[PATCH] [x86]Don't optimize cmp mem, 0 to load mem, reg + test reg, reg

[liuhongt <hongtao.liu@intel.com>]

There's peephole2 submit in 1990s which split cmp mem, 0 to load mem,
reg + test reg, reg. I don't know exact reason why gcc do this.

For latest x86 processors, ciscization should help processor frontend
also codesize, for processor backend, they should be the same(has same
uops).

So the patch deleted the peephole2, and also modify another splitter to
generate more cmp mem, 0 for 32-bit target.

It will help instruction fetch.

for minmax-1.c minmax-2.c minmax-10, pr96891.c, it's supposed to scan there's no
comparison to 1 or -1, so adjust the testcase since under 32-bit
target, we now generate cmp mem, 0 instead of load + test.

Similar for pr78035.c.

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}
No performance impact for SPEC2017 on ICX/Znver3.

Ok for trunk?

gcc/ChangeLog:

	* config/i386/i386.md (*<code><mode>3_1): Replace
	register_operand with nonimmediate_operand for operand 1. Also
	force_reg it when mode is QImode.
	(define_peephole2): Deleted related peephole2.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/minmax-1.c: Scan-assemble-not for cmp with 1
	or -1, also don't scan-assembler test for ia32.
	* gcc.target/i386/minmax-10.c: Ditto.
	* gcc.target/i386/minmax-2.c: Ditto.
	* gcc.target/i386/pr78035.c: Ditto.
	* gcc.target/i386/pr96861.c: Scan either cmp or test 3 times.
---
 gcc/config/i386/i386.md                   | 18 +++++-------------
 gcc/testsuite/gcc.target/i386/minmax-1.c  |  4 ++--
 gcc/testsuite/gcc.target/i386/minmax-10.c |  4 ++--
 gcc/testsuite/gcc.target/i386/minmax-2.c  |  4 ++--
 gcc/testsuite/gcc.target/i386/pr78035.c   |  2 +-
 gcc/testsuite/gcc.target/i386/pr96861.c   |  4 ++--
 6 files changed, 14 insertions(+), 22 deletions(-)

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 1be9b669909..93b905beb72 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -21871,7 +21871,7 @@ (define_insn_and_split "*<code><dwi>3_doubleword"
 (define_insn_and_split "*<code><mode>3_1"
   [(set (match_operand:SWI 0 "register_operand")
 	(maxmin:SWI
-	  (match_operand:SWI 1 "register_operand")
+	  (match_operand:SWI 1 "nonimmediate_operand")
 	  (match_operand:SWI 2 "general_operand")))
    (clobber (reg:CC FLAGS_REG))]
   "TARGET_CMOVE
@@ -21886,9 +21886,12 @@ (define_insn_and_split "*<code><mode>3_1"
 {
   machine_mode mode = <MODE>mode;
   rtx cmp_op = operands[2];
-
   operands[2] = force_reg (mode, cmp_op);
 
+  /* movqicc_noc only support register_operand for op1.  */
+  if (mode == QImode)
+    operands[1] = force_reg (mode, operands[1]);
+
   enum rtx_code code = <maxmin_rel>;
 
   if (cmp_op == const1_rtx)
@@ -22482,17 +22485,6 @@ (define_peephole2
   [(set (match_dup 2) (match_dup 1))
    (set (match_dup 0) (match_dup 2))])
 
-;; Don't compare memory with zero, load and use a test instead.
-(define_peephole2
-  [(set (match_operand 0 "flags_reg_operand")
- 	(match_operator 1 "compare_operator"
-	  [(match_operand:SI 2 "memory_operand")
-	   (const_int 0)]))
-   (match_scratch:SI 3 "r")]
-  "optimize_insn_for_speed_p () && ix86_match_ccmode (insn, CCNOmode)"
-  [(set (match_dup 3) (match_dup 2))
-   (set (match_dup 0) (match_op_dup 1 [(match_dup 3) (const_int 0)]))])
-
 ;; NOT is not pairable on Pentium, while XOR is, but one byte longer.
 ;; Don't split NOTs with a displacement operand, because resulting XOR
 ;; will not be pairable anyway.
diff --git a/gcc/testsuite/gcc.target/i386/minmax-1.c b/gcc/testsuite/gcc.target/i386/minmax-1.c
index 0ec35b1c5a1..840b32c5414 100644
--- a/gcc/testsuite/gcc.target/i386/minmax-1.c
+++ b/gcc/testsuite/gcc.target/i386/minmax-1.c
@@ -1,7 +1,7 @@
 /* { dg-do compile } */
 /* { dg-options "-O2 -march=opteron -mno-stv" } */
-/* { dg-final { scan-assembler "test" } } */
-/* { dg-final { scan-assembler-not "cmp" } } */
+/* { dg-final { scan-assembler "test" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not {(?n)cmp.*[$]+1} } } */
 #define max(a,b) (((a) > (b))? (a) : (b))
 int
 t(int a)
diff --git a/gcc/testsuite/gcc.target/i386/minmax-10.c b/gcc/testsuite/gcc.target/i386/minmax-10.c
index b044462c5a9..1dd2eedf435 100644
--- a/gcc/testsuite/gcc.target/i386/minmax-10.c
+++ b/gcc/testsuite/gcc.target/i386/minmax-10.c
@@ -34,5 +34,5 @@ unsigned int umin1(unsigned int x)
   return min(x,1);
 }
 
-/* { dg-final { scan-assembler-times "test" 6 } } */
-/* { dg-final { scan-assembler-not "cmp" } } */
+/* { dg-final { scan-assembler-times "test" 6 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not {(?n)cmp.*1} } } */
diff --git a/gcc/testsuite/gcc.target/i386/minmax-2.c b/gcc/testsuite/gcc.target/i386/minmax-2.c
index af9baeaaf7c..2c82f6cecb9 100644
--- a/gcc/testsuite/gcc.target/i386/minmax-2.c
+++ b/gcc/testsuite/gcc.target/i386/minmax-2.c
@@ -1,7 +1,7 @@
 /* { dg-do compile } */
 /* { dg-options "-O2 -mno-stv" } */
-/* { dg-final { scan-assembler "test" } } */
-/* { dg-final { scan-assembler-not "cmp" } } */
+/* { dg-final { scan-assembler "test" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not {(?n)cmp.*[$]1} } } */
 #define max(a,b) (((a) > (b))? (a) : (b))
 unsigned int
 t(unsigned int a)
diff --git a/gcc/testsuite/gcc.target/i386/pr78035.c b/gcc/testsuite/gcc.target/i386/pr78035.c
index 7d3a983b218..d543d3f1d38 100644
--- a/gcc/testsuite/gcc.target/i386/pr78035.c
+++ b/gcc/testsuite/gcc.target/i386/pr78035.c
@@ -22,4 +22,4 @@ int bar ()
 }
 
 /* We should not optimize away either comparison.  */
-/* { dg-final { scan-assembler-times "cmp" 2 } } */
+/* { dg-final { scan-assembler-times "(?:cmp|test)" 3 } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr96861.c b/gcc/testsuite/gcc.target/i386/pr96861.c
index 7b7aeccb83c..8c0f0841f7d 100644
--- a/gcc/testsuite/gcc.target/i386/pr96861.c
+++ b/gcc/testsuite/gcc.target/i386/pr96861.c
@@ -34,5 +34,5 @@ unsigned int umin1(unsigned int x)
   return min(x,1);
 }
 
-/* { dg-final { scan-assembler-times "test" 6 } } */
-/* { dg-final { scan-assembler-not "cmp" } } */
+/* { dg-final { scan-assembler-times "test" 6 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not {(?n)cmp.*[$]+1} } } */
-- 
2.18.1