Revisiting the Business Card Raytracer
fabiensanglard.net
Revisiting the Business Card Raytracer
1–10 of 54 posts
Re: Revisiting the Business Card Raytracer
#2101,000ms to 150ms is a phenomenal speedup. Props
Re: Revisiting the Business Card Raytracer
#3> Opening the binary with Binary Ninja revealed that clang had already managed to leverage the SSE registers.
X86-64 uses SSE registers for all floating point operations. I'm not sure that the author realized that they were looking at an -O0 binary. -O0 does not do vectorization (or anything else for that matter).
Re: Revisiting the Business Card Raytracer
#4If you increase resolution you can put more code on business card :P
Re: Revisiting the Business Card Raytracer
#5i love what fabien is doing with his website!
also been experimenting with pure html with an itsy-bitsy amount of css. for months now i wondered how to display code without involving javascript.
that textarea is so perfect! and i bet you when you copy and paste into word or your todo list application they won't even try to be "smart" about knowing what "rich text" is...
that's very cool.
Re: Revisiting the Business Card Raytracer
#6> Opening the binary with Binary Ninja revealed that clang had already managed to leverage the SSE registers. X86-64 uses SSE registers for all floating point operations. I'm not sure that the author realized that they were looking at an -O0 binary. -O0 does not do vectorization (or anything else for that matter).
Looking at it on Godbolt, it doesn't really leverage SSE on -O3, either. You can get a reasonable grasp of whether it's using SSE effectively or not just by looking at the instruction names.
mulss: multiplication of a single single-precision floating point value.
mulsd: multiplication of a single double-precision floating point value.
mulps: multiplication of a packed group of single-precision floating point values.
mulpd: multiplication of a packed group of double-precision floating point values.
If you're mostly seeing -ps suffixes only on moves and shuffles, you're looking at code that is not being vectorized. (And, actually, if you're seeing a lot of shuffles, that's also a good sign its not well-vectorized.)
Incidentally, if you're seeing unexpected -sd suffixes, those are often due to unintended conversions between float and double. They can have a noticeable effect on performance, especially if you end up calling the double versions of math functions (as they often use iterative algorithms that need more iterations to achieve double-precision).
I'm linking GCC output, because it's simpler to follow, but you see more or less the same struggle with Clang.
Re: Revisiting the Business Card Raytracer
#7> Opening the binary with Binary Ninja revealed that clang had already managed to leverage the SSE registers. X86-64 uses SSE registers for all floating point operations. I'm not sure that the author realized that they were looking at an -O0 binary. -O0 does not do vectorization (or anything else for that matter).
Yeah, use of SSE registers does not imply SIMD, since x87 is gone in x86-64, so even scalar FP has to use SSE registers. The asm snippets for v::operator*() in the "Optimization level 1" section use scalar SSE arithmetic only (mulss). (There's some use of movaps to move data around, but it's a stretch to call that SIMD.)
I think the "leverage" sentence you quoted and the "with SIMD taken care of" one shortly after are maybe a bit misleading, since the asm snippets there don't really demonstrate SIMD.
Re: Revisiting the Business Card Raytracer
#8> Opening the binary with Binary Ninja revealed that clang had already managed to leverage the SSE registers. X86-64 uses SSE registers for all floating point operations. I'm not sure that the author realized that they were looking at an -O0 binary. -O0 does not do vectorization (or anything else for that matter).
Yeah, use of SSE registers does not imply SIMD, since x87 is gone in x86-64, so even scalar FP has to use SSE registers. The asm snippets for v::operator*() in the "Optimization level 1" section use scalar SSE arithmetic only (mulss). (There's some use of movaps to move data around, but it's a stretch to call that SIMD.) I think the "leverage" sentence you quoted and the "with SIMD taken care of" one shortly after ar…
> since x87 is gone in x86-64, so even scalar FP has to use SSE registers.
No, it’s still there. What’s actually going on is that all x86-64 CPUs support SSE2, so there is little reason to use x87 in 64-bit code.
(You can use it for 80-bit precision. OTOH, for most purposes, 80-bit precision is actively harmful, and x87 is an incredible mess, so almost no one wants it.)
Re: Revisiting the Business Card Raytracer
#9i love what fabien is doing with his website! also been experimenting with pure html with an itsy-bitsy amount of css. for months now i wondered how to display code without involving javascript. that textarea is so perfect! and i bet you when you copy and paste into word or your todo list application they won't even try to be "smart" about knowing what "rich text" is... that's very cool.
i am glad that there is a small village of indomitable developers holding out against tens of megabytes of reactive functional progress modern javascript frameworks.
thank you
Re: Revisiting the Business Card Raytracer
#10> Opening the binary with Binary Ninja revealed that clang had already managed to leverage the SSE registers. X86-64 uses SSE registers for all floating point operations. I'm not sure that the author realized that they were looking at an -O0 binary. -O0 does not do vectorization (or anything else for that matter).
You are correct. Mārtiņš Možeiko pointed out that I had been too hasty when the article came out (https://twitter.com/mmozeiko/status/1257574246462570497). To conclude SIMD is leveraged when XMM registers are used is wrong. What I should have looked for are packed instructions.