AArch64: implement TARGET_VECTORIZE_CONDITIONAL_OPERATION_IS_EXPENSIVE [PR115531].

This implements the new target hook indicating that for AArch64 when possible
we prefer masked operations for any type vs doing LOAD + SELECT or
SELECT + STORE.

Thanks,
Tamar

gcc/ChangeLog:

	PR tree-optimization/115531
	* config/aarch64/aarch64.cc
	(aarch64_conditional_operation_is_expensive): New.
	(TARGET_VECTORIZE_CONDITIONAL_OPERATION_IS_EXPENSIVE): New.

gcc/testsuite/ChangeLog:

	PR tree-optimization/115531
	* gcc.dg/vect/vect-conditional_store_1.c: New test.
	* gcc.dg/vect/vect-conditional_store_2.c: New test.
	* gcc.dg/vect/vect-conditional_store_3.c: New test.
	* gcc.dg/vect/vect-conditional_store_4.c: New test.

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 0d41a193ec187755088c8f8d3de5a9ae5db4ced6..89eb66348f772a7e94f1acde29cd4badfd51fa3d 100644 (file)
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -28211,6 +28211,15 @@ aarch64_gen_adjusted_ldpstp (rtx *operands, bool load,
   return true;
 }
 
+/* Implement TARGET_VECTORIZE_CONDITIONAL_OPERATION_IS_EXPENSIVE.  Assume that
+   predicated operations when available are beneficial.  */
+
+static bool
+aarch64_conditional_operation_is_expensive (unsigned)
+{
+  return false;
+}
+
 /* Implement TARGET_VECTORIZE_EMPTY_MASK_IS_EXPENSIVE.  Assume for now that
    it isn't worth branching around empty masked ops (including masked
    stores).  */
@@ -30898,6 +30907,9 @@ aarch64_libgcc_floating_mode_supported_p
 #define TARGET_VECTORIZE_RELATED_MODE aarch64_vectorize_related_mode
 #undef TARGET_VECTORIZE_GET_MASK_MODE
 #define TARGET_VECTORIZE_GET_MASK_MODE aarch64_get_mask_mode
+#undef TARGET_VECTORIZE_CONDITIONAL_OPERATION_IS_EXPENSIVE
+#define TARGET_VECTORIZE_CONDITIONAL_OPERATION_IS_EXPENSIVE \
+  aarch64_conditional_operation_is_expensive
 #undef TARGET_VECTORIZE_EMPTY_MASK_IS_EXPENSIVE
 #define TARGET_VECTORIZE_EMPTY_MASK_IS_EXPENSIVE \
   aarch64_empty_mask_is_expensive

diff --git a/gcc/testsuite/gcc.dg/vect/vect-conditional_store_1.c b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_1.c
new file mode 100644 (file)
index 0000000..03128b1
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_1.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_masked_store } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+void foo1 (char *restrict a, int *restrict b, int *restrict c, int n, int stride)
+{
+  if (stride <= 1)
+    return;
+
+  for (int i = 0; i < n; i++)
+    {
+      int res = c[i];
+      int t = b[i+stride];
+      if (a[i] != 0)
+        res = t;
+      c[i] = res;
+    }
+}
+
+/* { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" } } */
+/* { dg-final { scan-tree-dump-not "VEC_COND_EXPR " "vect" { target aarch64-*-* } } } */

diff --git a/gcc/testsuite/gcc.dg/vect/vect-conditional_store_2.c b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_2.c
new file mode 100644 (file)
index 0000000..a038987
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_2.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_masked_store } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+void foo2 (char *restrict a, int *restrict b, int *restrict c, int n, int stride)
+{
+  if (stride <= 1)
+    return;
+
+  for (int i = 0; i < n; i++)
+    {
+      int res = c[i];
+      int t = b[i+stride];
+      if (a[i] != 0)
+        t = res;
+      c[i] = t;
+    }
+}
+
+/* { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" } } */
+/* { dg-final { scan-tree-dump-not "VEC_COND_EXPR " "vect" { target aarch64-*-* } } } */

diff --git a/gcc/testsuite/gcc.dg/vect/vect-conditional_store_3.c b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_3.c
new file mode 100644 (file)
index 0000000..8a89875
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_3.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_masked_store } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+void foo3 (float *restrict a, int *restrict b, int *restrict c, int n, int stride)
+{
+  if (stride <= 1)
+    return;
+
+  for (int i = 0; i < n; i++)
+    {
+      int res = c[i];
+      int t = b[i+stride];
+      if (a[i] >= 0)
+        t = res;
+      c[i] = t;
+    }
+}
+
+/* { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" } } */
+/* { dg-final { scan-tree-dump-not "VEC_COND_EXPR " "vect" { target aarch64-*-* } } } */

diff --git a/gcc/testsuite/gcc.dg/vect/vect-conditional_store_4.c b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_4.c
new file mode 100644 (file)
index 0000000..18ef42e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_4.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_masked_store } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+void foo4 (signed char *restrict a, int *restrict b, int *restrict c, int *restrict d, int n, int stride)
+{
+  if (stride <= 1)
+    return;
+
+  for (int i = 0; i < n; i++)
+    {
+      int res1 = c[i];
+      int res2 = d[i];
+      int t = b[i+stride];
+      if (a[i] > 0)
+        t = res1;
+      else if (a[i] < 0)
+        t = res2 * 2;
+
+      c[i] = t;
+    }
+}
+
+/* { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" } } */
+/* { dg-final { scan-tree-dump-times "VEC_COND_EXPR " "vect" 1 { target aarch64-*-* } } } */