autovectorizer: Test autovectorization of different dot-prod modes.

Given the novel treatment of the dot product optab as a conversion, we
are now able to target different relationships between output modes and
input modes.

This is made clearer by way of example. Previously, on AArch64, the
following loop was vectorizable:

uint32_t udot4(int n, uint8_t* data) {
  uint32_t sum = 0;
  for (int i=0; i<n; i+=1)
    sum += data[i] * data[i];
  return sum;
}

while the following was not:

uint32_t udot2(int n, uint16_t* data) {
  uint32_t sum = 0;
  for (int i=0; i<n; i+=1)
    sum += data[i] * data[i];
  return sum;
}

Under the new treatment of the dot product optab, they are both now
vectorizable.

This adds the relevant target-agnostic check to ensure this behavior
in the autovectorizer, gated behind the new check_effective_target
`vect_dotprod_hisi' as well a runtime check targeting aarch64.

gcc/testsuite/ChangeLog:

	* lib/target-supports.exp (check_effective_target_vect_dotprod_hisi):
	New.
	* gcc.dg/vect/vect-dotprod-conv-optab.c: Likewise.
	* gcc.target/aarch64/vect-dotprod-twoway-hisi.c: Likewise.

3 files changed, 116 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.dg/vect/vect-dotprod-conv-optab.c b/gcc/testsuite/gcc.dg/vect/vect-dotprod-conv-optab.c
new file mode 100644
index 0000000..63e6c95
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-dotprod-conv-optab.c
@@ -0,0 +1,41 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_dotprod_hisi } */
+/* Ensure that, given the same input datatype, both the two-way and four-way
+   dot products are autovectorized, with the correct operation then selected
+   based on the distinct output types.  */
+#include <stdint.h>
+
+uint32_t udot4(int n, uint8_t* data) {
+  uint32_t sum = 0;
+  for (int i=0; i<n; i+=1) {
+    sum += data[i] * data[i];
+  }
+  return sum;
+}
+
+int32_t sdot4(int n, int8_t* data) {
+  int32_t sum = 0;
+  for (int i=0; i<n; i+=1) {
+    sum += data[i] * data[i];
+  }
+  return sum;
+}
+
+uint32_t udot2(int n, uint16_t* data) {
+  uint32_t sum = 0;
+  for (int i=0; i<n; i+=1) {
+    sum += data[i] * data[i];
+  }
+  return sum;
+}
+
+int32_t sdot2(int n, int16_t* data) {
+  int32_t sum = 0;
+  for (int i=0; i<n; i+=1) {
+    sum += data[i] * data[i];
+  }
+  return sum;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 4 "vect" } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/vect-dotprod-twoway-hisi.c b/gcc/testsuite/gcc.target/aarch64/vect-dotprod-twoway-hisi.c
new file mode 100644
index 0000000..0490faa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vect-dotprod-twoway-hisi.c
@@ -0,0 +1,66 @@
+/* { dg-do run } */
+/* { dg-require-effective-target vect_dotprod_hisi } */
+/* { dg-options "-static -O3 -ftree-vectorize -fdump-tree-vect-details -save-temps" } */
+/* Ensure runtime correctness in the autovectorized two-way dot product operations.  */
+
+#include <stdint.h>
+#include <stdlib.h>
+#pragma GCC target "+sme2"
+
+uint32_t
+udot2 (int n, uint16_t* data)  __arm_streaming
+{
+  uint32_t sum = 0;
+  for (int i=0; i<n; i+=1) {
+    sum += data[i] * data[i];
+  }
+  return sum;
+}
+
+int32_t
+sdot2 (int n, int16_t* data)  __arm_streaming
+{
+  int32_t sum = 0;
+  for (int i=0; i<n; i+=1) {
+    sum += data[i] * data[i];
+  }
+  return sum;
+}
+
+int
+main ()
+{
+
+  uint16_t u_input_nil[] = { [0 ... 3] = 0 };
+  uint16_t u_input_min[] = { [0 ... 3] = 1 };
+  uint16_t u_input_max[] = { [0 ... 3] = 32767};
+
+  uint32_t u_nil_dotprod = udot2 (4, u_input_nil);
+  uint32_t u_min_dotprod = udot2 (4, u_input_min);
+  uint32_t u_max_dotprod = udot2 (4, u_input_max);
+
+  if (u_nil_dotprod != 0
+      || u_min_dotprod != 4
+      || u_max_dotprod != 4294705156)
+    abort ();
+
+  int16_t s_input_nil[] = { [0 ... 3] = 0 };
+  int16_t s_input_min[] = { [0 ... 3] = -23170 };
+  int16_t s_input_max[] = { [0 ... 3] =  23170 };
+
+  int32_t s_nil_dotprod = sdot2 (4, s_input_nil);
+  int32_t s_min_dotprod = sdot2 (4, s_input_min);
+  int32_t s_max_dotprod = sdot2 (4, s_input_max);
+
+  if (s_nil_dotprod != 0
+      || s_min_dotprod != 2147395600
+      || s_max_dotprod != 2147395600)
+      abort ();
+
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 46 "vect" } } */
+/* { dg-final { scan-assembler "\[ \t\]udot\tz\[0-9\]+.s, z\[0-9\]+.h, z\[0-9\]+.h" } } */
+/* { dg-final { scan-assembler "\[ \t\]sdot\tz\[0-9\]+.s, z\[0-9\]+.h, z\[0-9\]+.h" } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 05a63c4..f92f7f1 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -4294,6 +4294,15 @@ proc check_effective_target_vect_int_div { } {
     return [check_effective_target_aarch64_sve]
 }
 
+# Return 1 if the target supports two-way dot products on inpus of hi mode
+# producing si outputs, 0 otherwise.
+
+proc check_effective_target_vect_dotprod_hisi { } {
+    return [check_cached_effective_target_indexed aarch64_sme2 {
+	expr { [check_effective_target_aarch64_sme2]
+    }}]
+}
+
 # Return 1 if the target supports vectorization of early breaks,
 # 0 otherwise.
 #