From 9d5019a1968ce2d54d054df223be16ca832d913e Mon Sep 17 00:00:00 2001
From: Andrew Pinski <apinski@cavium.com>
Date: Wed, 8 Feb 2017 02:54:17 +0000
Subject: [PATCH] aarch64.md (popcount<mode>2): New pattern.

2016-02-07  Andrew Pinski  <apinski@cavium.com>

gcc
	* config/aarch64/aarch64.md (popcount<mode>2): New pattern.

gcc/testsuite
	* gcc.target/aarch64/popcount.c : New Testcase.

From-SVN: r245267
---
 gcc/ChangeLog                             |  4 +++
 gcc/config/aarch64/aarch64.md             | 33 +++++++++++++++++++++++
 gcc/testsuite/ChangeLog                   |  4 +++
 gcc/testsuite/gcc.target/aarch64/popcnt.c | 23 ++++++++++++++++
 4 files changed, 64 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/popcnt.c

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index ead1661df3b..527143ac944 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2017-02-07  Andrew Pinski  <apinski@cavium.com>
+
+	* config/aarch64/aarch64.md (popcount<mode>2): New pattern.
+
 2017-02-07  Andrew Pinski  <apinski@cavium.com>
 
 	* config/aarch64/aarch64-cores.def (thunderx): Disable LSE.
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 7550c3e7c2b..5adc5edb8dd 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -3779,6 +3779,39 @@
   }
 )
 
+;; Pop count be done via the "CNT" instruction in AdvSIMD.
+;;
+;; MOV	v.1d, x0
+;; CNT	v1.8b, v.8b
+;; ADDV b2, v1.8b
+;; MOV	w0, v2.b[0]
+
+(define_expand "popcount<mode>2"
+  [(match_operand:GPI 0 "register_operand")
+   (match_operand:GPI 1 "register_operand")]
+  "TARGET_SIMD"
+{
+  rtx v = gen_reg_rtx (V8QImode);
+  rtx v1 = gen_reg_rtx (V8QImode);
+  rtx r = gen_reg_rtx (QImode);
+  rtx in = operands[1];
+  rtx out = operands[0];
+  if(<MODE>mode == SImode)
+    {
+      rtx tmp;
+      tmp = gen_reg_rtx (DImode);
+      /* If we have SImode, zero extend to DImode, pop count does
+         not change if we have extra zeros. */
+      emit_insn (gen_zero_extendsidi2 (tmp, in));
+      in = tmp;
+    }
+  emit_move_insn (v, gen_lowpart (V8QImode, in));
+  emit_insn (gen_popcountv8qi2 (v1, v));
+  emit_insn (gen_reduc_plus_scal_v8qi (r, v1));
+  emit_insn (gen_zero_extendqi<mode>2 (out, r));
+  DONE;
+})
+
 (define_insn "clrsb<mode>2"
   [(set (match_operand:GPI 0 "register_operand" "=r")
         (clrsb:GPI (match_operand:GPI 1 "register_operand" "r")))]
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 7d793de238f..81b25807dd0 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2017-02-07  Andrew Pinski  <apinski@cavium.com>
+
+	* gcc.target/aarch64/popcount.c : New Testcase.
+
 2017-02-07  Jakub Jelinek  <jakub@redhat.com>
 
 	PR rtl-optimization/79386
diff --git a/gcc/testsuite/gcc.target/aarch64/popcnt.c b/gcc/testsuite/gcc.target/aarch64/popcnt.c
new file mode 100644
index 00000000000..7e957966d8e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcnt.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int
+foo (int x)
+{
+  return __builtin_popcount (x);
+}
+
+long
+foo1 (long x)
+{
+  return __builtin_popcountl (x);
+}
+
+long long
+foo2 (long long x)
+{
+  return __builtin_popcountll (x);
+}
+
+/* { dg-final { scan-assembler-not "popcount" } } */
+/* { dg-final { scan-assembler-times "cnt\t" 3 } } */
-- 
2.30.2