Luke Gorrie
Luke Gorrie
@raj2569 I am curious about that too :-) Hopefully we will find out along the way. Could be that there is an interesting explanation, could be that it magically disappears...
Fixed the bug with 4993c37. This code works fine up to 128KB inputs in casual testing. That limitation seems okay to me i.e. not worth writing more code to increase...
Added `snabbmark checksum` benchmark: ``` $ taskset -c 1 sudo ./snabb snabbmark checksum VARIANT BYTES/PACKET BYTES/CYCLE CYCLES/PACKET base 631.331 0.326 1935.081 asm 631.331 4.244 148.770 avx2 631.331 2.743 230.180 sse2...
This branch is taking a little bit of a different turn: I found a fairly straightforward formulation of checksum in C that GCC is able to automatically vectorize when compiled...
@jsnell Yes, I know what you mean. In Snabb we pin exact versions of LuaJIT and DynASM so that we can "geek out" on them but have tried to be...
I wonder if a better PCIe core is available that can do 16G? I'm asking the Twitterverse. PCIe bifurcation should be something that we can live with if we have...
(also: sounds plausible to ship an EasyNIC with 8Gbps PCIe bandwidth if this can later be upgrade to 16Gbps with a firmware update (new PCIe endpoint core). This is a...
@mithro LiteEth/LitePCIe looks really interesting, great if there is something there that we can reuse! EasyNIC is all about making software developers happy by creating a simple and beautiful interface...
@insekt Great that you are getting information about the PHY. If the lifetime is very short that would be a problem. On the other hand 10G ethernet and PCIe 2.0...
@mithro Goal here is to make a NIC that Snabb users (for example) can deploy applications with. These are typically people working in ISPs or other network operators. In this...