I benchmarked the following naive matrix multiplication algorithm in both Julia 0.6 and 1.0. Surprisingly, Julia 1.0 version runs 4 times slower. Doing @code_llvm shows very neat output in 0.6 vs. 1.0. Any idea what is going wrong? Why doesn’t @simd work well in 1.0? The times are as follows: 0.…

Naive matrix multiplication is super slow in Julia 1.0?

Elrod August 17, 2018, 2:47am 11

As I pointed out here, Julia can do a really good job “producing C code” for matrix multiplication!

Topic		Replies	Views
Question About Transposes and Matrix Multiplication Speed Numerics	9	2189	August 22, 2018
Non-intuitive perf diff between `matrix * vector`, `matrix' * vector` and `copy(matrix') * vector` Performance blas	2	707	September 27, 2019
@inbounds: is the compiler now so smart that this is no longer necessary? Performance	33	3013	July 16, 2018
Why mul! is so fast? General Usage question , linearalgebra	7	6950	November 26, 2019
Native Julia gemm implementation Performance	16	3640	May 3, 2018