This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [patch 1/2] AMD bdver2 processors - BMI


On Tue, Nov 2, 2010 at 10:53 AM, Richard Henderson <rth@redhat.com> wrote:
> On 11/02/2010 05:27 AM, Quentin Neill wrote:
>> Actually BSF indexes the lowest set bit, TZCNT counts zeros, so if I'm
>> thinking clearly BSF(X)==TZCNT(X)+1
>
> Nope. ?Looking carefully the differences are:
>
> ? ? ? ? ? ? ? ?BSF ? ? ? ? ? ? ? ? ? ? TZCNT
> Result for 0 ? ?Undefined ? ? ? ? ? ? ? Operand-Width
> ZF ? ? ? ? ? ? ?Set iff 0 input ? ? ? ? Set iff 0 output
> CF ? ? ? ? ? ? ?Undefined ? ? ? ? ? ? ? Set iff 0 input
>
> otherwise the actual value result is identical.

Thanks, I misread the BSF definition, thinking it was indexed off bit
1.  "Looking carefully" is the key :)


>>> #define CTZ_DEFINED_VALUE_AT_ZERO(MODE, VALUE) ...[snip]...
>> I take it his goes in defaults.h? ?How do I test this?
> This goes in i386.h.  Test this by seeing that __builtin_ctz
> with a constant operand 0 gets folded properly.

Okay, thanks.

Any hints on what test case this would go in?

> Note that
> there's a CLZ_DEFINED_VALUE_AT_ZERO as well, which would be
> used for the LZCNT instruction.

To be clear, this needs to be defined and added to i386.h as well.

I don't see where any tests exercise the existIng LZCNT insn yet, so
I'll add those too.

Going back to one of last week's replies...

On Fri, Oct 22, 2010 at 3:59 PM, Richard Henderson <rth@redhat.com> wrote:
> (define_insn "ctz<mode>2"
>  [(set (match_operand:SWI48 0 "register_operand" "=r")
>        (ctz:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "rm")))
>   (clobber (reg:CC FLAGS_REG))]
>  ""
> {
>  if (TARGET_BMI)
>    return "tzcnt{<imodesuffix>}\t{%1, %0|%0, %1}";
>  else
>    return "bsf{<imodesuffix>}\t{%1, %0|%0, %1}";
> }
>  [(set_attr "type" "alu1")
>   (set_attr "prefix_0f" "1")
>   (set (attr "prefix_rep" (symbol_ref "TARGET_BMI"))
>   (set_attr "mode" "<MODE>")])


One more question:

The line that said
    (set (attr "prefix_rep" (symbol_ref "TARGET_BMI"))

ended up being
    (set (attr "prefix_rep") (symbol_ref "TARGET_BMI"))

but my question is how is the "prefix_rep" attribute used?

-- 
Quentin


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]