If you have the code with inline assembly for MacOS M1, I can test it.
> On Apr 25, 2023, at 22:39, Jeffrey Walton <noloa...@gmail.com> wrote: > > > > On Friday, March 31, 2023 at 1:44:41 AM UTC-4 Sam Van Gucht wrote: > Hi everyone, > > We noticed AES GCM in significant slower on M1 compare to an Intel Mac. > Encrypting a 100mb files takes ~130ms on Intel Mac & while on M1 it takes > ~510ms. > > Are the ARMv8 Cryptographic instructions not supported > > The Clang compiler provided by Apple is crippled. It does not provide the > intrinsics needed for the multiplies. > > The fix is to use inline assembly. Apple compilers support the mnemonics. > > I don't have access to an Apple ARMv8 and M1 machines any longer. I donated > the one I bought to the GCC Compile Farm. They loaded Debian on it. > > Jeff > -- > You received this message because you are subscribed to the Google Groups > "Crypto++ Users" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to cryptopp-users+unsubscr...@googlegroups.com. > To view this discussion on the web visit > https://groups.google.com/d/msgid/cryptopp-users/56d9db2e-ab96-4259-817a-c767141a80b7n%40googlegroups.com. -- You received this message because you are subscribed to the Google Groups "Crypto++ Users" group. To unsubscribe from this group and stop receiving emails from it, send an email to cryptopp-users+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/cryptopp-users/2CE8A97E-67A4-4B48-BB93-3E1DF381DB3E%40gmail.com.
