+2019-01-07 Richard Sandiford <richard.sandiford@arm.com>
+
+ PR tree-optimization/88598
+ * tree.h (single_nonzero_element): Declare.
+ * tree.c (single_nonzero_element): New function.
+ * match.pd: Fold certain reductions of X & CST to X[I] & CST[I]
+ if I is the only nonzero element of CST.
+
2019-01-07 Richard Sandiford <richard.sandiford@arm.com>
PR tree-optimization/88598
{ wide_int_to_tree (sizetype, off); })
{ swap_p ? @0 : @2; }))
{ rhs_tree; })))))))))
+
+/* Fold REDUC (@0 & @1) -> @0[I] & @1[I] if element I is the only nonzero
+ element of @1. */
+(for reduc (IFN_REDUC_PLUS IFN_REDUC_IOR IFN_REDUC_XOR)
+ (simplify (reduc (view_convert? (bit_and @0 VECTOR_CST@1)))
+ (with { int i = single_nonzero_element (@1); }
+ (if (i >= 0)
+ (with { tree elt = vector_cst_elt (@1, i);
+ tree elt_type = TREE_TYPE (elt);
+ unsigned int elt_bits = tree_to_uhwi (TYPE_SIZE (elt_type));
+ tree size = bitsize_int (elt_bits);
+ tree pos = bitsize_int (elt_bits * i); }
+ (view_convert
+ (bit_and:elt_type
+ (BIT_FIELD_REF:elt_type @0 { size; } { pos; })
+ { elt; })))))))
+2019-01-07 Richard Sandiford <richard.sandiford@arm.com>
+
+ PR tree-optimization/88598
+ * gcc.dg/vect/pr88598-1.c: New test.
+ * gcc.dg/vect/pr88598-2.c: Likewise.
+ * gcc.dg/vect/pr88598-3.c: Likewise.
+ * gcc.dg/vect/pr88598-4.c: Likewise.
+ * gcc.dg/vect/pr88598-5.c: Likewise.
+ * gcc.dg/vect/pr88598-6.c: Likewise.
+
2019-01-07 Richard Sandiford <richard.sandiford@arm.com>
PR tree-optimization/88598
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-fdump-tree-optimized" } */
+
+#include "tree-vect.h"
+
+#define N 4
+
+int a[N];
+
+int __attribute__ ((noipa))
+f1 (void)
+{
+ int b[N] = { 15, 0, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] & b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f2 (void)
+{
+ int b[N] = { 0, 31, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] & b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f3 (void)
+{
+ int b[N] = { 0, 0, 0, -1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] & b[i];
+ return res;
+}
+
+int
+main ()
+{
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ a[i] = 0xe0 + i;
+
+ if (f1 () != (a[0] & 15)
+ || f2 () != (a[1] & 31)
+ || f3 () != a[N - 1])
+ __builtin_abort ();
+
+ return 0;
+}
+
+/* ??? We need more constant folding for this to work with fully-masked
+ loops. */
+/* { dg-final { scan-tree-dump-not {REDUC_PLUS} "optimized" { xfail aarch64_sve } } } */
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-fdump-tree-optimized" } */
+
+#include "tree-vect.h"
+
+#define N 4
+
+int a[N];
+
+int __attribute__ ((noipa))
+f1 (void)
+{
+ int b[N] = { 1, 0, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f2 (void)
+{
+ int b[N] = { 0, 1, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f3 (void)
+{
+ int b[N] = { 0, 0, 0, 1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int
+main ()
+{
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ a[i] = 0xe0 + i;
+
+ if (f1 () != a[0]
+ || f2 () != a[1]
+ || f3 () != a[N - 1])
+ __builtin_abort ();
+
+ return 0;
+}
+
+/* ??? We need more constant folding for this to work with fully-masked
+ loops. */
+/* { dg-final { scan-tree-dump-not {REDUC_PLUS} "optimized" { xfail aarch64_sve } } } */
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-ffast-math -fdump-tree-optimized" } */
+
+#include "tree-vect.h"
+
+#define N 4
+
+float a[N];
+
+float __attribute__ ((noipa))
+f1 (void)
+{
+ float b[N] = { 1, 0, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+float __attribute__ ((noipa))
+f2 (void)
+{
+ float b[N] = { 0, 1, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+float __attribute__ ((noipa))
+f3 (void)
+{
+ float b[N] = { 0, 0, 0, 1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int
+main ()
+{
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ a[i] = 0xe0 + i;
+
+ if (f1 () != a[0]
+ || f2 () != a[1]
+ || f3 () != a[N - 1])
+ __builtin_abort ();
+
+ return 0;
+}
+
+/* ??? We need more constant folding for this to work with fully-masked
+ loops. */
+/* { dg-final { scan-tree-dump-not {REDUC_PLUS} "optimized" { xfail aarch64_sve } } } */
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-fdump-tree-optimized" } */
+
+#include "tree-vect.h"
+
+#define N 4
+
+int a[N];
+
+int __attribute__ ((noipa))
+f1 (void)
+{
+ int b[N] = { 0, 15, 15, 15 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] & b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f2 (void)
+{
+ int b[N] = { 0, 31, 0, 31 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] & b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f3 (void)
+{
+ int b[N] = { -1, -1, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] & b[i];
+ return res;
+}
+
+int
+main ()
+{
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ a[i] = 0xe0 + i;
+
+ if (f1 () != (a[1] & 15) + (a[2] & 15) + (a[3] & 15)
+ || f2 () != (a[1] & 31) + (a[3] & 31)
+ || f3 () != a[0] + a[1])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-fdump-tree-optimized" } */
+
+#include "tree-vect.h"
+
+#define N 4
+
+int a[N];
+
+int __attribute__ ((noipa))
+f1 (void)
+{
+ int b[N] = { 0, 1, 1, 1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f2 (void)
+{
+ int b[N] = { 0, 1, 0, 1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int __attribute__ ((noipa))
+f3 (void)
+{
+ int b[N] = { 1, 1, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int
+main ()
+{
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ a[i] = 0xe0 + i;
+
+ if (f1 () != a[1] + a[2] + a[3]
+ || f2 () != a[1] + a[3]
+ || f3 () != a[0] + a[1])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-ffast-math -fdump-tree-optimized" } */
+
+#include "tree-vect.h"
+
+#define N 4
+
+float a[N];
+
+float __attribute__ ((noipa))
+f1 (void)
+{
+ float b[N] = { 0, 1, 1, 1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+float __attribute__ ((noipa))
+f2 (void)
+{
+ float b[N] = { 0, 1, 0, 1 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+float __attribute__ ((noipa))
+f3 (void)
+{
+ float b[N] = { 1, 1, 0, 0 }, res = 0;
+ for (int i = 0; i < N; ++i)
+ res += a[i] * b[i];
+ return res;
+}
+
+int
+main ()
+{
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ a[i] = 0xe0 + i;
+
+ if (f1 () != a[1] + a[2] + a[3]
+ || f2 () != a[1] + a[3]
+ || f3 () != a[0] + a[1])
+ __builtin_abort ();
+
+ return 0;
+}
return NULL_TREE;
}
+/* If VECTOR_CST T has a single nonzero element, return the index of that
+ element, otherwise return -1. */
+
+int
+single_nonzero_element (const_tree t)
+{
+ unsigned HOST_WIDE_INT nelts;
+ unsigned int repeat_nelts;
+ if (VECTOR_CST_NELTS (t).is_constant (&nelts))
+ repeat_nelts = nelts;
+ else if (VECTOR_CST_NELTS_PER_PATTERN (t) == 2)
+ {
+ nelts = vector_cst_encoded_nelts (t);
+ repeat_nelts = VECTOR_CST_NPATTERNS (t);
+ }
+ else
+ return -1;
+
+ int res = -1;
+ for (unsigned int i = 0; i < nelts; ++i)
+ {
+ tree elt = vector_cst_elt (t, i);
+ if (!integer_zerop (elt) && !real_zerop (elt))
+ {
+ if (res >= 0 || i >= repeat_nelts)
+ return -1;
+ res = i;
+ }
+ }
+ return res;
+}
+
/* Build an empty statement at location LOC. */
tree
extern tree uniform_integer_cst_p (tree);
+extern int single_nonzero_element (const_tree);
+
/* Given a CONSTRUCTOR CTOR, return the element values as a vector. */
extern vec<tree, va_gc> *ctor_to_vec (tree);
projects / gcc.git / commitdiff