On 2/26/2014 1:22 PM, Tom Musta wrote: > I see one problem with the PowerPC vncipher instruction. This instruction is > not equivalent the aesdec. Moreover, the AddRoundKey (XOR) is performed > *before* > applying the InvMixColumns operation. So the AES_Te4 mapping is not correct > for PPC.
s/AES_Te4/AES_Te*/ And I should have added ... Even though I cannot use AES_Te4, I certainly can construct a flattened table for InvMixColumns (a la AES_T*). This will result in a faster implementation. Does it make sense to put this InvMixColumns table in common utilities even if PowerPC is the only user? It seems to be mainly an issue of space (about 4K).
