rs6000.md (movdf_hardfloat32): Add a comment explaining the register ordering preferences.

2012-11-20  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* config/rs6000/rs6000.md (movdf_hardfloat32): Add a comment
	explaining the register ordering preferences.

From-SVN: r193673
This commit is contained in:
Michael Meissner 2012-11-20 19:29:02 +00:00 committed by Michael Meissner
parent 7139194bf9
commit 96ceaa374e
2 changed files with 13 additions and 0 deletions

View File

@ -1,3 +1,8 @@
2012-11-20 Michael Meissner <meissner@linux.vnet.ibm.com>
* config/rs6000/rs6000.md (movdf_hardfloat32): Add a comment
explaining the register ordering preferences.
2012-11-20 Aldy Hernandez <aldyh@redhat.com>
PR tree-optimization/55350

View File

@ -8018,6 +8018,14 @@
;; Don't have reload use general registers to load a constant. It is
;; less efficient than loading the constant into an FP register, since
;; it will probably be used there.
;; The move constraints are ordered to prefer floating point registers before
;; general purpose registers to avoid doing a store and a load to get the value
;; into a floating point register when it is needed for a floating point
;; operation. Prefer traditional floating point registers over VSX registers,
;; since the D-form version of the memory instructions does not need a GPR for
;; reloading.
(define_insn "*movdf_hardfloat32"
[(set (match_operand:DF 0 "nonimmediate_operand" "=m,d,d,ws,?wa,Z,?Z,ws,?wa,wa,Y,r,!r,!r,!r,!r")
(match_operand:DF 1 "input_operand" "d,m,d,Z,Z,ws,wa,ws,wa,j,r,Y,r,G,H,F"))]