aarch64: Improve popcount for bytes [PR113042]

For popcount for bytes, we don't need the reduction addition
after the vector cnt instruction as we are only counting one
byte's popcount.
This changes the popcount extend to cover all ALLI rather than GPI.

Changes since v1:
* v2 - Use ALLI iterator and combine all into one pattern.
       Add new testcases popcnt[6-8].c.
* v3 - Simplify TARGET_CSSC path.
       Use convert_to_mode instead of gen_zero_extend* directly.
       Some other small cleanups.

Bootstrapped and tested on aarch64-linux-gnu with no regressions.

	PR target/113042

gcc/ChangeLog:

	* config/aarch64/aarch64.md (popcount<mode>2): Update pattern
	to support ALLI modes.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/popcnt5.c: New test.
	* gcc.target/aarch64/popcnt6.c: New test.
	* gcc.target/aarch64/popcnt7.c: New test.
	* gcc.target/aarch64/popcnt8.c: New test.

Signed-off-by: Andrew Pinski <quic_apinski@quicinc.com>

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 665a333903c980537cc84ef896eba8dd9fb42600..12dcc16529ad8ede4578b7ce0f47d7ecac3a61b2 100644 (file)
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -5341,9 +5341,9 @@
 ;; MOV w0, v2.b[0]
 
 (define_expand "popcount<mode>2"
-  [(set (match_operand:GPI 0 "register_operand")
-       (popcount:GPI (match_operand:GPI 1 "register_operand")))]
-  "TARGET_CSSC || TARGET_SIMD"
+  [(set (match_operand:ALLI 0 "register_operand")
+       (popcount:ALLI (match_operand:ALLI 1 "register_operand")))]
+  "TARGET_CSSC ? GET_MODE_BITSIZE (<MODE>mode) >= 32 : TARGET_SIMD"
 {
   if (!TARGET_CSSC)
     {
@@ -5351,18 +5351,29 @@
       rtx v1 = gen_reg_rtx (V8QImode);
       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;
-       }
+      /* SImode and HImode should be zero extended to DImode.
+        popcount does not change if we have extra zeros.  */
+      if (<MODE>mode == SImode || <MODE>mode == HImode)
+       in = convert_to_mode (DImode, in, true);
+
       emit_move_insn (v, gen_lowpart (V8QImode, in));
       emit_insn (gen_popcountv8qi2 (v1, v));
-      emit_insn (gen_aarch64_zero_extend<mode>_reduc_plus_v8qi (out, v1));
+      /* QImode, just extract from the v8qi vector.  */
+      if (<MODE>mode == QImode)
+       emit_move_insn (out, gen_lowpart (QImode, v1));
+      /* HI and SI, reduction is zero extended to SImode. */
+      else if (<MODE>mode == SImode || <MODE>mode == HImode)
+       {
+         rtx out1 = gen_reg_rtx (SImode);
+         emit_insn (gen_aarch64_zero_extendsi_reduc_plus_v8qi (out1, v1));
+         emit_move_insn (out, gen_lowpart (<MODE>mode, out1));
+       }
+      /* DImode, reduction is zero extended to DImode. */
+      else
+       {
+         gcc_assert (<MODE>mode == DImode);
+         emit_insn (gen_aarch64_zero_extenddi_reduc_plus_v8qi (out, v1));
+       }
       DONE;
     }
 })

diff --git a/gcc/testsuite/gcc.target/aarch64/popcnt5.c b/gcc/testsuite/gcc.target/aarch64/popcnt5.c
new file mode 100644 (file)
index 0000000..406369d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcnt5.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+/* PR target/113042 */
+
+#pragma GCC target "+nocssc"
+
+/*
+** h8:
+**     ldr     b[0-9]+, \[x0\]
+**     cnt     v[0-9]+.8b, v[0-9]+.8b
+**     smov    w0, v[0-9]+.b\[0\]
+**     ret
+*/
+/* We should not need the addv here since we only need a byte popcount. */
+
+unsigned h8 (const unsigned char *a) {
+         return __builtin_popcountg (a[0]);
+}

diff --git a/gcc/testsuite/gcc.target/aarch64/popcnt6.c b/gcc/testsuite/gcc.target/aarch64/popcnt6.c
new file mode 100644 (file)
index 0000000..e882cb2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcnt6.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+/* PR target/113042 */
+
+#pragma GCC target "+nocssc"
+
+/*
+** h8:
+**     ldr     h[0-9]+, \[x0\]
+**     cnt     v[0-9]+.8b, v[0-9]+.8b
+**     addv    b[0-9]+, v[0-9]+.8b
+**     fmov    w0, s[0-9]+
+**     ret
+*/
+
+unsigned h8 (const unsigned short *a) {
+         return __builtin_popcountg (a[0]);
+}

diff --git a/gcc/testsuite/gcc.target/aarch64/popcnt7.c b/gcc/testsuite/gcc.target/aarch64/popcnt7.c
new file mode 100644 (file)
index 0000000..8dfff21
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcnt7.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+/* PR target/113042 */
+
+#pragma GCC target "+cssc"
+
+/*
+** h8:
+**     ldrb    w[0-9]+, \[x0\]
+**     cnt     w[0-9]+, w[0-9]+
+**     ret
+*/
+/* We should not produce any extra zero extend for this code */
+
+unsigned h8 (const unsigned char *a) {
+         return __builtin_popcountg (a[0]);
+}

diff --git a/gcc/testsuite/gcc.target/aarch64/popcnt8.c b/gcc/testsuite/gcc.target/aarch64/popcnt8.c
new file mode 100644 (file)
index 0000000..66a88b6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/popcnt8.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+/* PR target/113042 */
+
+#pragma GCC target "+cssc"
+
+/*
+** h8:
+**     ldrh    w[0-9]+, \[x0\]
+**     cnt     w[0-9]+, w[0-9]+
+**     ret
+*/
+/* We should not produce any extra zero extend for this code */
+
+unsigned h8 (const unsigned short *a) {
+         return __builtin_popcountg (a[0]);
+}