These are like the previous patch, but using | rather than * - I was unable to
get the previous test to pass on PowerPC and MIPS.
I note there is no inherent vector operation here - a bitwise OR across a word,
and a "reduction via shifts" using scalar (not vector) ops would be all that's
necessary. However, GCC doesn't exploit this possibility at present, and I don't
have any plans at present to add such myself.
Passing on x86_64-linux-gnu, aarch64-none-elf, aarch64_be-none-elf,
arm-none-eabi.
The 'scan-tree-dump' part passes on mips64 and powerpc (although the latter is
disabled as check_effective_target_whole_vector_shift gives 0, as per previous
patch)
gcc/testsuite/ChangeLog:
* gcc.dg/vect/vect-reduc-or_1.c: New test.
* gcc.dg/vect/vect-reduc-or_2.c: Likewise.
diff --git a/gcc/testsuite/gcc.dg/vect/vect-reduc-or_1.c b/gcc/testsuite/gcc.dg/vect/vect-reduc-or_1.c
new file mode 100644
index 0000000000000000000000000000000000000000..4e1a8577ce21aad539fca7cf07700b99575dfab0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-reduc-or_1.c
@@ -0,0 +1,35 @@
+/* { dg-require-effective-target whole_vector_shift } */
+
+/* Write a reduction loop to be reduced using vector shifts. */
+
+extern void abort(void);
+
+unsigned char in[16] __attribute__((__aligned__(16)));
+
+int
+main (unsigned char argc, char **argv)
+{
+ unsigned char i = 0;
+ unsigned char sum = 1;
+
+ for (i = 0; i < 16; i++)
+ in[i] = (i + i + 1) & 0xfd;
+
+ /* Prevent constant propagation of the entire loop below. */
+ asm volatile ("" : : : "memory");
+
+ for (i = 0; i < 16; i++)
+ sum |= in[i];
+
+ if (sum != 29)
+ {
+ __builtin_printf("Failed %d\n", sum);
+ abort();
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump "Reduce using vector shifts" "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/vect-reduc-or_2.c b/gcc/testsuite/gcc.dg/vect/vect-reduc-or_2.c
new file mode 100644
index 0000000000000000000000000000000000000000..e25467e59221adc09cbe0bb7548842902a4bf6da
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-reduc-or_2.c
@@ -0,0 +1,31 @@
+/* { dg-require-effective-target whole_vector_shift } */
+
+/* Write a reduction loop to be reduced using vector shifts and folded. */
+
+extern void abort(void);
+
+int
+main (unsigned char argc, char **argv)
+{
+ unsigned char in[16] __attribute__((aligned(16)));
+ unsigned char i = 0;
+ unsigned char sum = 1;
+
+ for (i = 0; i < 16; i++)
+ in[i] = (i + i + 1) & 0xfd;
+
+ for (i = 0; i < 16; i++)
+ sum |= in[i];
+
+ if (sum != 29)
+ {
+ __builtin_printf("Failed %d\n", sum);
+ abort();
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump "Reduce using vector shifts" "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+