Hi Kyrill,
Thanks for reviewing the patch and your useful comments.
>> looks good to me if it has gone through the normal required
>> bootstrap and testing, but I can't approve.
Bootstrapped and Regression Tested on aarch64-thunderx-linux.
>> The rest of the MD file uses the term AdvSIMD. Also, the instrurction
>> is CNT rather than "pop count".
Done.
>> __builtin_popcount takes an unsigned int, so this should be
>> scanning for absence of popcountsi2 instead?
Done.
Please find attached the modified patch as per review comments
and let me know if its okay for Stage-1 or current branch.
Thanks,
Naveen
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 65eb326..0acb3f0 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -3785,6 +3785,39 @@
}
)
+;; 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/gcc.target/aarch64/popcnt.c b/gcc/testsuite/gcc.target/aarch64/popcnt.c
new file mode 100644
index 0000000..37cf4b9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcnt.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int
+foo (int x)
+{
+ return __builtin_popcount (x);
+}
+
+long
+foo1 (int x)
+{
+ return __builtin_popcountl (x);
+}
+
+/* { dg-final { scan-assembler-not "popcount" } } */
+/* { dg-final { scan-assembler-times "cnt\t" 2 } } */
