So digital giants have more lobbyist potential (in financial terms only, they cannot compete in massive 'job creation' in a districts all around the US, especially blue collar jobs) than the whole MIC, and the incentives to use it to counter lobbyist potential of warmongers. Why don't they use it for actual lobbying-for-global-piece?
The "Arab Spring" was just another power projection project, you only need to examine how many so-called NGOs that ran the social media campaigns were directly or indirectly funded by intelligence agencies.
But more to the point of the GP, to think that only the military industrial complex profits from American global dominance is incredibly naive. All the U.S. interventionism in South America for the last century (i.e. armed insurrection against democracies to install fascist dictatorships) was about opening markets and resources for exploitation by American (civil) corporations.
And forums where readers still communicate with authors shaping the new chapters.
> This essay will focus on two particularly striking mid-nineteenth-century examples of the complex relationships that unite the writer, readers, and editor of a serial. The first one is a French novel. Les Mystères de Paris, by Eugène Sue, which was serialized over a year and a half in 1842-43 in the Paris daily Le Journal des Débats Politiques et Littéraires, which translates literally as the Journal of Political and Literary Debates; the second is Uncle Tom's Cabin, by Harriet Beecher Stowe, which first appeared in the antisîavery weekly, the National Era, between 1851 and 1852.
> My first point is that in the case of both works, apart from the fact that they aimed at social reform and were tremendously popular and violently criticized, their respective readers played a role in giving final form to each novel, particularly in terms of length. I will then examine the locus of the discussion that is being carried on between the readers and the writer. In Stowe's case, since she was writing far from Washington, where the National Era was based, the conversation between the reader and the writer was carried on in the columns of the Era itself. In Sue's case, the correspondence between reader and writer was mostly conducted via private letters, for reasons I will go into later. Sue kept more than three hvmdred of the letters he received while writing Les Mystères; those letters have now been edited and published. As can be imagined, they provide a rare and invaluable insight into the interaction between reader and writer during the publication of a serial.
I had this feeling exactly listening (great, as everything Aaron does) presentation about manipulation and transformation of trees in APL, https://www.youtube.com/watch?v=hzPd3umu78g
In the comments the guy says the hardware the benchmark was running on had 3TB of RAM.
That's not average hardware. It's a couple hundred connections max running select statements as fast as possible on the best hardware they could afford to test against.
That doesn't translate into your CRUD app handling a million requests per second.
And 5 if not 9 out of that Fortune 10' NoSQL dbs were just tied with a duck tape ('Our frontend team needs something they could understand - Ah okay then') to the mainframe with a previous generation of NoSQL - like ADABAS, IMS or z/TPF - and a ton of COBOL code where all the work is done since forever.
Universal kernel bypass for IO? Does it imply every userspace program should know how to communicate with every kind of IO device? No block layer? What about memory and caching?
That's not a bad idea. You'll need some sort of mechanism to make sure they don't step on each other's toes, but otherwise it's a sound concept, not unlike MS-DOS.
It seems some highest-performant enterprise solutions consider the MS-DOS way as well.
"The Coherent Accelerator Processor Interface (CAPI) is a general term for the infrastructure that provides high throughput and low latency path to the flash storage connected to the IBM POWER 8+ System. CAPI accelerator card is attached coherently as a peer to the Power8+ processor. This removes the overhead and complexity of the IO subsystem and allows the accelerator to operate as part of an application. In this paper, we present the results of experiments on IBM FlashSystem900 (FS900) with CAPI accelerator card using the "CAPI-Flash IBM Data Engine for NoSQL Software" Library. This library provides the application, a direct access to the underlying flash storage through user space APIs, to manage and access the data in flash. This offloads kernel IO driver functionality to dedicated CAPI FPGA accelerator hardware. The results indicate that FS900 & CAPI, together with the metadata cache in RAM, delivers the highest IO/s and OP/s for read operations. This was higher than just using RAM, along with utilizing lesser CPU resources."
OTOH, "As one step toward building high performance NVM systems, we explore the potential dependencies between system call performance and major hardware components (e.g., CPU, memory, storage) under typical user cases (e.g., software compilation, installation, web browser, office suite) in this paper. We find that there is a strong dependency between the system call performance and the CPU architecture. On the other hand, the type of persistent storage plays a less important role in affecting the performance."
"Itanium was in-order VLIW, hope people will build compiler to get perf. We came from opposite direction - we use dynamic scheduling. We are not VLIW, every node defines sub-graphs and dependent instructions. We designed the compiler first. We build hardware around the compiler, Intel approach the opposite."
https://www.anandtech.com/show/13255/hot-chips-2018-tachyum-...
