x86: improve lea peepholes

gcc.target/i386/lea-3.c fails on ia32 with PIE enabled by default.
There are two reasons for that:

- setting up the PIC register requires one addl instruction, and the
  testcase wants none

- the expected lea-combining peephole doesn't get applied for two
  reasons:

-- the second insn of the pair that could be turned into a single lea
   doesn't clobber CC, but the existing peephole2 requires an add with
   such a clobber

-- the first and second insns set different regs, and the existing
   peephole2 requires them to be the same

Add extra peephole2s for when the second insn doesn't clobber CC, and
for when the first set reg is different, but it dies at the second
insn.

Adjust lea-3.c to run with -fno-PIE, and add lea-4.c with -fPIE.

The last of the newly-added peephole2s, that enables lea-4.c to pass,
also hits during an i686-linux-gnu bootstrap (without PIE enabled),
while building shared libraries for the target.  I haven't been able
to exercise the other 2, but I haven't tried very hard, and I see no
why they couldn't possibly hit, so I left them in.

for  gcc/ChangeLog

	* config/i386/i386.md (lea peephole2): Add 3 new variants.

for  gcc/testsuite/ChangeLog

	* gcc.target/i386/lea-3.c: Add -fno-PIE.
	* gcc.target/i386/lea-4.c: New, with -fPIE.

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index df7135f84d47828d3244df89086c1ff3cb6ed496..b5d838934251c5e4b6f60cbe442cbc1732505bcc 100644 (file)
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -6452,6 +6452,48 @@
   [(set (match_dup 0) (plus:SWI48 (plus:SWI48 (match_dup 0)
                                              (match_dup 1))
                                  (match_dup 2)))])
+
+(define_peephole2
+  [(parallel [(set (match_operand:SWI48 0 "register_operand")
+                  (plus:SWI48 (match_dup 0)
+                              (match_operand 1 "register_operand")))
+             (clobber (reg:CC FLAGS_REG))])
+   (set (match_dup 0)
+       (plus:SWI48 (match_dup 0)
+                   (match_operand 2 "x86_64_immediate_operand")))]
+  "!TARGET_AVOID_LEA_FOR_ADDR || optimize_function_for_size_p (cfun)"
+  [(set (match_dup 0) (plus:SWI48 (plus:SWI48 (match_dup 0)
+                                             (match_dup 1))
+                                 (match_dup 2)))])
+
+(define_peephole2
+  [(parallel [(set (match_operand:SWI48 0 "register_operand")
+                  (plus:SWI48 (match_dup 0)
+                              (match_operand 1 "register_operand")))
+             (clobber (reg:CC FLAGS_REG))])
+   (parallel [(set (match_operand:SWI48 3 "register_operand")
+                  (plus:SWI48 (match_dup 0)
+                              (match_operand 2 "x86_64_immediate_operand")))
+             (clobber (reg:CC FLAGS_REG))])]
+  "(!TARGET_AVOID_LEA_FOR_ADDR || optimize_function_for_size_p (cfun))
+   && peep2_reg_dead_p (2, operands[0])"
+  [(set (match_dup 3) (plus:SWI48 (plus:SWI48 (match_dup 0)
+                                             (match_dup 1))
+                                 (match_dup 2)))])
+
+(define_peephole2
+  [(parallel [(set (match_operand:SWI48 0 "register_operand")
+                  (plus:SWI48 (match_dup 0)
+                              (match_operand 1 "register_operand")))
+             (clobber (reg:CC FLAGS_REG))])
+   (set (match_operand:SWI48 3 "register_operand")
+       (plus:SWI48 (match_dup 0)
+                   (match_operand 2 "x86_64_immediate_operand")))]
+  "(!TARGET_AVOID_LEA_FOR_ADDR || optimize_function_for_size_p (cfun))
+   && peep2_reg_dead_p (2, operands[0])"
+  [(set (match_dup 3) (plus:SWI48 (plus:SWI48 (match_dup 0)
+                                             (match_dup 1))
+                                 (match_dup 2)))])
 \f
 ;; Add instructions
 

diff --git a/gcc/testsuite/gcc.target/i386/lea-3.c b/gcc/testsuite/gcc.target/i386/lea-3.c
index 84e66b00fc25e539861254bd022ce2258edcc9ed..ce50531f935458cc53a304409c62cec7448cf451 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/lea-3.c
+++ b/gcc/testsuite/gcc.target/i386/lea-3.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2" } */
+/* { dg-options "-O2 -fno-PIE" } */
 
 int m;
 

diff --git a/gcc/testsuite/gcc.target/i386/lea-4.c b/gcc/testsuite/gcc.target/i386/lea-4.c
new file mode 100644 (file)
index 0000000..7bb2cec
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/lea-4.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fPIE" } */
+/* Same as lea-3.c, but with -fPIE.  On ia32, that requires setting up the PIC
+   register, which requires an addl instruction.  */
+
+int m;
+
+int foo(int y)
+{
+  return (m+y-1)/y;
+}
+
+/* { dg-final { scan-assembler "leal" } } */
+/* { dg-final { scan-assembler-not "addl" { target lp64 } } } */
+/* { dg-final { scan-assembler-times "addl" 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-not "subl" } } */