I found the syntax for the DCMPY instruction to be a little confusing. I think it's due to an inconsistency in the documentation.
Let me explain by contrasting it with the CMPY instruction. Here are the descriptions of each:
CMPY (.unit) src1, src2, dst_o:dst_e
DCMPY (.unit) src1, src2, dst
The DCMPY operand type description only seems to add to the confusion:
src1 = dwop1
src2 = xdwop2
dst = dwdst
From my reading of the syntax (on pages 3-2, 3-3), this seems to indicate that both the operands are 64-bit register pairs, although I think this is incorrect. Shouldn't the destination be a 128-bit register quad?
While it may seem obvious when you know how the instructions work, it's confusing when you're first trying to examine/learn the instructions. Based on the single example shown in the instruction description, I'm guessing that a consistent syntax for DCMPY would be:
DCMPY (.unit) src1_o:src1_e, src2_o:src2_e, dst_3:dst_2:dst_1:dst_0
Can someone confirm the instruction description is misleading; and if so, mark it for correction?
Thanks,
Scott
