Intel Xeon Skylake Compilers: Clang Showing Strong Performance Against GCC

[phoronix]

Phoronix: Intel Xeon Skylake Compilers: Clang Showing Strong Performance Against GCC

A few days ago on the new Intel Xeon E3 1245 v5 "Skylake" system I ran a variety of GCC and LLVM Clang compiler benchmarks to show how the performance of the resulting binaries differ between these competing open-source compilers.

http://www.phoronix.com/vr.php?view=22593

[adakite]

Can't figure out if this beast supports AVX-512 instruction. Any idea Michael?

[darkblu]

Can't figure out if this beast supports AVX-512 instruction. Any idea Michael?

Not yet. In 2016 Xeons.

Michael

I'm not sure what Skylake support we're measuring here, given --with-tune=generic..

[carewolf]

Headline: "Clang showing strong performance against gcc"

Content: "Clang showing worse performance against gcc in every single benchmark"

[Luke_Wolf]

Headline: "Clang showing strong performance against gcc"

Content: "Clang showing worse performance against gcc in every single benchmark"

Ehm... no, other than in a handful of tests like C-Ray, Clang was at performance parity with the difference between them not being statistically significant. with clang "Winning" some of these like the Apache static page serving, and all the while maintains it's significant lead in compile times.

[carewolf]

Ehm... no, other than in a handful of tests like C-Ray, Clang was at performance parity with the difference between them not being statistically significant. with clang "Winning" some of these like the Apache static page serving, and all the while maintains it's significant lead in compile times.

The apache benchmark was the last one, and everything was tied. The only benchmarks Clang did better than gcc 6 in was the two compilation time results and 7-zip performance.

Btw, Gcc 6 looks really good in this test. Didn't the last gcc 6 benchmark show almost no improvements? What changed?

[lowflyer]

This stupid race "Clang compiles faster than ..." reminds of the eighties. (The eighties in the last millenium) There were two companies selling C compilers. (that was for the beloved Amiga) Whenever they had a new release they usually went into "boasting mode" about the compile time of their new product. And then, out of nothing, came a single guy that created a compiler that did not compete with the compile speed. He asked a single question: "Did you have a look at the code quality of the produced code of the compilers?" Then there were long faces and a long silence after that.

[lowflyer]

This stupid race "Clang compiles faster than ..." reminds of the eighties. (The eighties in the last millenium) There were two companies selling C compilers. (that was for the beloved Amiga) Whenever they had a new release they usually went into "boasting mode" about the compile time of their new product. And then, out of nothing, came a single guy that created a compiler that did not compete with the compile speed. He asked a single question: "Did you have a look at the code quality of the produced code of the compilers?" Then there were long faces and a long silence after that.

[Luke_Wolf]

The apache benchmark was the last one, and everything was tied. The only benchmarks Clang did better than gcc 6 in was the two compilation time results and 7-zip performance.

That's basically what I said in different words. Now compare that to what you originally said

Headline: "Clang showing strong performance against gcc"

Content: "Clang showing worse performance against gcc in every single benchmark"

Do you see the problem?

[carewolf]

That's basically what I said in different words. Now compare that to what you originally said



Do you see the problem?

It was sarcastic exageration, it might be a slight exageration, but it was not nearly as great an exageration as the headline.