gemm
gemm copied to clipboard
sarah-ek
Hi, While investigating the crate performance I found out that running parallelism could be highly detrimental to performance. This only occurs with machines with a lot of cores (and therefore...
Hi @sarah-ek, I have an operation where I need to apply matrix multiplication to f32,f16 to obtain f32 matrix. The addition and multiplication should be done in f32 format. So:...
There is a comment in the code base: https://github.com/sarah-ek/gemm/blob/main/gemm/src/gemm.rs#L151 which says that gemm panics if T is not f32 and f64. But I was able to run it with f16...
Hi, Are you thinking of adding support for Neon and Wasm architecture anypoint in the road map of this crate ?
Hi, I created a small Rust example: ``` use gemm_f16::f16; fn main() { println!("Hello, fp16!"); let a = f16::from_f32(3.1f32); let b = f16::from_f32(2.2f32); let c = a * b; if...
While building the https://github.com/oxfordcontrol/Clarabel.rs project on i386, this error occurred: ``` Compiling gemm-common v0.18.0 error[E0599]: no function or associated item named `new` found for struct `CpuId` in the current scope...
I recently found out that [this is a thing](https://en.wikichip.org/wiki/intel/crystal_well) when trying to run a `candle` program (which depends on `gemm`) on this machine: ``` # grep 'model name' /proc/cpuinfo model...
A small thing I just noticed: gemm ends up pulling in two versions of the `bitflags` crate. That probably does not have a huge effect on build times, but if...
