More Zonkyness

AMD’s “Secret” 32-Bit ABI

Mar 132014

This blog posting talks about machine code and whether 32-bit code or 64-bit code is more appropriate. When AMD released the Opteron way back in 2003, it was the first processor to support the x86-64 instruction set for supporting 64-bit code whilst maintaining backward compatibility with the old IA32 code. Or in other words, the Opteron could run both 32-bit code and 64-bit code.

Everybody leaped onto the 64-bit bandwagon without thinking too much about it – it was faster.

But if we look at the other processors that made the transition from 32-bit code to 64-bit code – such as the SPARC, MIPS, etc., we find something interesting. Much of the code running on the relevant operating systems remained 32-bit – not as a transitional measure, but because the 32-bit code was faster. If you look at a relatively modern Solaris system the contents of /bin contain 500-odd binaries that are 32-bit and just 11 that are 64-bit (most of which aren’t in fact part of Solaris but another add-on package).

It turns out that in general, 64-bit code is slower than 32-bit code. In the case of x86-64, 64-bit code is faster not because it is 64-bit, but because of the architectural changes that were also introduced – including (probably most significantly) extra registers.

How do we know this? Apart from it being obvious to those who have lived through the 32-bit to 64-bit transition multiple times, it turns out that people have been experimenting. As it turns out, the x86-64 architecture does allow for 32-bit code to be run with all the features of the x86-64 architecture and that architecture has been labelled as X32.

It turns out that X32 code can be anywhere from 5-40% faster than 64-bit code. The largest increases come from code that makes very heavy use of pointers, and at present no benchmarks of “ordinary” software have been released.

The “downside” of X32 is of course that the software is limited to 4Gbytes of memory, but most programmes don’t need that much memory because 4Gbytes is a lot. Forget that huge video editor you’re playing with – that will quite possibly need 64-bit pointers, but what about all the other software running on your machine?

There are over 400 processes running on my workstation, and none of those processes really requires more than 4Gbytes of memory. Sure I run software that does require more than 4Gbytes of memory, but not all the time.

And running things 10% quicker would be useful … or alternatively running things quicker means the processor can spend more time asleep making battery life longer.

In the UK, FGM Victims: 66,000 in total, MGM Victims: 31,000 per year!

General No Responses »

Mar 012014

According to an article in the Guardian about the schoolgirl who campaigned for more information on FGM in schools, there are up to 66,000 victims of female genitial multilation in the UK. If you count circumcision as male genital mutilation, then according to a couple of sources, there are roughly 31,000 victims of male gentical mutilation per year.

And the rate of circumcision has been falling for decades; according to an article on the prevalence of male circumcision, the average rate of male circumcision approximates about 10% which would mean that there are in total approximately 2.7 million men who have been circumcised.

Let’s perform a little experiment with those figures. Let us assume that a victim of MGM suffers 1/100 of the agony of a victim of FGM. This is of course nonsense as different kinds of FGM are practiced and how on earth do you measure the level of agony for any victim? But let’s crunch those numbers …

It turns out that using those assumptions there are the equivalent of 27,000 victims of FGM amongst the male population!

Now in case anyone misunderstands me, I’m fully behind the campaign against FGM. It’s a primitive and barbaric custom practiced for reasons that are probably due to religious fanatics being terrified of female sexuality.

But we shouldn’t ignore MGM just because it seems less severe and is practiced for less repressive reasons – for mistaken health benefits, spurious “aesthetic” reasons, or just to mark someone as a member of a tribe. Whilst it may seem a little extreme to call male circumcision MGM, it is worth pointing out that there is a reason for calling it male circumcision. In the past FGM was called female circumcision; changing attitudes have relabelled it FGM. There is no reason to suppose that in the future, male circumcision will be universally reviled as MGM.

There is something else that is overlooked too. There is nothing wrong with genital mutilation if it is freely chosen by a responsible adult … for themselves. In other words there is nothing wrong with either FGM or MGM.

What is wrong is any kind of childhood mutilation – genitial mutilation or otherwise. Nobody has the right to make that sort of decision on behalf of another, not parents, nor religious leaders. At one time, paedophiles were labelled “kiddie fiddlers”, well it’s time to label practitioners of CGM (FGM+MGM) “kiddie fiddlers” too.

People Of Colour …

General No Responses »

Mar 012014

Every time I encounter this phrase (usually misspelled “people of color”), or the phrases “men of colour” and “women of colour” (and presumably “children of colour”), it grates.

Now don’t get me wrong, it beats the hell out of phrases like “nigger”, “gook”, “wog”, “chink”, etc. And even not quite as insulting terms such as “minority” or “non-white”.

But :-

White is a colour too. In fact most of those who are labelled “white” are not in fact covered in skin whose colour is actually white. We’re all colourful people!
Wouldn’t it be better to label the problem rather than the target? I.e “rascists”. One of the problems with using the target (“people of colour”) is that whilst most racism is directed against people of colour, some is still directed against others – and the problem is racism rather than the target.
There’s something wrong with the world when it is necessary to categorise people by the colour of the dead stuff that keeps the squishy bits on the inside.

Slicing Up The Liberty PIE

Uncategorized No Responses »

Feb 272014

The Daily Mail has decided to attack Harriet Harman in relation to her involvement with the Liberty organisation when it was known as the National Council for Civil Liberties (it is still formally called that). Liberty (in the 1970s) allowed an organisation called the Paedophile Information Exchange to affiliate with Liberty.

Personally I feel it is more than a little unfair to target Harriet Harman in this way, and I’m not exactly one of her fans.

In retrospect, it is clear that Liberty were very mistaken in being associated with PIE (and PAL). But their support was not unconditional – it is clear that their support was limited to suggesting that society should consider whether consensual sex between an adult and a child was necessarily damaging.

Or in other words whether a 16-year old woman who sleeps with her 5-year old boyfriend should be painted the same colour as a predator such as Jimmy Saville. However it seems that many of PIEs leaders were the kind of predator that would have gotten along well with Jimmy.

Liberty terminated their relationship with PIE by 1983 and the current head of Liberty issued an apology for the relationship: “It is a source of continuing disgust and horror that even the NCCL had to expel paedophiles from its ranks in 1983 after infiltration at some point in the 70s.”

So like many organisations, Liberty made a mistake in the 1970s and have apologised for it. But what about Harriet Harman?

Harriet Harman was the legal officer for Liberty at the time – she didn’t head the organisation and probably had no more than a small say in the direction of the organisation as a whole. If she knew about the connection to PIE, and objected, she would probably been told the liberal lefty equivalent of “shut up and soldier on”. Picking on Harriet Harman is unfair … it is the organisation that was at fault not her.

And indeed Patricia Hewitt‘s apology for Liberty’s association with PIE clearly indicates that Harriett Harman had very little say in whether Liberty accepted PIE’s affiliation or not; and indeed her work had nothing to do with PIE.

As always we can see the Daily Mail is conducting little more that a witch hunt against those who hold views not on the extreme right.

Reshelving ….

Computing No Responses »

Feb 232014

Just an experiment in producing a video :-

Not especially good because I’m too lazy to go back and even out the exposure (so the lighting doesn’t keep changing).

Older Entries Newer Entries