clock , so the question of its frequency must be treated as a hypothetical calculation. A performance of 100,000 operations per second implies 10 µs per operation, but it is not possible to fairly deduce a single arithmometer clock frequency from this.
You can call me in any topic by writing @ElektrodaBot. Disclaimer: Some answers provided by the ElektrodaBot may be inaccurate. Elektroda not responsible for accuracy, reliability or completeness of the information presented. All ElektrodaBot responses should be verified by the user. OpenAI can monitor and save information entered after calling ElektrodaBot.
Odra 1305 credited with F-117 shootdown calculation
A little-known feat of the Odra 1305, in its military RONAD 25 variant, was the shooting down of an American F-117 stealth aircraft over Serbia in the 1990s – the valve-based radar (reportedly dating back to the Second World War) picked up a faint echo, and the Odra calculated all the ballistic parameters needed to shoot it down in 7 seconds. I once heard that the Odra 1305s were designed for 300 years of continuous, fault-free operation.
Questioning how original Odra computer designs were
So, reading up on the history of Odra computers and bearing in mind the considerable complexity of these devices’ circuitry, I wonder how much of the design was the work of Polish engineers and how much was simply copied from ready-made solutions that had already been devised. Were the individual components of the computer a completely innovative design, or were they modelled on Western designs, including American ones?
If these were our own original solutions, then I really do have great respect for the Polish designers of that era. I get the impression that, with the benefit of hindsight, we’ve actually taken a step backwards in terms of development, even though we have far better computers and tools at our fingertips. Nowadays, many things are designed and programmed on a ‘copy-and-paste’ basis; there are few truly innovative solutions.
I’ve also touched on the subject of Polish measuring equipment in another thread before. It was what it was, but there was quite a lot of it – oscilloscopes, digital multimeters, meters and many, many others. A great many models were produced for those times. Or perhaps it was precisely those times that called for self-sufficiency and the considerable design ingenuity that went with it.
It was probably much the same with the Odra and Mera computers; you had to manage on your own somehow. And once that necessity and motivation had gone, the Polish electronics and IT industry collapsed. There was also no ambition to produce anything of their own for export. And even if there had been, Western competition actively helped to put a stop to it.
In the case of the Odra 1305, there was no original design; they simply imported ICL parts from England and cobbled them together with AVT components. Although the initial plan was to acquire a computer from IBM, our delegation was, as the saying goes, literally kicked out of the IBM building by security because IBM stated that it would not do business with communists – fearing sanctions from Washington – so our people went to ICL, where there was vodka, coffee, tea, and the English sold our delegation an ICL computer complete with an operating system, confident that the Poles wouldn’t be able to assemble it or get it up and running – imagine their surprise when they found out we’d managed to do just that. Our mathematicians would have needed ten years to write a new operating system from scratch, so it was decided to use foreign currency to purchase a computer with an operating system from the West and import it in parts.
The mobile military version of the Odra was Rodan . Looking at how the capabilities of successive generations of the Odra increased – with changes to word length, the addition of new components (main memory) and advances in technology (vacuum tubes, transistors, TTL circuits), it is hard to come away with any impression other than that of visible work on the development of this series of computers. Table 1 contains a summary of the specifications for successive Odra computer models: https://aresluna.org/attached/computerhistory/articles/odra
From what I understand about the ICLs, the Odra 1304 was designed to be compatible with ICL instructions; as a result, the computer was not only compatible with the instruction set but executed them faster than the ICL1904. However, what was actually acquired was software that was available on the ICL1904, and the Odra was capable of running that software.
As far as I’m aware, Optimus used to avoid paying taxes.
I don’t mean to offend you, but unfortunately I have to write this to clarify matters for people who aren’t necessarily familiar with this case and might mistakenly assume that, mate, you’re telling the truth.
As far as I’m aware, you unfortunately have little knowledge of the Optimus case and, worse still, you’re misleading others by slandering the company and its owner:
“In 2006, the Ministry of Finance published the ‘White Paper on JTT Computer and Optimus SA’, explaining – from the perspective of the public administration – the affairs of both companies[23]. According to the authors of the ‘White Paper’, the main source of the problems lay in contradictions within the provisions exempting the import of educational aids from VAT, which were passed by the Sejm in 1993 and not subsequently repealed despite the reasons for their introduction having ceased to exist (responsibility for the quality of tax legislation cannot be placed solely on the Ministry of Finance). According to the Ministry of Finance, the actions of the tax authorities were in accordance with procedures, whilst the interpretation of the defendants’ actions and the application of the legally controversial so-called ‘tax avoidance clause’ were in the interests of the State Treasury, even if the Supreme Administrative Court (NSA) did not subsequently share this view. The authors of the ‘Book’, however, admitted that the position adopted by the tax inspection authorities in both of the above cases was erroneous and noted worrying information suggesting a political and corrupt background to Roman Kluska’s case. They also highlighted a number of problems within the public administration which led to such a drastic turn of events in both cases:
the lack of transparency in the tax authorities’ actions – the excessive use of official secrecy to block public access to the findings of tax audits;
the long-standing tolerance of a dysfunctional legal mechanism; the legislature’s failure to abolish the redundant legal mechanism at a sufficiently early stage, before it degenerated into a dysfunctional system;
an uncoordinated and inconsistent approach by public administration bodies to ambiguous legal provisions; the inconsistency of the Ministry of Finance, which, on the one hand, recognised the flaw in this provision, yet at the same time penalised businesses for breaching it;
a worrying convergence of actions by local administrative bodies (district offices, provincial offices, military recruitment offices) in relation to the defendants"
>>21928881 In fact, every addition operation works, as it were, in series Addition always starts from the least significant bit, and the result of the next bit must be corrected by a carry; in reality, therefore, each addition is delayed by the number of bits multiplied by the gate delay.
Such a serial circuit has another advantage, apart from the obvious reduction in the number of components – meaning it is cheaper – namely that, in principle, numbers with any number of bits can be easily added together, regardless of the data bus width. A similar solution, namely a serial arithmetic unit, was used in the Datapoint 2200 terminal, whose unit – built using TTL circuits – served as a model for the designers of the i8008 processor and, consequently, for all Intel processors in the 8080 and x86 families, etc.
It is possible to use addition with carry-lookahead (CLA)... this is a much faster solution, but it requires the use of a greater number of transistors/gates.
Yes, but then the demand for gates and connections increases exponentially, which starts to become a problem with low-integration circuits, and the increase in speed is rather modest.
Not least because instruction cycles take considerably longer than the propagation time of a single gate.
What’s more, the architecture is further complicated by the move away from BCD arithmetic, which was dominant in early computers.
That is why most early processors used microcode.
As a point of interest, a 16-bit 68000 took quite a long time to multiply two 16-bit numbers, a time that depended on the number of ones in the operand according to the formula
38+2n for the MULU instruction, and if the result of the previous multiplication was taken into account, it depended on the number of combinations of 10 for the input data with the MULS instruction. The worst-case scenario was for the input 0x5555.
It was even worse for division, where the average instruction execution time was 158 cycles.
So, all in all, the 8-bit 6502 processor, which lacked multiplication instructions, required a comparable number of cycles to perform multiplication via a subroutine at the same clock frequency.
And these are external clock cycles; the 68k processor actually operated at twice the external clock speed.
There is also something known as the ‘Manchester carry adder chain’. However, it cannot be implemented in every technology.
It’s not the students’ fault, nor even that of those in power. The US is the centre of information technology because they were the ones who started this revolution. Nobody can change that; such is the law of first-mover advantage. The most talented people, not just from Poland, are heading to where the greatest opportunities lie. I don’t understand why there’s all this constant grumbling. I have friends who earn 10,000–15,000 zlotys net a month and still complain about low wages. Our standard of living is very high. Life is certainly easier here than in the US. We enjoy a level of prosperity our forebears could never have dreamt of, but there will always be grumblers who complain about how bad things are here, and they have no idea how to make things better.
The Odra played the role of a ballistic computer in the downing of the F-117. The entire radar system was highly complex. It certainly wasn’t just a single radar. This is a technology that is only now beginning to be discussed publicly, based on the analysis of reflections and disturbances from ‘natural’ sources of radio waves. It is difficult even to call it a radar; it is rather a system of listening posts, analysing disturbances in the ‘natural’ level of radio radiation (at that time mainly originating from radio and television transmitters).
