"Avoid instructions (executable code) and operand data (working storage or stack storage) in the same cache lines; which can be costly due to moving cache lines between the separated (split) local caches (instruction/data L1/L2)"
-- C. Kevin Shum, Distinguished Engineer, IBM z Systems Microprocessor Development (March 2016) Charles -----Original Message----- From: IBM Mainframe Assembler List [mailto:[email protected]] On Behalf Of Keith Moe Sent: Wednesday, August 1, 2018 1:27 PM To: [email protected] Subject: Re: EQU * considered harmful Inline data is only a killer if it is updated. It is merely less efficient if it is read only (same cache line in instruction and data caches). My example was merely to show that the "INSTRUCT" statement would force half word alignment. Aside from macros that expand inline CONSTANTS (not updatable areas), I generally avoid mixing instructions and data. Even in non-reentrant code (unfortunately there's a lot here that I have to maintain and it's not worth it to make it reentrant), I try to isolate code blocks and data blocks. Keith Moe BMC Software, Inc. -------------------------------------------- On Wed, 8/1/18, Charles Mills <[email protected]> wrote: Subject: Re: EQU * considered harmful To: [email protected] Date: Wednesday, August 1, 2018, 1:05 PM Well, one could argue that "DS" implies a variable, not instructions, and is therefore inappropriate as something on which to hang an instruction label. I like the idea of some kind of "instruction" attribute for EQU, with an error if you branched to a non-instruction symbol. I think I might argue for an EQU operand rather than a new opcode, but that is a quibble. J NEXTL DC CL(oddnumber)' ' NEXTL INSTRUCT You know that data mixed with instructions is just a performance KILLER on modern CPUs? They have separate i- and data caches, and mingling the two makes a mess that must be straightened out, at a cost of CPU cycles. Charles -----Original Message----- From: IBM Mainframe Assembler List [mailto:[email protected]] On Behalf Of Keith Moe Sent: Wednesday, August 1, 2018 12:06 PM To: [email protected] Subject: Re: EQU * considered harmful I have been using label DS 0H for instruction labels just about forever and will continue to do so until I retire. That said, the label has the attribute of a half word, not the attribute of an instruction label. Putting the label on the actual instruction has the "problem" of inserting code at the label before the existing instruction, which the separate label simplifies. That said, I wish the assembler had an "instruction" assembler statement that could be used to assign labels that would receive the attribute of the immediate following instruction. It would also force half word alignment if necessary. Example: LABEL INSTRUCT CLI JNE NEXTL whatever J NEXTL DC CL(oddnumber)' ' NEXTL INSTRUCT ...... The LABEL and NEXTL symbols would be assigned the attribute of the immediately following instruction (including length of the instruction). The assembler could then have an option that would flag branch and execute references to labels that are NOT instructions (and ACONTROL to turn it on and off). If the first statement the generates something is not an instruction, this could also be considered a warning situation. In the situation where the instruction is generated via non-standard means (i.e., DC X'xxxx' because the Opcode does not have a mnemonic), the ACONTROL function could be used to avoid the warning. Keith Moe BMC Software, Inc. --------------------------------------------
