i386: Optimize blsi followed by comparison [PR98567]

The BLSI instruction sets SF and ZF based on the result and clears OF.
CF is set to something unrelated.

The following patch optimizes BLSI followed by comparison, so we don't need
to emit a TEST insn in between.

2021-01-07  Jakub Jelinek  <jakub@redhat.com>

	PR target/98567
	* config/i386/i386.md (*bmi_blsi_<mode>_cmp, *bmi_blsi_<mode>_ccno):
	New define_insn patterns.

	* gcc.target/i386/pr98567-1.c: New test.
	* gcc.target/i386/pr98567-2.c: New test.

3 files changed, 91 insertions, 0 deletions

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 6f6af8c..c102312 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14563,6 +14563,35 @@
    (set_attr "btver2_decode" "double")
    (set_attr "mode" "<MODE>")])
 
+(define_insn "*bmi_blsi_<mode>_cmp"
+  [(set (reg FLAGS_REG)
+	(compare
+	  (and:SWI48
+	    (neg:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "rm"))
+	    (match_dup 1))
+	  (const_int 0)))
+   (set (match_operand:SWI48 0 "register_operand" "=r")
+	(and:SWI48 (neg:SWI48 (match_dup 1)) (match_dup 1)))]
+   "TARGET_BMI && ix86_match_ccmode (insn, CCNOmode)"
+   "blsi\t{%1, %0|%0, %1}"
+  [(set_attr "type" "bitmanip")
+   (set_attr "btver2_decode" "double")
+   (set_attr "mode" "<MODE>")])
+
+(define_insn "*bmi_blsi_<mode>_ccno"
+  [(set (reg FLAGS_REG)
+	(compare
+	  (and:SWI48
+	    (neg:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "rm"))
+	    (match_dup 1))
+	  (const_int 0)))
+   (clobber (match_scratch:SWI48 0 "=r"))]
+   "TARGET_BMI && ix86_match_ccmode (insn, CCNOmode)"
+   "blsi\t{%1, %0|%0, %1}"
+  [(set_attr "type" "bitmanip")
+   (set_attr "btver2_decode" "double")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn "*bmi_blsmsk_<mode>"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
         (xor:SWI48
diff --git a/gcc/testsuite/gcc.target/i386/pr98567-1.c b/gcc/testsuite/gcc.target/i386/pr98567-1.c
new file mode 100644
index 0000000..ef53ec7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr98567-1.c
@@ -0,0 +1,31 @@
+/* PR target/98567 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbmi -fno-stack-protector" } */
+/* { dg-final { scan-assembler-times "\tblsi" 4 } } */
+/* { dg-final { scan-assembler-times "\tsetne\t" 2 } } */
+/* { dg-final { scan-assembler-times "\tsete\t" 2 } } */
+/* { dg-final { scan-assembler-not "\ttest\[ld]" } } */
+
+int
+foo (unsigned long x)
+{
+  return (-x & x) == 0;
+}
+
+int
+bar (unsigned int x)
+{
+  return (-x & x) == 0;
+}
+
+int
+baz (unsigned long x)
+{
+  return (x & -x) != 0;
+}
+
+int
+qux (unsigned int x)
+{
+  return 0 != (x & -x);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr98567-2.c b/gcc/testsuite/gcc.target/i386/pr98567-2.c
new file mode 100644
index 0000000..dccb24f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr98567-2.c
@@ -0,0 +1,31 @@
+/* PR target/98567 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbmi -fno-stack-protector" } */
+/* { dg-final { scan-assembler-times "\tblsi" 4 } } */
+/* { dg-final { scan-assembler-times "\tsetle\t" 2 } } */
+/* { dg-final { scan-assembler-times "\tsetg\t" 2 } } */
+/* { dg-final { scan-assembler-not "\ttest\[ld]" } } */
+
+int
+foo (unsigned long x)
+{
+  return 0 >= (int) (-x & x);
+}
+
+int
+bar (unsigned int x)
+{
+  return (int) (-x & x) <= 0;
+}
+
+int
+baz (unsigned long x)
+{
+  return (int) (x & -x) > 0;
+}
+
+int
+qux (unsigned int x)
+{
+  return 0 < (int) (x & -x);
+}