Hello!
Attached patch extends TARGET_READ_MODIFY{,_WRITE} peepholes to handle
all integer modes, while also taking care not to introduce additional
QImode register stalls.
While looking at the insn enable condition, I noticed that we don't
use "probe_stack" pattern any more, as the stack check loop is now
implemented in a different way.
2016-04-28 Uros Bizjak <ubiz...@gmail.com>
* config/i386/i386.md (peephole2s for operations with memory inputs):
Use SWI mode iterator.
(peephole2s for operations with memory outputs): Ditto.
Do not check for stack checking probe.
(probe_stack): Remove expander.
Patch was bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.
Committed to mainline SVN.
Uros.
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md (revision 235582)
+++ config/i386/i386.md (working copy)
@@ -17552,20 +17552,6 @@
DONE;
})
-;; Use IOR for stack probes, this is shorter.
-(define_expand "probe_stack"
- [(match_operand 0 "memory_operand")]
- ""
-{
- rtx (*gen_ior3) (rtx, rtx, rtx);
-
- gen_ior3 = (GET_MODE (operands[0]) == DImode
- ? gen_iordi3 : gen_iorsi3);
-
- emit_insn (gen_ior3 (operands[0], operands[0], const0_rtx));
- DONE;
-})
-
(define_insn "adjust_stack_and_probe<mode>"
[(set (match_operand:P 0 "register_operand" "=r")
(unspec_volatile:P [(match_operand:P 1 "register_operand" "0")]
@@ -17894,11 +17880,11 @@
;; Don't do logical operations with memory inputs.
(define_peephole2
- [(match_scratch:SI 2 "r")
- (parallel [(set (match_operand:SI 0 "register_operand")
- (match_operator:SI 3 "arith_or_logical_operator"
+ [(match_scratch:SWI 2 "<r>")
+ (parallel [(set (match_operand:SWI 0 "register_operand")
+ (match_operator:SWI 3 "arith_or_logical_operator"
[(match_dup 0)
- (match_operand:SI 1 "memory_operand")]))
+ (match_operand:SWI 1 "memory_operand")]))
(clobber (reg:CC FLAGS_REG))])]
"!(TARGET_READ_MODIFY || optimize_insn_for_size_p ())"
[(set (match_dup 2) (match_dup 1))
@@ -17907,10 +17893,10 @@
(clobber (reg:CC FLAGS_REG))])])
(define_peephole2
- [(match_scratch:SI 2 "r")
- (parallel [(set (match_operand:SI 0 "register_operand")
- (match_operator:SI 3 "arith_or_logical_operator"
- [(match_operand:SI 1 "memory_operand")
+ [(match_scratch:SWI 2 "<r>")
+ (parallel [(set (match_operand:SWI 0 "register_operand")
+ (match_operator:SWI 3 "arith_or_logical_operator"
+ [(match_operand:SWI 1 "memory_operand")
(match_dup 0)]))
(clobber (reg:CC FLAGS_REG))])]
"!(TARGET_READ_MODIFY || optimize_insn_for_size_p ())"
@@ -17962,15 +17948,13 @@
; the same decoder scheduling characteristics as the original.
(define_peephole2
- [(match_scratch:SI 2 "r")
- (parallel [(set (match_operand:SI 0 "memory_operand")
- (match_operator:SI 3 "arith_or_logical_operator"
+ [(match_scratch:SWI 2 "<r>")
+ (parallel [(set (match_operand:SWI 0 "memory_operand")
+ (match_operator:SWI 3 "arith_or_logical_operator"
[(match_dup 0)
- (match_operand:SI 1 "nonmemory_operand")]))
+ (match_operand:SWI 1 "<nonmemory_operand>")]))
(clobber (reg:CC FLAGS_REG))])]
- "!(TARGET_READ_MODIFY_WRITE || optimize_insn_for_size_p ())
- /* Do not split stack checking probes. */
- && GET_CODE (operands[3]) != IOR && operands[1] != const0_rtx"
+ "!(TARGET_READ_MODIFY_WRITE || optimize_insn_for_size_p ())"
[(set (match_dup 2) (match_dup 0))
(parallel [(set (match_dup 2)
(match_op_dup 3 [(match_dup 2) (match_dup 1)]))
@@ -17978,15 +17962,13 @@
(set (match_dup 0) (match_dup 2))])
(define_peephole2
- [(match_scratch:SI 2 "r")
- (parallel [(set (match_operand:SI 0 "memory_operand")
- (match_operator:SI 3 "arith_or_logical_operator"
- [(match_operand:SI 1 "nonmemory_operand")
+ [(match_scratch:SWI 2 "<r>")
+ (parallel [(set (match_operand:SWI 0 "memory_operand")
+ (match_operator:SWI 3 "arith_or_logical_operator"
+ [(match_operand:SWI 1 "<nonmemory_operand>")
(match_dup 0)]))
(clobber (reg:CC FLAGS_REG))])]
- "!(TARGET_READ_MODIFY_WRITE || optimize_insn_for_size_p ())
- /* Do not split stack checking probes. */
- && GET_CODE (operands[3]) != IOR && operands[1] != const0_rtx"
+ "!(TARGET_READ_MODIFY_WRITE || optimize_insn_for_size_p ())"
[(set (match_dup 2) (match_dup 0))
(parallel [(set (match_dup 2)
(match_op_dup 3 [(match_dup 1) (match_dup 2)]))
