diff mbox

[AArch64] Implement popcount pattern

Message ID CO2PR07MB2694C853BCFC5E83EF1E3D3583980@CO2PR07MB2694.namprd07.prod.outlook.com
State New
Headers show

Commit Message

Hurugalawadi, Naveen Dec. 12, 2016, 3:16 a.m. UTC 
Hi,

Please find attached the patch that implements the support for popcount
patterns in AArch64.

The implementation improves OVS-DPDK on ThunderX by 3%. It would have a
similar effect on other AArch64 targets.

Please review the patch and let us know if its okay?

2016-12-12  Andrew Pinski  <apinski@cavium.com>

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

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

Patch

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 65eb326..c688ddc 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -3785,6 +3785,39 @@ 
   }
 )
 
+/* Pop count be done via the pop count instruction in NEON. */
+/*
+  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/gcc.target/aarch64/popcount.c b/gcc/testsuite/gcc.target/aarch64/popcount.c
new file mode 100644
index 0000000..2d71168
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcount.c
@@ -0,0 +1,10 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int foo(int x)
+{
+  return __builtin_popcount(x);
+}
+
+/* { dg-final { scan-assembler-not "popcountdi2" } } */
+/* { dg-final { scan-assembler "cnt\t" } } */