https://spectrum.ieee.org/ibm-mainframe [ ] IEEE.orgIEEE Xplore Digital LibraryIEEE StandardsMore Sites Sign InJoin IEEE A Quadrillion Mainframes on Your Lap Share FOR THE TECHNOLOGY INSIDER [ ] Explore by topic AerospaceArtificial IntelligenceBiomedicalComputingConsumer ElectronicsEnergyHistory of TechnologyRoboticsSemiconductorsSensors TelecommunicationsTransportation FOR THE TECHNOLOGY INSIDER Topics AerospaceArtificial IntelligenceBiomedicalComputingConsumer ElectronicsEnergyHistory of TechnologyRoboticsSemiconductorsSensors TelecommunicationsTransportation Sections FeaturesNewsOpinionCareersDIYEngineering Resources More Special ReportsExplainersPodcastsVideosNewslettersTop Programming LanguagesRobots Guide For IEEE Members The MagazineThe Institute For IEEE Members The MagazineThe Institute IEEE Spectrum About UsContact UsReprints & PermissionsAdvertising Follow IEEE Spectrum Support IEEE Spectrum IEEE Spectrum is the flagship publication of the IEEE -- the world's largest professional organization devoted to engineering and applied sciences. Our articles, podcasts, and infographics inform our readers about developments in technology, engineering, and science. Join IEEE Subscribe About IEEEContact & SupportAccessibilityNondiscrimination PolicyTerms IEEE Privacy Policy (c) Copyright 2021 IEEE -- All rights reserved. A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. IEEE websites place cookies on your device to give you the best user experience. By using our websites, you agree to the placement of these cookies. To learn more, read our Privacy Policy. view privacy policy accept & close Stay ahead of the latest technology trends. Become an IEEE member. Enjoy more free content and benefits by creating an account Saving articles to read later requires an IEEE Spectrum account The Institute content is only available for members Downloading full PDF issues is exclusive for IEEE Members Access to Spectrum's Digital Edition is exclusive for IEEE Members Following topics is a feature exclusive for IEEE Members Adding your response to an article requires an IEEE Spectrum account Create an account to access more content and features on IEEE Spectrum, including the ability to save articles to read later, download Spectrum Collections, and participate in conversations with readers and editors. For more exclusive content and features, consider Joining IEEE. This article is for IEEE members only. Join the world's largest professional organization devoted to engineering and applied sciences and get access to all of Spectrum's articles, podcasts, and special reports. Learn more - Join the world's largest professional organization devoted to engineering and applied sciences and get access to all of Spectrum's articles, archives, PDF downloads, and other benefits. Learn more - CREATE AN ACCOUNTSIGN IN JOIN IEEESIGN IN Enjoy more free content and benefits by creating an account Create an account to access more content and features on IEEE Spectrum, including the ability to save articles to read later, download Spectrum Collections, and participate in conversations with readers and editors. For more exclusive content and features, consider Joining IEEE. CREATE AN ACCOUNTSIGN IN Topic Magazine Type Computing Opinion A Quadrillion Mainframes on Your Lap Your laptop is way more powerful than you might realize Rodney Brooks 2h 3 min read Black and white photograph of a man in a large room with mainframe computer elements lining the walls The IBM 7090 was the first line of transistorized computers, in the early 1960s. It was based on the 709 line, which used vacuum tubes. Gamma-Keystone/Getty Images computing history of technology computers Whenever I hear someone rhapsodize about how much more computer power we have now compared with what was available in the 1960s during the Apollo era, I cringe. Those comparisons usually grossly underestimate the difference. By 1961, a few universities around the world had bought IBM 7090 mainframes. The 7090 was the first line of all-transistor computers, and it cost US $20 million in today's money, or about 6,000 times as much as a top-of-the-line laptop today. Its early buyers typically deployed the computers as a shared resource for an entire campus. Very few users were fortunate enough to get as much as an hour of computer time per week. --------------------------------------------------------------------- The 7090 had a clock cycle of 2.18 microseconds, so the operating frequency was just under 500 kilohertz. But in those days, instructions were not pipelined, so most took more than one cycle to execute. Some integer arithmetic took up to 14 cycles, and a floating-point operation could hog up to 15. So the 7090 is generally estimated to have executed about 100,000 instructions per second. Most modern computer cores can operate at a sustained rate of 3 billion instructions per second, with much faster peak speeds. That is 30,000 times as fast, so a modern chip with four or eight cores is easily 100,000 times as fast. Unlike the lucky person in 1961 who got an hour of computer time, you can run your laptop all the time, racking up more than 1,900 years of 7090 computer time every week. (Far be it from me to ask how many of those hours are spent on Minecraft.) Continuing with this comparison, consider the number of instructions needed to train the popular natural-language AI model, GPT-3. Executing them on cloud servers took the equivalent of 355 years of laptop time, which translates to more than 36 million years on the 7090. You'd need a lot of coffee as you waited for that job to finish. A week of computing time on a modern laptop would take longer than the age of the universe on the 7090. But, really, this comparison is unfair to today's computers. Your laptop probably has 16 gigabytes of main memory. The 7090 maxed out at 144 kilobytes. To run the same program would require an awful lot of shuffling of data into and out of the 7090--and it would have to be done using magnetic tapes. The best tape drives in those days had maximum data-transfer rates of 60 KB per second. Although 12 tape units could be attached to a single 7090 computer, that rate needed to be shared among them. But such sharing would require that a group of human operators swap tapes on the drives; to read (or write) 16 GB of data this way would take three days. So data transfer, too, was slower by a factor of about 100,000 compared with today's rate. So now the 7090 looks to have run at about a quadrillionth (10-15) the speed of your 2021 laptop. A week of computing time on a modern laptop would take longer than the age of the universe on the 7090. But wait, there's more! Each core in your laptop has built-in SIMD (single instruction, multiple data) extensions that turbocharge floating-point arithmetic, used for vector operations. Not even a whiff of those on the 7090. And then there's the GPU, originally used for graphics speedup, but now used for the bulk of AI learning such as in training GPT-3. And the latest iPhone chip, the A15 Bionic, has not one, but five GPUs, as well as a bonus neural engine that runs 15 trillion arithmetic operations per second on top of all the other comparisons we have made. The difference in just 60 years is mind boggling. But I wonder, are we using all that computation effectively to make as much difference as our forebears did after the leap from pencil and paper to the 7090? This article appears in the January 2022 print issue as "So Much Moore." From Your Site Articles * Building the System/360 Mainframe Nearly Destroyed IBM - IEEE ... > * What Does It Take to Keep a Classic Mainframe Alive? - IEEE ... > Related Articles Around the Web * IBM Archives: Mainframe family tree and chronology > * Why on Earth Is IBM Still Making Mainframes? | WIRED > computing history of technology computers Rodney Brooks Rodney Brooks is the Panasonic Professor of Robotics (emeritus) at MIT, where he was director of the AI Lab and then CSAIL. He has been cofounder of iRobot, Rethink Robotics, and Robust AI, where he is currently CTO. The Conversation (0) A black and white photo of a submersible in the water in front of a pier with debris on it. The Institute Topic Type Article History of Technology The First U.S. Human-Operated Submersible Changed the Course of Oceanography 3h 4 min read Honda researcher inserts a charged Mobile Power Pack e-battery into an e-rickshaw. News Topic Type Transportation Honda Is Readying a Novel Battery Sharing Service for E-taxis in India 6h 4 min read The top of a mobile phone mast covered in telecommunications equipment is seen against a clear blue sky. Topic News Type Telecommunications European Telcos Sound Alarm Over Flagging Open RAN Progress 8h 4 min read Related Stories Review Topic Hands On Type Computing 10 Gifts For Retrocomputing Fans History of Technology Topic Type Feature Inventing the Atari 2600 Topic News Type History of Technology Behind the Scenes of Spectrum's Dive Into the Atari 2600 Design Topic Magazine Feature Special reports Transportation Type Should the Cobalt for EVs Come From the Congo or the Seafloor? The Metals Company's pilot program raises muddy questions David Schneider 6h 4 min read A large dome-shaped robotic vehicle for collecting polymetallic nodules rests on the bottom of the ocean. The Metals Company will outfit its nodule-collection robot with lights and cameras, which will document its effects on the ocean floor. The Metals Company Last March, BMW and Volvo joined other companies calling for a moratorium on deep-sea mining, one spearheaded by the World Wildlife Fund. These carmakers' names were significant because the battery in an electric vehicle contains at least a few kilograms of cobalt, a metal that some hope one day to extract from the seabed--to the chagrin of many environmentalists. This simmering controversy will no doubt reach the boiling point in 2022, when the Metals Company begins testing a system for collecting metal-rich nodules from the ocean floor. Most press coverage will no doubt paint a simplistic picture of the arguments for and against doing so. But the question of whether obtaining cobalt and other valuable metals from the ocean floor would help or hurt the environment overall is, in fact, quite complicated. A reasoned judgement will hinge on many things, including how much you are concerned by the toll from conventional mining. More than half of the world's cobalt currently comes from the Democratic Republic of the Congo, which has had a dismal record for protecting the environment and the well-being of the people who live and work around its mines. Would having another large source available--the deep Pacific--help corporate buyers pressure Congolese mining companies to clean up their act? This and other important questions will remain open for some time, but one critical component in the calculus--the degree of environmental disruption involved in collecting metal-rich nodules from the deep Pacific--should become much clearer after the Metals Company begins pilot operations later this year. Those operations will be conducted from what formerly served as a petroleum drill ship, rechristened Hidden Gem. The giant vessel is now being outfitted to collect polymetallic nodules, which are gravel- to briquette-size concretions that can be found strewn almost like paving stones on certain parts of the deep-ocean floor. Unlike some other strategies for obtaining metal ores from the seafloor, getting them from nodules is more a matter of collecting than "mining" in the usual sense of the word. Sometime in 2022, workers on the Hidden Gem will lower into the water a steel pipe of colossal proportions, one segment at a time, with a total length of 4 kilometers. But it won't simply dangle over the seafloor, hoovering up nodules like a giant underwater vacuum cleaner. "At the business end is the robotic collector vehicle," explains Jon Machin, head of offshore engineering at the Metals Company. This vehicle is some 12 meters long and weighs 80 tonnes in air. In water, though, it weighs significantly less--just enough for the vehicle to gain traction as it propels itself, but not so much as to cause it to get mired in the mud. Compressed air injected into the bottom of the pipe will create countless bubbles, which will help raise the mix of nodules, mud, and seawater. A flexible conduit will connect the end of the steel pipe with the vehicle. As the vehicle moves over the bottom, it will funnel nodules through this flexible conduit and into the pipe, where they will be sent upward using what Machin calls "an air-lift system": Compressed air injected into the bottom of the pipe will create countless bubbles, which will help raise the nodules, along with some mud and seawater. Nodules will be separated from this slurry aboard the Hidden Gem, which will store them in its hold and discard what remains. The best depth to discharge the leftovers is not yet entirely clear. Doing so in shallow water could affect the abundant sea life that lives there, while releasing it too close to the seafloor wouldn't give the mud an opportunity to spread and thin before settling. This could potentially bury the immobile creatures that reside on the bottom at these depths (albeit at very low densities). The Goldilocks plan is to discharge the seawater and mud through a second pipe at an intermediate depth of about 1,200 meters. Oceanographers from MIT and elsewhere have been studying the environmental consequences of such operations. They even mounted a research expedition in the Pacific in 2018, during which they pumped a mixture of dye and mud from the bottom into the water. This allowed the researchers to discern whether the fine mud particles would glom together. "It doesn't look like that's the case," says E. Eric Adams, an expert in water-quality monitoring at MIT, who was one of the participants in that study. This experiment also helped the scientists to verify their models of the movement of the resulting turbid plumes. "We showed that you could do a fairly good job with a simple equation," says Adams. Oceanographers will have weeks or months to investigate further how well their models match reality when the Metals Company conducts its 2022 tests with the Hidden Gem. Later, Machin says, "we plan to ramp up with bespoke, newly built vessels." That assumes that the company continues to receive the needed permits from the International Seabed Authority, which has jurisdiction in these waters. There are many examples of seafloor disruption most people never think about--trawling by fishing vessels, dredging, even the mining of diamonds off the coast of Namibia, to name a few. These actions take place where marine life is far more abundant than at the great depths where nodules form. But given the World Wildlife Fund's call for a moratorium in deep-seabed mining, it's likely the Metals Company's upcoming pilot operations will stir up as much debate as it does mud. This article appears in the January 2022 print issue as "Deep-Sea Mining Stirs Up Muddy Questions." From Your Site Articles * Could Sucking Up the Seafloor Solve Battery Shortage? - IEEE ... > * Autonomous Robots Could Mine the Deep Seafloor - IEEE Spectrum > Related Articles Around the Web * Polymetallic Nodules > * Biological responses to disturbance from simulated deep-sea ... > * Nodules - The Metals Company > Keep Reading | Show less