[joe91]

Assuming the M1 GPU works like most modern GPUs then bounds checking is already built into every memory operation.

Memory operations in modern GPUs basically evolved from fetching textures (which intrinsically have bounds checking built in, they have a width and height). All modern desktop GPUs (and probably mobile GPUs these days) use "descriptors" for textures and buffers which specify both address and size. Out of range fetches from a buffer return 0 and out of range writes are no operations.

There have been some GPUs in the past that could literally write to any address in main memory (famously the GPU in the XBox360 could do this), but its not true of any modern GPU as far as I know.

On a different note, 900 GFlops from a GPU is not really that impressive. Desktop GPUs reached this kind of performance nearly 10 years ago, but I guess its not bad for a first generation new design.

[thitcanh]

I guess it's not bad for a fanless 10-watt SoC the size of a stamp on an entry-level portable computer in a browser.

To get that kind of performance nearly 10 years ago in a desktop GPU, I bet you would need a whole lot of dollars, watts, and cube inches.

It is impressive unless you compare apples to oranges.

Plus, on bare metal it reaches 2.6 TFLOPs already.

[ChuckNorris89]

>entry-level portable computer

Not all computers are Macs and at €1000 starting price, it's the entry level Mac but by no means an entry level computer.

Entry level computers are in the €400 ballpark (i5/4500U, 8GB RAM, 256 SSD).

For €1000 you could get a pretty strong gaming computer which is by no means entry level.

[chungus_khan]

Nearly 10 years ago a 2.6 TFLOP (FP32) GTX 660ti cost about $300 and had a TDP of 150w.

[nynx]

See, that's what I also thought, but I've heard that the built-in bounds checking can be pretty buggy. I'm not an expert though.

Yeah, compared to modern desktop GPUs, which can hit probably 20-30 times this, it's not that impressive. That being said, they're also consuming 20-30 times the power.