PR target/11877: Use xor to write zero to memory with -Os

The following patch attempts to resolve PR target/11877 (without
triggering PR/23102).  On x86_64, writing an SImode or DImode zero
to memory uses an instruction encoding that is larger than first
clearing a register (using xor) then writing that to memory.  Hence,
after reload, the peephole2 pass can determine if there's a suitable
free register, and if so, use that to shrink the code size with -Os.

To improve code size, and avoid inserting a large number of xor
instructions (PR target/23102), this patch makes use of peephole2's
efficient pattern matching to use a single temporary for a run of
consecutive writes.  In theory, one could do better still with a
new target-specific pass, gated on -Os, to shrink these instructions
(like stv), but that's probably overkill for the little remaining
space savings.

Evaluating this patch on the CSiBE benchmark (v2.1.1) results in a
0.26% code size improvement (3715273 bytes down to 3705477) on x86_64
with -Os [saving 1 byte every 400].  549 of 894 tests improve, two
tests grow larger.  Analysis of these 2 pathological cases reveals
that although peephole2's match_scratch prefers to use a call-clobbered
register (to avoid requiring a new stack frame), very rarely this
interacts with GCC's shrink wrapping optimization, which may previously
have avoided saving/restoring a call clobbered register, such as %eax,
in the calling function.

2021-06-21  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	PR target/11877
	* config/i386/i386.md: New define_peephole2s to shrink writing
	1, 2 or 4 consecutive zeros to memory when optimizing for size.

gcc/testsuite/ChangeLog
	PR target/11877
	* gcc.target/i386/pr11877.c: New test case.

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 48532eb7ddf924de257e8f02000afd96013d1942..2333261a894b753c635e58129328c2195691fa01 100644 (file)
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -19357,6 +19357,42 @@
   ix86_expand_clear (operands[1]);
 })
 
+;; When optimizing for size, zeroing memory should use a register.
+(define_peephole2
+  [(match_scratch:SWI48 0 "r")
+   (set (match_operand:SWI48 1 "memory_operand" "") (const_int 0))
+   (set (match_operand:SWI48 2 "memory_operand" "") (const_int 0))
+   (set (match_operand:SWI48 3 "memory_operand" "") (const_int 0))
+   (set (match_operand:SWI48 4 "memory_operand" "") (const_int 0))]
+  "optimize_insn_for_size_p () && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(set (match_dup 1) (match_dup 0))
+   (set (match_dup 2) (match_dup 0))
+   (set (match_dup 3) (match_dup 0))
+   (set (match_dup 4) (match_dup 0))]
+{
+  ix86_expand_clear (operands[0]);
+})
+
+(define_peephole2
+  [(match_scratch:SWI48 0 "r")
+   (set (match_operand:SWI48 1 "memory_operand" "") (const_int 0))
+   (set (match_operand:SWI48 2 "memory_operand" "") (const_int 0))]
+  "optimize_insn_for_size_p () && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(set (match_dup 1) (match_dup 0))
+   (set (match_dup 2) (match_dup 0))]
+{
+  ix86_expand_clear (operands[0]);
+})
+
+(define_peephole2
+  [(match_scratch:SWI48 0 "r")
+   (set (match_operand:SWI48 1 "memory_operand" "") (const_int 0))]
+  "optimize_insn_for_size_p () && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(set (match_dup 1) (match_dup 0))]
+{
+  ix86_expand_clear (operands[0]);
+})
+
 ;; Reload dislikes loading constants directly into class_likely_spilled
 ;; hard registers.  Try to tidy things up here.
 (define_peephole2

diff --git a/gcc/testsuite/gcc.target/i386/pr11877.c b/gcc/testsuite/gcc.target/i386/pr11877.c
new file mode 100644 (file)
index 0000000..5a488cc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr11877.c
@@ -0,0 +1,16 @@
+/* PR target/11877 */
+/* { dg-do compile } */
+/* { dg-options "-Os" } */
+
+void foo (long long *p)
+{
+  *p = 0;
+}
+
+void bar (int *p)
+{
+  *p = 0;
+}
+
+/* { dg-final { scan-assembler-times "xorl\[ \t\]" 2 } } */
+/* { dg-final { scan-assembler-not "\\\$0," } } */