committed: cris: New peephole2 movulsr + test-case.

Message ID 202007060042.0660gG69031810@ignucius.se.axis.com
State New
Headers show
Series
  • committed: cris: New peephole2 movulsr + test-case.
Related show

Commit Message

Peter Bergner via Gcc-patches July 6, 2020, 12:42 a.m.
(The previous patch was also committed, FWIW, I just forgot to
mention it.)

Combine likes to change a zero-extension / and + shift as seen
in the test-case source to a logical shift followed by an and of
the shifted mask, like:
 lsrq 1,r0
 and.d 0x7f,r0

This was observed in the hot loop of coremark crcu16 and crcu32,
when doing other changes affecting instruction selection.  While
fixable by other means (like instruction costs or combine
patches), I wanted to break this out from those "other means".
The similarity to extant peephole optimizations is not
deliberate.

I noticed some paths to other peephole2 test-cases have changed
due to moves and renaming, so I updated them.

gcc:
	* config/cris/cris.md (movulsr): New peephole2.

gcc/testsuite:
	* gcc.target/cris/peep2-movulsr.c: New test.
---
 gcc/config/cris/cris.md                       | 45 ++++++++++++++++++++++++---
 gcc/testsuite/gcc.target/cris/peep2-movulsr.c | 19 +++++++++++
 2 files changed, 60 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/cris/peep2-movulsr.c

-- 
2.11.0

Patch

diff --git a/gcc/config/cris/cris.md b/gcc/config/cris/cris.md
index ae6a27f5f2c..c36a5402be3 100644
--- a/gcc/config/cris/cris.md
+++ b/gcc/config/cris/cris.md
@@ -2515,8 +2515,45 @@  (define_expand "casesi"
 
 ;; We have trouble with and:s and shifts.  Maybe something is broken in
 ;; gcc?  Or it could just be that bit-field insn expansion is a bit
-;; suboptimal when not having extzv insns.
-;; Testcase for the following four peepholes: gcc.dg/cris-peep2-xsrand.c
+;; suboptimal when not having extzv insns.  Or combine being over-eager
+;; to canonicalize to "and", and ignorant on the benefits of the right
+;; mixture of "and" and "zero-extend".
+
+;; Testcase for the following peephole: gcc.target/cris/peep2-movulsr.c
+
+;; Where equivalent and where the "and" argument doesn't fit "andq" but
+;; is 16 bits or smaller, replace the "and" with a zero-extend preceding
+;; the shift.  A zero-extend is shorter and faster than "and" with a
+;; 32-bit argument.
+
+(define_peephole2 ; movulsr
+  [(parallel
+    [(set (match_operand:SI 0 "register_operand")
+	  (lshiftrt:SI (match_dup 0)
+		       (match_operand:SI 1 "const_int_operand")))
+     (clobber (reg:CC CRIS_CC0_REGNUM))])
+   (parallel
+    [(set (match_dup 0)
+	  (and:SI (match_dup 0)
+		  (match_operand 2 "const_int_operand")))
+     (clobber (reg:CC CRIS_CC0_REGNUM))])]
+  "INTVAL (operands[2]) > 31 && INTVAL (operands[2]) <= 0xffff
+   && (((INTVAL (operands[2]) <= 0xff ? 0xff : 0xffff) >> INTVAL (operands[1]))
+       == INTVAL (operands[2]))"
+  [(parallel
+    ;; The zero-extend is expressed as an "and", only because that's easier
+    ;; than messing with zero-extend of a subreg.
+    [(set (match_dup 0) (and:SI (match_dup 0) (match_dup 3)))
+     (clobber (reg:CC CRIS_CC0_REGNUM))])
+   (parallel
+    [(set (match_dup 0) (lshiftrt:SI (match_dup 0) (match_dup 1)))
+     (clobber (reg:CC CRIS_CC0_REGNUM))])]
+{
+  operands[3]
+    = INTVAL (operands[2]) <= 0xff ? GEN_INT (0xff) :  GEN_INT (0xffff);
+})
+
+;; Testcase for the following four peepholes: gcc.target/cris/peep2-xsrand.c
 
 (define_peephole2 ; asrandb
   [(parallel
@@ -2635,7 +2672,7 @@  (define_peephole2 ; lsrandw
 ;;   move.d reg_or_mem,reg_32
 ;;   and.d const_32__65535,reg_32
 ;; Fix it with these two peephole2's.
-;; Testcases: gcc.dg/cris-peep2-andu1.c gcc.dg/cris-peep2-andu2.c
+;; Testcases: gcc.target/cris/peep2-andu1.c gcc.target/cris/peep2-andu2.c
 
 (define_peephole2 ; andu
   [(parallel
@@ -2679,7 +2716,7 @@  (define_peephole2 ; andu
 						? QImode : amode)));
 })
 
-;; Since r186861, gcc.dg/cris-peep2-andu2.c trigs this pattern, with which
+;; Since r186861, gcc.target/cris/peep2-andu2.c trigs this pattern, with which
 ;; we fix up e.g.:
 ;;  movu.b 254,$r9.
 ;;  and.d $r10,$r9
diff --git a/gcc/testsuite/gcc.target/cris/peep2-movulsr.c b/gcc/testsuite/gcc.target/cris/peep2-movulsr.c
new file mode 100644
index 00000000000..a19afce3982
--- /dev/null
+++ b/gcc/testsuite/gcc.target/cris/peep2-movulsr.c
@@ -0,0 +1,19 @@ 
+/* { dg-do compile } */
+/* { dg-final { scan-assembler "movu.w " } } */
+/* { dg-final { scan-assembler "movu.b " } } */
+/* { dg-final { scan-assembler-not "and.. " } } */
+/* { dg-options "-O2" } */
+
+/* Test the "movulsrb", "movulsrw" peephole2:s trivially.  */
+
+unsigned int
+movulsrb (unsigned int x)
+{
+  return (x & 255) >> 1;
+}
+
+unsigned int
+movulsrw (unsigned int x)
+{
+  return (x & 65535) >> 4;
+}