[PATCH] Optimize kmov + kmov + or to kortest.

[liuhongt]

For instruction sequence like
        kmovb   %k0, %edx
        kmovb   %k1, %ecx
        orb     %cl, %dl
        je      .L5

if only CCZ is cared, it can be optimized to

        kortestb %k1, %k0
        je      .L5

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32}.
Ready push to trunk.

gcc/ChangeLog:

        * config/i386/i386.md (*ior<mode>_ccz_1): New define_insn.

gcc/testsuite/ChangeLog:

        * gcc.target/i386/kortest_ccz-1.c: New test.
---
 gcc/config/i386/i386.md                       | 16 ++++++++++++++++
 gcc/testsuite/gcc.target/i386/kortest_ccz-1.c | 13 +++++++++++++
 2 files changed, 29 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/kortest_ccz-1.c

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 3ea2439526b..ae26ef02c22 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14203,6 +14203,22 @@ (define_insn "*<code>si_2_zext_imm"
    (set_attr "isa" "*,apx_ndd")
    (set_attr "mode" "SI")])
 
+;; It must be put before *<code><mode>_3, the blow one.
+(define_insn "*ior<mode>_ccz_1"
+  [(set (reg:CCZ FLAGS_REG)
+       (compare:CCZ
+        (ior:SWI1248_AVX512BWDQ_64
+         (match_operand:SWI1248_AVX512BWDQ_64 1 "nonimmediate_operand" "%0,?k")
+         (match_operand:SWI1248_AVX512BWDQ_64 2 "<general_operand>" "<g>, k"))
+        (const_int 0)))
+   (clobber (match_scratch:SWI1248_AVX512BWDQ_64 0 "=<r>, k"))]
+  "TARGET_AVX512F && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
+  "@
+   or{<imodesuffix>}\t{%2, %0|%0, %2}
+   kortest<mskmodesuffix>\t{%1, %2|%2, %1}"
+  [(set_attr "type" "alu,msklog")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn "*<code><mode>_3"
   [(set (reg FLAGS_REG)
        (compare (any_or:SWI
diff --git a/gcc/testsuite/gcc.target/i386/kortest_ccz-1.c 
b/gcc/testsuite/gcc.target/i386/kortest_ccz-1.c
new file mode 100644
index 00000000000..0f8d4bf9f22
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/kortest_ccz-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-march=x86-64-v4 -O3" } */
+/* { dg-final { scan-assembler-not "kmov" } } */
+/* { dg-final { scan-assembler "kortest" } } */
+
+int
+foo (int *__restrict a, int* __restrict d, int b, int c, int n)
+{
+  for (int i = 0; i != 10000; i++)
+    if (a[i] > b || d[i] > c)
+      return 1;
+  return 0;
+}
-- 
2.34.1