> -----Original Message-----
> From: Richard Sandiford <richard.sandif...@arm.com>
> Sent: Friday, December 17, 2021 4:19 PM
> To: Tamar Christina via Gcc-patches <gcc-patches@gcc.gnu.org>
> Cc: Tamar Christina <tamar.christ...@arm.com>; nd <n...@arm.com>;
> rguent...@suse.de
> Subject: Re: [1/3 PATCH]middle-end vect: Simplify and extend the complex
> numbers validation routines.
>
> Just a comment on the documentation:
>
> Tamar Christina via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
> > diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index
> >
> 9ec051e94e10cca9eec2773e1b8c01b74b6ea4db..60dc5b3ea6087c2824ad1467
> bc66
> > e9cfebe9dcfc 100644
> > --- a/gcc/doc/md.texi
> > +++ b/gcc/doc/md.texi
> > @@ -6325,12 +6325,12 @@ Perform a vector multiply and accumulate that
> > is semantically the same as a multiply and accumulate of complex numbers.
> >
> > @smallexample
> > - complex TYPE c[N];
> > - complex TYPE a[N];
> > - complex TYPE b[N];
> > + complex TYPE op0[N];
> > + complex TYPE op1[N];
> > + complex TYPE op2[N];
> > for (int i = 0; i < N; i += 1)
> > @{
> > - c[i] += a[i] * b[i];
> > + op2[i] += op1[i] * op2[i];
> > @}
>
> I think this should be:
>
> op0[i] = op1[i] * op2[i] + op3[i];
>
> since operand 0 is the output and operand 3 is the accumulator input.
>
> Same idea for the others. For:
>
> > @@ -6415,12 +6415,12 @@ Perform a vector multiply that is semantically
> > the same as multiply of complex numbers.
> >
> > @smallexample
> > - complex TYPE c[N];
> > - complex TYPE a[N];
> > - complex TYPE b[N];
> > + complex TYPE op0[N];
> > + complex TYPE op1[N];
> > + complex TYPE op2[N];
> > for (int i = 0; i < N; i += 1)
> > @{
> > - c[i] = a[i] * b[i];
> > + op2[i] = op0[i] * op1[i];
>
> …this I think it should be:
>
> op0[i] = op1[i] * op2[i];
Updated patch attached.
Bootstrapped Regtested on aarch64-none-linux-gnu,
x86_64-pc-linux-gnu and no regressions.
Ok for master? and backport to GCC 11 after some stew?
Thanks,
Tamar
gcc/ChangeLog:
PR tree-optimization/102819
PR tree-optimization/103169
* doc/md.texi: Update docs for cfms, cfma.
* tree-data-ref.h (same_data_refs): Accept optional offset.
* tree-vect-slp-patterns.c (is_linear_load_p): Fix issue with repeating
patterns.
(vect_normalize_conj_loc): Remove.
(is_eq_or_top): Change to take two nodes.
(enum _conj_status, compatible_complex_nodes_p,
vect_validate_multiplication): New.
(class complex_add_pattern, complex_add_pattern::matches,
complex_add_pattern::recognize, class complex_mul_pattern,
complex_mul_pattern::recognize, class complex_fms_pattern,
complex_fms_pattern::recognize, class complex_operations_pattern,
complex_operations_pattern::recognize, addsub_pattern::recognize): Pass
new cache.
(complex_fms_pattern::matches, complex_mul_pattern::matches): Pass new
cache and use new validation code.
* tree-vect-slp.c (vect_match_slp_patterns_2, vect_match_slp_patterns,
vect_analyze_slp): Pass along cache.
(compatible_calls_p): Expose.
* tree-vectorizer.h (compatible_calls_p, slp_node_hash,
slp_compat_nodes_map_t): New.
(class vect_pattern): Update signatures include new cache.
gcc/testsuite/ChangeLog:
PR tree-optimization/102819
PR tree-optimization/103169
* g++.dg/vect/pr99149.cc: xfail for now.
* gcc.dg/vect/complex/pr102819-1.c: New test.
* gcc.dg/vect/complex/pr102819-2.c: New test.
* gcc.dg/vect/complex/pr102819-3.c: New test.
* gcc.dg/vect/complex/pr102819-4.c: New test.
* gcc.dg/vect/complex/pr102819-5.c: New test.
* gcc.dg/vect/complex/pr102819-6.c: New test.
* gcc.dg/vect/complex/pr102819-7.c: New test.
* gcc.dg/vect/complex/pr102819-8.c: New test.
* gcc.dg/vect/complex/pr102819-9.c: New test.
* gcc.dg/vect/complex/pr103169.c: New test.
--- inline copy of patch ---
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index
9ec051e94e10cca9eec2773e1b8c01b74b6ea4db..ad06b02d36876082afe4c3f3fb51887f7a522b23
100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -6325,12 +6325,13 @@ Perform a vector multiply and accumulate that is
semantically the same as
a multiply and accumulate of complex numbers.
@smallexample
- complex TYPE c[N];
- complex TYPE a[N];
- complex TYPE b[N];
+ complex TYPE op0[N];
+ complex TYPE op1[N];
+ complex TYPE op2[N];
+ complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
- c[i] += a[i] * b[i];
+ op0[i] = op1[i] * op2[i] + op3[i];
@}
@end smallexample
@@ -6348,12 +6349,13 @@ the same as a multiply and accumulate of complex
numbers where the second
multiply arguments is conjugated.
@smallexample
- complex TYPE c[N];
- complex TYPE a[N];
- complex TYPE b[N];
+ complex TYPE op0[N];
+ complex TYPE op1[N];
+ complex TYPE op2[N];
+ complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
- c[i] += a[i] * conj (b[i]);
+ op0[i] = op1[i] * conj (op2[i]) + op3[i];
@}
@end smallexample
@@ -6370,12 +6372,13 @@ Perform a vector multiply and subtract that is
semantically the same as
a multiply and subtract of complex numbers.
@smallexample
- complex TYPE c[N];
- complex TYPE a[N];
- complex TYPE b[N];
+ complex TYPE op0[N];
+ complex TYPE op1[N];
+ complex TYPE op2[N];
+ complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
- c[i] -= a[i] * b[i];
+ op0[i] = op1[i] * op2[i] - op3[i];
@}
@end smallexample
@@ -6393,12 +6396,13 @@ the same as a multiply and subtract of complex numbers
where the second
multiply arguments is conjugated.
@smallexample
- complex TYPE c[N];
- complex TYPE a[N];
- complex TYPE b[N];
+ complex TYPE op0[N];
+ complex TYPE op1[N];
+ complex TYPE op2[N];
+ complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
- c[i] -= a[i] * conj (b[i]);
+ op0[i] = op1[i] * conj (op2[i]) - op3[i];
@}
@end smallexample
@@ -6415,12 +6419,12 @@ Perform a vector multiply that is semantically the same
as multiply of
complex numbers.
@smallexample
- complex TYPE c[N];
- complex TYPE a[N];
- complex TYPE b[N];
+ complex TYPE op0[N];
+ complex TYPE op1[N];
+ complex TYPE op2[N];
for (int i = 0; i < N; i += 1)
@{
- c[i] = a[i] * b[i];
+ op0[i] = op1[i] * op2[i];
@}
@end smallexample
@@ -6437,12 +6441,12 @@ Perform a vector multiply by conjugate that is
semantically the same as a
multiply of complex numbers where the second multiply arguments is conjugated.
@smallexample
- complex TYPE c[N];
- complex TYPE a[N];
- complex TYPE b[N];
+ complex TYPE op0[N];
+ complex TYPE op1[N];
+ complex TYPE op2[N];
for (int i = 0; i < N; i += 1)
@{
- c[i] = a[i] * conj (b[i]);
+ op0[i] = op1[i] * conj (op2[i]);
@}
@end smallexample
diff --git a/gcc/testsuite/g++.dg/vect/pr99149.cc
b/gcc/testsuite/g++.dg/vect/pr99149.cc
index
e6e0594a336fa053ffba64a12e2de43a4e373f49..bb9f5fa89f12b184368bf5488d6e9432c2166463
100755
--- a/gcc/testsuite/g++.dg/vect/pr99149.cc
+++ b/gcc/testsuite/g++.dg/vect/pr99149.cc
@@ -24,4 +24,4 @@ public:
} n;
main() { n.j(); }
-/* { dg-final { scan-tree-dump-times "stmt.*COMPLEX_MUL" 1 "slp2" } } */
+/* { dg-final { scan-tree-dump-times "stmt.*COMPLEX_MUL" 1 "slp2" { xfail {
vect_float } } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-1.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-1.c
new file mode 100644
index
0000000000000000000000000000000000000000..46b9a55f05279d732fa1418e02f779cf693ede07
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void bad1(float v1, float v2)
+{
+ for (int r = 0; r < 100; r += 4)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * (f[2][r] + v2) - f[1][i] * (f[2][i] + v1);
+ f[0][i] = f[1][r] * (f[2][i] + v1) + f[1][i] * (f[2][r] + v2);
+ f[0][r+2] = f[1][r+2] * (f[2][r+2] + v2) - f[1][i+2] * (f[2][i+2] + v1);
+ f[0][i+2] = f[1][r+2] * (f[2][i+2] + v1) + f[1][i+2] * (f[2][r+2] + v2);
+ // ^^^^^^^ ^^^^^^^
+ }
+}
+
+/* { dg-final { scan-tree-dump "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-2.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-2.c
new file mode 100644
index
0000000000000000000000000000000000000000..ffe646efe57f7ad07541b0fb96601596f46dc5f8
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-2.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void bad1(float v1, float v2)
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * (f[2][r] + v1) - f[1][i] * (f[2][i] + v2);
+ f[0][i] = f[1][r] * (f[2][i] + v1) + f[1][i] * (f[2][r] + v2);
+ }
+}
+
+/* { dg-final { scan-tree-dump-not "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-3.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-3.c
new file mode 100644
index
0000000000000000000000000000000000000000..5f98aa204d8b11b0cb433f8965dbb72cf8940de1
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-3.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void good1(float v1, float v2)
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * (f[2][r] + v2) - f[1][i] * (f[2][i] + v1);
+ f[0][i] = f[1][r] * (f[2][i] + v1) + f[1][i] * (f[2][r] + v2);
+ }
+}
+
+/* { dg-final { scan-tree-dump "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-4.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-4.c
new file mode 100644
index
0000000000000000000000000000000000000000..882851789c5085e734000609114be480d3b08bd0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-4.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void good1()
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * f[2][r] - f[1][i] * f[2][i];
+ f[0][i] = f[1][r] * f[2][i] + f[1][i] * f[2][r];
+ }
+}
+
+/* { dg-final { scan-tree-dump "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-5.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-5.c
new file mode 100644
index
0000000000000000000000000000000000000000..6a2d549d65f3f27d407fb0bd469473e6a5c333ae
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-5.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void good2()
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * (f[2][r] + 1) - f[1][i] * (f[2][i] + 1);
+ f[0][i] = f[1][r] * (f[2][i] + 1) + f[1][i] * (f[2][r] + 1);
+ }
+}
+
+/* { dg-final { scan-tree-dump "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-6.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-6.c
new file mode 100644
index
0000000000000000000000000000000000000000..71e66dbe3b29eec1fffb8df9b216022fdc0af54e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-6.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void bad1()
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * f[2][r] - f[1][i] * f[3][i];
+ f[0][i] = f[1][r] * f[2][i] + f[1][i] * f[3][r];
+ // ^^^^^^^ ^^^^^^^
+ }
+}
+
+/* { dg-final { scan-tree-dump-not "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-7.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-7.c
new file mode 100644
index
0000000000000000000000000000000000000000..536672f3c8bb474ad5fa4bb61b3a36b555acf3cf
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-7.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void bad2()
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * (f[2][r] + 1) - f[1][i] * f[2][i];
+ f[0][i] = f[1][r] * (f[2][i] + 1) + f[1][i] * f[2][r];
+ // ^^^^
+ }
+}
+
+/* { dg-final { scan-tree-dump-not "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-8.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-8.c
new file mode 100644
index
0000000000000000000000000000000000000000..07b48148688b7d530e5891d023d558b58a485c23
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-8.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+float f[12][100];
+
+void bad3()
+{
+ for (int r = 0; r < 100; r += 2)
+ {
+ int i = r + 1;
+ f[0][r] = f[1][r] * f[2][r] - f[1][r] * f[2][i];
+ f[0][i] = f[1][r] * f[2][i] + f[1][i] * f[2][r];
+ // ^^^^^^^
+ }
+}
+
+/* { dg-final { scan-tree-dump-not "Found COMPLEX_MUL" "vect" { target {
vect_float } } } } */
+
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr102819-9.c
b/gcc/testsuite/gcc.dg/vect/complex/pr102819-9.c
new file mode 100644
index
0000000000000000000000000000000000000000..7655852434b21b381fe7ee316e8caf3d485b8ee1
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr102819-9.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+
+#include <stdio.h>
+#include <complex.h>
+
+#define N 200
+#define TYPE float
+#define TYPE2 float
+
+void g (TYPE2 complex a[restrict N], TYPE complex b[restrict N], TYPE complex
c[restrict N])
+{
+ for (int i=0; i < N; i++)
+ {
+ c[i] -= a[i] * b[0];
+ }
+}
+
+/* The pattern overlaps with COMPLEX_ADD so we need to support consuming ADDs
in COMPLEX_FMS. */
+
+/* { dg-final { scan-tree-dump "Found COMPLEX_FMS" "vect" { xfail { vect_float
} } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/complex/pr103169.c
b/gcc/testsuite/gcc.dg/vect/complex/pr103169.c
new file mode 100644
index
0000000000000000000000000000000000000000..1bfabbd85a0eedfb4156a82574324126e9083fc5
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/complex/pr103169.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target { vect_double } } } */
+/* { dg-add-options arm_v8_3a_complex_neon } */
+/* { dg-additional-options "-O2 -fvect-cost-model=unlimited" } */
+
+_Complex double b_0, c_0;
+
+void
+mul270snd (void)
+{
+ c_0 = b_0 * 1.0iF * 1.0iF;
+}
+
diff --git a/gcc/tree-data-ref.h b/gcc/tree-data-ref.h
index
74f579c9f3f23bac25d21546068c2ab43209aa2b..8ad5fa521279b20fa5e63eecf442d5dc5c16e7ee
100644
--- a/gcc/tree-data-ref.h
+++ b/gcc/tree-data-ref.h
@@ -600,10 +600,11 @@ same_data_refs_base_objects (data_reference_p a,
data_reference_p b)
}
/* Return true when the data references A and B are accessing the same
- memory object with the same access functions. */
+ memory object with the same access functions. Optionally skip the
+ last OFFSET dimensions in the data reference. */
static inline bool
-same_data_refs (data_reference_p a, data_reference_p b)
+same_data_refs (data_reference_p a, data_reference_p b, int offset = 0)
{
unsigned int i;
@@ -614,7 +615,7 @@ same_data_refs (data_reference_p a, data_reference_p b)
if (!same_data_refs_base_objects (a, b))
return false;
- for (i = 0; i < DR_NUM_DIMENSIONS (a); i++)
+ for (i = offset; i < DR_NUM_DIMENSIONS (a); i++)
if (!eq_evolutions_p (DR_ACCESS_FN (a, i), DR_ACCESS_FN (b, i)))
return false;
diff --git a/gcc/tree-vect-slp-patterns.c b/gcc/tree-vect-slp-patterns.c
index
0350441fad9690cd5d04337171ca3470a064a571..020c29bba08c5bd80503a2dbc04292f8fd310b3c
100644
--- a/gcc/tree-vect-slp-patterns.c
+++ b/gcc/tree-vect-slp-patterns.c
@@ -149,12 +149,13 @@ is_linear_load_p (load_permutation_t loads)
int valid_patterns = 4;
FOR_EACH_VEC_ELT (loads, i, load)
{
- if (candidates[0] != PERM_UNKNOWN && load != 1)
+ unsigned adj_load = load % 2;
+ if (candidates[0] != PERM_UNKNOWN && adj_load != 1)
{
candidates[0] = PERM_UNKNOWN;
valid_patterns--;
}
- if (candidates[1] != PERM_UNKNOWN && load != 0)
+ if (candidates[1] != PERM_UNKNOWN && adj_load != 0)
{
candidates[1] = PERM_UNKNOWN;
valid_patterns--;
@@ -596,11 +597,12 @@ class complex_add_pattern : public complex_pattern
public:
void build (vec_info *);
static internal_fn
- matches (complex_operation_t op, slp_tree_to_load_perm_map_t *, slp_tree *,
- vec<slp_tree> *);
+ matches (complex_operation_t op, slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *, slp_tree *, vec<slp_tree> *);
static vect_pattern*
- recognize (slp_tree_to_load_perm_map_t *, slp_tree *);
+ recognize (slp_tree_to_load_perm_map_t *, slp_compat_nodes_map_t *,
+ slp_tree *);
static vect_pattern*
mkInstance (slp_tree *node, vec<slp_tree> *m_ops, internal_fn ifn)
@@ -647,6 +649,7 @@ complex_add_pattern::build (vec_info *vinfo)
internal_fn
complex_add_pattern::matches (complex_operation_t op,
slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t * /* compat_cache */,
slp_tree *node, vec<slp_tree> *ops)
{
internal_fn ifn = IFN_LAST;
@@ -692,13 +695,14 @@ complex_add_pattern::matches (complex_operation_t op,
vect_pattern*
complex_add_pattern::recognize (slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache,
slp_tree *node)
{
auto_vec<slp_tree> ops;
complex_operation_t op
= vect_detect_pair_op (*node, true, &ops);
internal_fn ifn
- = complex_add_pattern::matches (op, perm_cache, node, &ops);
+ = complex_add_pattern::matches (op, perm_cache, compat_cache, node, &ops);
if (ifn == IFN_LAST)
return NULL;
@@ -709,147 +713,214 @@ complex_add_pattern::recognize
(slp_tree_to_load_perm_map_t *perm_cache,
* complex_mul_pattern
******************************************************************************/
-/* Check to see if either of the trees in ARGS are a NEGATE_EXPR. If the first
- child (args[0]) is a NEGATE_EXPR then NEG_FIRST_P is set to TRUE.
-
- If a negate is found then the values in ARGS are reordered such that the
- negate node is always the second one and the entry is replaced by the child
- of the negate node. */
+/* Helper function to check if PERM is KIND or PERM_TOP. */
static inline bool
-vect_normalize_conj_loc (vec<slp_tree> &args, bool *neg_first_p = NULL)
+is_eq_or_top (slp_tree_to_load_perm_map_t *perm_cache,
+ slp_tree op1, complex_perm_kinds_t kind1,
+ slp_tree op2, complex_perm_kinds_t kind2)
{
- gcc_assert (args.length () == 2);
- bool neg_found = false;
-
- if (vect_match_expression_p (args[0], NEGATE_EXPR))
- {
- std::swap (args[0], args[1]);
- neg_found = true;
- if (neg_first_p)
- *neg_first_p = true;
- }
- else if (vect_match_expression_p (args[1], NEGATE_EXPR))
- {
- neg_found = true;
- if (neg_first_p)
- *neg_first_p = false;
- }
+ complex_perm_kinds_t perm1 = linear_loads_p (perm_cache, op1);
+ if (perm1 != kind1 && perm1 != PERM_TOP)
+ return false;
- if (neg_found)
- args[1] = SLP_TREE_CHILDREN (args[1])[0];
+ complex_perm_kinds_t perm2 = linear_loads_p (perm_cache, op2);
+ if (perm2 != kind2 && perm2 != PERM_TOP)
+ return false;
- return neg_found;
+ return true;
}
-/* Helper function to check if PERM is KIND or PERM_TOP. */
+enum _conj_status { CONJ_NONE, CONJ_FST, CONJ_SND };
static inline bool
-is_eq_or_top (complex_perm_kinds_t perm, complex_perm_kinds_t kind)
+compatible_complex_nodes_p (slp_compat_nodes_map_t *compat_cache,
+ slp_tree a, int *pa, slp_tree b, int *pb)
{
- return perm == kind || perm == PERM_TOP;
-}
+ bool *tmp;
+ std::pair<slp_tree, slp_tree> key = std::make_pair(a, b);
+ if ((tmp = compat_cache->get (key)) != NULL)
+ return *tmp;
-/* Helper function that checks to see if LEFT_OP and RIGHT_OP are both
MULT_EXPR
- nodes but also that they represent an operation that is either a complex
- multiplication or a complex multiplication by conjugated value.
+ compat_cache->put (key, false);
- Of the negation is expected to be in the first half of the tree (As required
- by an FMS pattern) then NEG_FIRST is true. If the operation is a conjugate
- operation then CONJ_FIRST_OPERAND is set to indicate whether the first or
- second operand contains the conjugate operation. */
+ if (SLP_TREE_CHILDREN (a).length () != SLP_TREE_CHILDREN (b).length ())
+ return false;
-static inline bool
-vect_validate_multiplication (slp_tree_to_load_perm_map_t *perm_cache,
- const vec<slp_tree> &left_op,
- const vec<slp_tree> &right_op,
- bool neg_first, bool *conj_first_operand,
- bool fms)
-{
- /* The presence of a negation indicates that we have either a conjugate or a
- rotation. We need to distinguish which one. */
- *conj_first_operand = false;
- complex_perm_kinds_t kind;
-
- /* Complex conjugates have the negation on the imaginary part of the
- number where rotations affect the real component. So check if the
- negation is on a dup of lane 1. */
- if (fms)
+ if (SLP_TREE_DEF_TYPE (a) != SLP_TREE_DEF_TYPE (b))
+ return false;
+
+ /* Only internal nodes can be loads, as such we can't check further if they
+ are externals. */
+ if (SLP_TREE_DEF_TYPE (a) != vect_internal_def)
{
- /* Canonicalization for fms is not consistent. So have to test both
- variants to be sure. This needs to be fixed in the mid-end so
- this part can be simpler. */
- kind = linear_loads_p (perm_cache, right_op[0]);
- if (!((is_eq_or_top (linear_loads_p (perm_cache, right_op[0]),
PERM_ODDODD)
- && is_eq_or_top (linear_loads_p (perm_cache, right_op[1]),
- PERM_ODDEVEN))
- || (kind == PERM_ODDEVEN
- && is_eq_or_top (linear_loads_p (perm_cache, right_op[1]),
- PERM_ODDODD))))
- return false;
+ for (unsigned i = 0; i < SLP_TREE_SCALAR_OPS (a).length (); i++)
+ {
+ tree op1 = SLP_TREE_SCALAR_OPS (a)[pa[i % 2]];
+ tree op2 = SLP_TREE_SCALAR_OPS (b)[pb[i % 2]];
+ if (!operand_equal_p (op1, op2, 0))
+ return false;
+ }
+
+ compat_cache->put (key, true);
+ return true;
}
+
+ auto a_stmt = STMT_VINFO_STMT (SLP_TREE_REPRESENTATIVE (a));
+ auto b_stmt = STMT_VINFO_STMT (SLP_TREE_REPRESENTATIVE (b));
+
+ if (gimple_code (a_stmt) != gimple_code (b_stmt))
+ return false;
+
+ /* code, children, type, externals, loads, constants */
+ if (gimple_num_args (a_stmt) != gimple_num_args (b_stmt))
+ return false;
+
+ /* At this point, a and b are known to be the same gimple operations. */
+ if (is_gimple_call (a_stmt))
+ {
+ if (!compatible_calls_p (dyn_cast <gcall *> (a_stmt),
+ dyn_cast <gcall *> (b_stmt)))
+ return false;
+ }
+ else if (!is_gimple_assign (a_stmt))
+ return false;
else
{
- if (linear_loads_p (perm_cache, right_op[1]) != PERM_ODDODD
- && !is_eq_or_top (linear_loads_p (perm_cache, right_op[0]),
- PERM_ODDEVEN))
+ tree_code acode = gimple_assign_rhs_code (a_stmt);
+ tree_code bcode = gimple_assign_rhs_code (b_stmt);
+ if ((acode == REALPART_EXPR || acode == IMAGPART_EXPR)
+ && (bcode == REALPART_EXPR || bcode == IMAGPART_EXPR))
+ return true;
+
+ if (acode != bcode)
return false;
}
- /* Deal with differences in indexes. */
- int index1 = fms ? 1 : 0;
- int index2 = fms ? 0 : 1;
-
- /* Check if the conjugate is on the second first or second operand. The
- order of the node with the conjugate value determines this, and the dup
- node must be one of lane 0 of the same DR as the neg node. */
- kind = linear_loads_p (perm_cache, left_op[index1]);
- if (kind == PERM_TOP)
+ if (!SLP_TREE_LOAD_PERMUTATION (a).exists ()
+ || !SLP_TREE_LOAD_PERMUTATION (b).exists ())
{
- if (linear_loads_p (perm_cache, left_op[index2]) == PERM_EVENODD)
- return true;
+ for (unsigned i = 0; i < gimple_num_args (a_stmt); i++)
+ {
+ tree t1 = gimple_arg (a_stmt, i);
+ tree t2 = gimple_arg (b_stmt, i);
+ if (TREE_CODE (t1) != TREE_CODE (t2))
+ return false;
+
+ /* If SSA name then we will need to inspect the children
+ so we can punt here. */
+ if (TREE_CODE (t1) == SSA_NAME)
+ continue;
+
+ if (!operand_equal_p (t1, t2, 0))
+ return false;
+ }
}
- else if (kind == PERM_EVENODD && !neg_first)
+ else
{
- if ((kind = linear_loads_p (perm_cache, left_op[index2])) !=
PERM_EVENEVEN)
+ auto dr1 = STMT_VINFO_DATA_REF (SLP_TREE_REPRESENTATIVE (a));
+ auto dr2 = STMT_VINFO_DATA_REF (SLP_TREE_REPRESENTATIVE (b));
+ /* Don't check the last dimension as that's checked by the lineary
+ checks. This check is also much stricter than what we need
+ because it doesn't consider loading from adjacent elements
+ in the same struct as loading from the same base object.
+ But for now, I'll play it safe. */
+ if (!same_data_refs (dr1, dr2, 1))
return false;
- return true;
}
- else if (kind == PERM_EVENEVEN && neg_first)
+
+ for (unsigned i = 0; i < SLP_TREE_CHILDREN (a).length (); i++)
{
- if ((kind = linear_loads_p (perm_cache, left_op[index2])) !=
PERM_EVENODD)
+ if (!compatible_complex_nodes_p (compat_cache,
+ SLP_TREE_CHILDREN (a)[i], pa,
+ SLP_TREE_CHILDREN (b)[i], pb))
return false;
-
- *conj_first_operand = true;
- return true;
}
- else
- return false;
-
- if (kind != PERM_EVENEVEN)
- return false;
+ compat_cache->put (key, true);
return true;
}
-/* Helper function to help distinguish between a conjugate and a rotation in a
- complex multiplication. The operations have similar shapes but the order of
- the load permutes are different. This function returns TRUE when the order
- is consistent with a multiplication or multiplication by conjugated
- operand but returns FALSE if it's a multiplication by rotated operand. */
-
static inline bool
vect_validate_multiplication (slp_tree_to_load_perm_map_t *perm_cache,
- const vec<slp_tree> &op,
- complex_perm_kinds_t permKind)
+ slp_compat_nodes_map_t *compat_cache,
+ vec<slp_tree> &left_op,
+ vec<slp_tree> &right_op,
+ bool subtract,
+ enum _conj_status *_status)
{
- /* The left node is the more common case, test it first. */
- if (!is_eq_or_top (linear_loads_p (perm_cache, op[0]), permKind))
+ auto_vec<slp_tree> ops;
+ enum _conj_status stats = CONJ_NONE;
+
+ /* The complex operations can occur in two layouts and two permute sequences
+ so declare them and re-use them. */
+ int styles[][4] = { { 0, 2, 1, 3} /* {L1, R1} + {L2, R2}. */
+ , { 0, 3, 1, 2} /* {L1, R2} + {L2, R1}. */
+ };
+
+ /* Now for the corresponding permutes that go with these values. */
+ complex_perm_kinds_t perms[][4]
+ = { { PERM_EVENEVEN, PERM_ODDODD, PERM_EVENODD, PERM_ODDEVEN }
+ , { PERM_EVENODD, PERM_ODDEVEN, PERM_EVENEVEN, PERM_ODDODD }
+ };
+
+ /* These permutes are used during comparisons of externals on which
+ we require strict equality. */
+ int cq[][4][2]
+ = { { { 0, 0 }, { 1, 1 }, { 0, 1 }, { 1, 0 } }
+ , { { 0, 1 }, { 1, 0 }, { 0, 0 }, { 1, 1 } }
+ };
+
+ /* Default to style and perm 0, most operations use this one. */
+ int style = 0;
+ int perm = subtract ? 1 : 0;
+
+ /* Check if we have a negate operation, if so absorb the node and continue
+ looking. */
+ bool neg0 = vect_match_expression_p (right_op[0], NEGATE_EXPR);
+ bool neg1 = vect_match_expression_p (right_op[1], NEGATE_EXPR);
+
+ /* Determine which style we're looking at. We only have different ones
+ whenever a conjugate is involved. */
+ if (neg0 && neg1)
+ ;
+ else if (neg0)
{
- if (!is_eq_or_top (linear_loads_p (perm_cache, op[1]), permKind))
- return false;
+ right_op[0] = SLP_TREE_CHILDREN (right_op[0])[0];
+ stats = CONJ_FST;
+ if (subtract)
+ perm = 0;
}
- return true;
+ else if (neg1)
+ {
+ right_op[1] = SLP_TREE_CHILDREN (right_op[1])[0];
+ stats = CONJ_SND;
+ perm = 1;
+ }
+
+ *_status = stats;
+
+ /* Flatten the inputs after we've remapped them. */
+ ops.create (4);
+ ops.safe_splice (left_op);
+ ops.safe_splice (right_op);
+
+ /* Extract out the elements to check. */
+ slp_tree op0 = ops[styles[style][0]];
+ slp_tree op1 = ops[styles[style][1]];
+ slp_tree op2 = ops[styles[style][2]];
+ slp_tree op3 = ops[styles[style][3]];
+
+ /* Do cheapest test first. If failed no need to analyze further. */
+ if (linear_loads_p (perm_cache, op0) != perms[perm][0]
+ || linear_loads_p (perm_cache, op1) != perms[perm][1]
+ || !is_eq_or_top (perm_cache, op2, perms[perm][2], op3, perms[perm][3]))
+ return false;
+
+ return compatible_complex_nodes_p (compat_cache, op0, cq[perm][0], op1,
+ cq[perm][1])
+ && compatible_complex_nodes_p (compat_cache, op2, cq[perm][2], op3,
+ cq[perm][3]);
}
/* This function combines two nodes containing only even and only odd lanes
@@ -908,11 +979,12 @@ class complex_mul_pattern : public complex_pattern
public:
void build (vec_info *);
static internal_fn
- matches (complex_operation_t op, slp_tree_to_load_perm_map_t *, slp_tree *,
- vec<slp_tree> *);
+ matches (complex_operation_t op, slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *, slp_tree *, vec<slp_tree> *);
static vect_pattern*
- recognize (slp_tree_to_load_perm_map_t *, slp_tree *);
+ recognize (slp_tree_to_load_perm_map_t *, slp_compat_nodes_map_t *,
+ slp_tree *);
static vect_pattern*
mkInstance (slp_tree *node, vec<slp_tree> *m_ops, internal_fn ifn)
@@ -943,6 +1015,7 @@ class complex_mul_pattern : public complex_pattern
internal_fn
complex_mul_pattern::matches (complex_operation_t op,
slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache,
slp_tree *node, vec<slp_tree> *ops)
{
internal_fn ifn = IFN_LAST;
@@ -990,17 +1063,13 @@ complex_mul_pattern::matches (complex_operation_t op,
|| linear_loads_p (perm_cache, left_op[1]) == PERM_ODDEVEN)
return IFN_LAST;
- bool neg_first = false;
- bool conj_first_operand = false;
- bool is_neg = vect_normalize_conj_loc (right_op, &neg_first);
+ enum _conj_status status;
+ if (!vect_validate_multiplication (perm_cache, compat_cache, left_op,
+ right_op, false, &status))
+ return IFN_LAST;
- if (!is_neg)
+ if (status == CONJ_NONE)
{
- /* A multiplication needs to multiply agains the real pair, otherwise
- the pattern matches that of FMS. */
- if (!vect_validate_multiplication (perm_cache, left_op, PERM_EVENEVEN)
- || vect_normalize_conj_loc (left_op))
- return IFN_LAST;
if (add0)
ifn = IFN_COMPLEX_FMA;
else
@@ -1008,11 +1077,6 @@ complex_mul_pattern::matches (complex_operation_t op,
}
else
{
- if (!vect_validate_multiplication (perm_cache, left_op, right_op,
- neg_first, &conj_first_operand,
- false))
- return IFN_LAST;
-
if(add0)
ifn = IFN_COMPLEX_FMA_CONJ;
else
@@ -1029,19 +1093,13 @@ complex_mul_pattern::matches (complex_operation_t op,
ops->quick_push (add0);
complex_perm_kinds_t kind = linear_loads_p (perm_cache, left_op[0]);
- if (kind == PERM_EVENODD)
+ if (kind == PERM_EVENODD || kind == PERM_TOP)
{
ops->quick_push (left_op[1]);
ops->quick_push (right_op[1]);
ops->quick_push (left_op[0]);
}
- else if (kind == PERM_TOP)
- {
- ops->quick_push (left_op[1]);
- ops->quick_push (right_op[1]);
- ops->quick_push (left_op[0]);
- }
- else if (kind == PERM_EVENEVEN && !conj_first_operand)
+ else if (kind == PERM_EVENEVEN && status != CONJ_SND)
{
ops->quick_push (left_op[0]);
ops->quick_push (right_op[0]);
@@ -1061,13 +1119,14 @@ complex_mul_pattern::matches (complex_operation_t op,
vect_pattern*
complex_mul_pattern::recognize (slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache,
slp_tree *node)
{
auto_vec<slp_tree> ops;
complex_operation_t op
= vect_detect_pair_op (*node, true, &ops);
internal_fn ifn
- = complex_mul_pattern::matches (op, perm_cache, node, &ops);
+ = complex_mul_pattern::matches (op, perm_cache, compat_cache, node, &ops);
if (ifn == IFN_LAST)
return NULL;
@@ -1115,9 +1174,9 @@ complex_mul_pattern::build (vec_info *vinfo)
/* First re-arrange the children. */
SLP_TREE_CHILDREN (*this->m_node).safe_grow (3);
- SLP_TREE_CHILDREN (*this->m_node)[0] = this->m_ops[0];
- SLP_TREE_CHILDREN (*this->m_node)[1] = this->m_ops[3];
- SLP_TREE_CHILDREN (*this->m_node)[2] = newnode;
+ SLP_TREE_CHILDREN (*this->m_node)[0] = this->m_ops[3];
+ SLP_TREE_CHILDREN (*this->m_node)[1] = newnode;
+ SLP_TREE_CHILDREN (*this->m_node)[2] = this->m_ops[0];
/* Tell the builder to expect an extra argument. */
this->m_num_args++;
@@ -1147,11 +1206,12 @@ class complex_fms_pattern : public complex_pattern
public:
void build (vec_info *);
static internal_fn
- matches (complex_operation_t op, slp_tree_to_load_perm_map_t *, slp_tree *,
- vec<slp_tree> *);
+ matches (complex_operation_t op, slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *, slp_tree *, vec<slp_tree> *);
static vect_pattern*
- recognize (slp_tree_to_load_perm_map_t *, slp_tree *);
+ recognize (slp_tree_to_load_perm_map_t *, slp_compat_nodes_map_t *,
+ slp_tree *);
static vect_pattern*
mkInstance (slp_tree *node, vec<slp_tree> *m_ops, internal_fn ifn)
@@ -1182,6 +1242,7 @@ class complex_fms_pattern : public complex_pattern
internal_fn
complex_fms_pattern::matches (complex_operation_t op,
slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache,
slp_tree * ref_node, vec<slp_tree> *ops)
{
internal_fn ifn = IFN_LAST;
@@ -1197,6 +1258,8 @@ complex_fms_pattern::matches (complex_operation_t op,
if (!vect_match_expression_p (root, MINUS_EXPR))
return IFN_LAST;
+ /* TODO: Support invariants here, with the new layout CADD now
+ can match before we get a chance to try CFMS. */
auto nodes = SLP_TREE_CHILDREN (root);
if (!vect_match_expression_p (nodes[1], MULT_EXPR)
|| vect_detect_pair_op (nodes[0]) != PLUS_MINUS)
@@ -1217,16 +1280,14 @@ complex_fms_pattern::matches (complex_operation_t op,
|| !vect_match_expression_p (l0node[1], MULT_EXPR))
return IFN_LAST;
- bool is_neg = vect_normalize_conj_loc (left_op);
-
- bool conj_first_operand = false;
- if (!vect_validate_multiplication (perm_cache, right_op, left_op, false,
- &conj_first_operand, true))
+ enum _conj_status status;
+ if (!vect_validate_multiplication (perm_cache, compat_cache, right_op,
+ left_op, true, &status))
return IFN_LAST;
- if (!is_neg)
+ if (status == CONJ_NONE)
ifn = IFN_COMPLEX_FMS;
- else if (is_neg)
+ else
ifn = IFN_COMPLEX_FMS_CONJ;
if (!vect_pattern_validate_optab (ifn, *ref_node))
@@ -1243,26 +1304,12 @@ complex_fms_pattern::matches (complex_operation_t op,
ops->quick_push (right_op[1]);
ops->quick_push (left_op[1]);
}
- else if (kind == PERM_TOP)
- {
- ops->quick_push (l0node[0]);
- ops->quick_push (right_op[1]);
- ops->quick_push (right_op[0]);
- ops->quick_push (left_op[0]);
- }
- else if (kind == PERM_EVENEVEN && !is_neg)
- {
- ops->quick_push (l0node[0]);
- ops->quick_push (right_op[1]);
- ops->quick_push (right_op[0]);
- ops->quick_push (left_op[0]);
- }
else
{
ops->quick_push (l0node[0]);
ops->quick_push (right_op[1]);
ops->quick_push (right_op[0]);
- ops->quick_push (left_op[1]);
+ ops->quick_push (left_op[0]);
}
return ifn;
@@ -1272,13 +1319,14 @@ complex_fms_pattern::matches (complex_operation_t op,
vect_pattern*
complex_fms_pattern::recognize (slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache,
slp_tree *node)
{
auto_vec<slp_tree> ops;
complex_operation_t op
= vect_detect_pair_op (*node, true, &ops);
internal_fn ifn
- = complex_fms_pattern::matches (op, perm_cache, node, &ops);
+ = complex_fms_pattern::matches (op, perm_cache, compat_cache, node, &ops);
if (ifn == IFN_LAST)
return NULL;
@@ -1305,9 +1353,9 @@ complex_fms_pattern::build (vec_info *vinfo)
SLP_TREE_CHILDREN (*this->m_node).create (3);
/* First re-arrange the children. */
- SLP_TREE_CHILDREN (*this->m_node).quick_push (this->m_ops[0]);
SLP_TREE_CHILDREN (*this->m_node).quick_push (this->m_ops[1]);
SLP_TREE_CHILDREN (*this->m_node).quick_push (newnode);
+ SLP_TREE_CHILDREN (*this->m_node).quick_push (this->m_ops[0]);
/* And then rewrite the node itself. */
complex_pattern::build (vinfo);
@@ -1334,11 +1382,12 @@ class complex_operations_pattern : public
complex_pattern
public:
void build (vec_info *);
static internal_fn
- matches (complex_operation_t op, slp_tree_to_load_perm_map_t *, slp_tree *,
- vec<slp_tree> *);
+ matches (complex_operation_t op, slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *, slp_tree *, vec<slp_tree> *);
static vect_pattern*
- recognize (slp_tree_to_load_perm_map_t *, slp_tree *);
+ recognize (slp_tree_to_load_perm_map_t *, slp_compat_nodes_map_t *,
+ slp_tree *);
};
/* Dummy matches implementation for proxy object. */
@@ -1347,6 +1396,7 @@ internal_fn
complex_operations_pattern::
matches (complex_operation_t /* op */,
slp_tree_to_load_perm_map_t * /* perm_cache */,
+ slp_compat_nodes_map_t * /* compat_cache */,
slp_tree * /* ref_node */, vec<slp_tree> * /* ops */)
{
return IFN_LAST;
@@ -1356,6 +1406,7 @@ matches (complex_operation_t /* op */,
vect_pattern*
complex_operations_pattern::recognize (slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *ccache,
slp_tree *node)
{
auto_vec<slp_tree> ops;
@@ -1363,15 +1414,15 @@ complex_operations_pattern::recognize
(slp_tree_to_load_perm_map_t *perm_cache,
= vect_detect_pair_op (*node, true, &ops);
internal_fn ifn = IFN_LAST;
- ifn = complex_fms_pattern::matches (op, perm_cache, node, &ops);
+ ifn = complex_fms_pattern::matches (op, perm_cache, ccache, node, &ops);
if (ifn != IFN_LAST)
return complex_fms_pattern::mkInstance (node, &ops, ifn);
- ifn = complex_mul_pattern::matches (op, perm_cache, node, &ops);
+ ifn = complex_mul_pattern::matches (op, perm_cache, ccache, node, &ops);
if (ifn != IFN_LAST)
return complex_mul_pattern::mkInstance (node, &ops, ifn);
- ifn = complex_add_pattern::matches (op, perm_cache, node, &ops);
+ ifn = complex_add_pattern::matches (op, perm_cache, ccache, node, &ops);
if (ifn != IFN_LAST)
return complex_add_pattern::mkInstance (node, &ops, ifn);
@@ -1398,11 +1449,13 @@ class addsub_pattern : public vect_pattern
void build (vec_info *);
static vect_pattern*
- recognize (slp_tree_to_load_perm_map_t *, slp_tree *);
+ recognize (slp_tree_to_load_perm_map_t *, slp_compat_nodes_map_t *,
+ slp_tree *);
};
vect_pattern *
-addsub_pattern::recognize (slp_tree_to_load_perm_map_t *, slp_tree *node_)
+addsub_pattern::recognize (slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *, slp_tree *node_)
{
slp_tree node = *node_;
if (SLP_TREE_CODE (node) != VEC_PERM_EXPR
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index
b912c3577df61a694d5bb9e22c5303fe6a48ab6e..cb577f8a612d583254e42bb06a6d7a0875de5e75
100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -804,7 +804,7 @@ vect_get_and_check_slp_defs (vec_info *vinfo, unsigned char
swap,
/* Return true if call statements CALL1 and CALL2 are similar enough
to be combined into the same SLP group. */
-static bool
+bool
compatible_calls_p (gcall *call1, gcall *call2)
{
unsigned int nargs = gimple_call_num_args (call1);
@@ -2907,6 +2907,7 @@ optimize_load_redistribution
(scalar_stmts_to_slp_tree_map_t *bst_map,
static bool
vect_match_slp_patterns_2 (slp_tree *ref_node, vec_info *vinfo,
slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache,
hash_set<slp_tree> *visited)
{
unsigned i;
@@ -2918,11 +2919,13 @@ vect_match_slp_patterns_2 (slp_tree *ref_node, vec_info
*vinfo,
slp_tree child;
FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
found_p |= vect_match_slp_patterns_2 (&SLP_TREE_CHILDREN (node)[i],
- vinfo, perm_cache, visited);
+ vinfo, perm_cache, compat_cache,
+ visited);
for (unsigned x = 0; x < num__slp_patterns; x++)
{
- vect_pattern *pattern = slp_patterns[x] (perm_cache, ref_node);
+ vect_pattern *pattern
+ = slp_patterns[x] (perm_cache, compat_cache, ref_node);
if (pattern)
{
pattern->build (vinfo);
@@ -2943,7 +2946,8 @@ vect_match_slp_patterns_2 (slp_tree *ref_node, vec_info
*vinfo,
static bool
vect_match_slp_patterns (slp_instance instance, vec_info *vinfo,
hash_set<slp_tree> *visited,
- slp_tree_to_load_perm_map_t *perm_cache)
+ slp_tree_to_load_perm_map_t *perm_cache,
+ slp_compat_nodes_map_t *compat_cache)
{
DUMP_VECT_SCOPE ("vect_match_slp_patterns");
slp_tree *ref_node = &SLP_INSTANCE_TREE (instance);
@@ -2953,7 +2957,8 @@ vect_match_slp_patterns (slp_instance instance, vec_info
*vinfo,
"Analyzing SLP tree %p for patterns\n",
SLP_INSTANCE_TREE (instance));
- return vect_match_slp_patterns_2 (ref_node, vinfo, perm_cache, visited);
+ return vect_match_slp_patterns_2 (ref_node, vinfo, perm_cache, compat_cache,
+ visited);
}
/* STMT_INFO is a store group of size GROUP_SIZE that we are considering
@@ -3437,12 +3442,14 @@ vect_analyze_slp (vec_info *vinfo, unsigned
max_tree_size)
hash_set<slp_tree> visited_patterns;
slp_tree_to_load_perm_map_t perm_cache;
+ slp_compat_nodes_map_t compat_cache;
/* See if any patterns can be found in the SLP tree. */
bool pattern_found = false;
FOR_EACH_VEC_ELT (LOOP_VINFO_SLP_INSTANCES (vinfo), i, instance)
pattern_found |= vect_match_slp_patterns (instance, vinfo,
- &visited_patterns, &perm_cache);
+ &visited_patterns, &perm_cache,
+ &compat_cache);
/* If any were found optimize permutations of loads. */
if (pattern_found)
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index
2f6e1e268fb07e9de065ff9c45af87546e565d66..83cd0919c7838c65576e1debd881e0ec636a605a
100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -2268,6 +2268,7 @@ extern void duplicate_and_interleave (vec_info *,
gimple_seq *, tree,
extern int vect_get_place_in_interleaving_chain (stmt_vec_info, stmt_vec_info);
extern slp_tree vect_create_new_slp_node (unsigned, tree_code);
extern void vect_free_slp_tree (slp_tree);
+extern bool compatible_calls_p (gcall *, gcall *);
/* In tree-vect-patterns.c. */
extern void
@@ -2306,6 +2307,12 @@ typedef enum _complex_perm_kinds {
typedef hash_map <slp_tree, complex_perm_kinds_t>
slp_tree_to_load_perm_map_t;
+/* Cache from nodes pair to being compatible or not. */
+typedef pair_hash <nofree_ptr_hash <_slp_tree>,
+ nofree_ptr_hash <_slp_tree>> slp_node_hash;
+typedef hash_map <slp_node_hash, bool> slp_compat_nodes_map_t;
+
+
/* Vector pattern matcher base class. All SLP pattern matchers must inherit
from this type. */
@@ -2338,7 +2345,8 @@ class vect_pattern
public:
/* Create a new instance of the pattern matcher class of the given type.
*/
- static vect_pattern* recognize (slp_tree_to_load_perm_map_t *, slp_tree *);
+ static vect_pattern* recognize (slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *, slp_tree *);
/* Build the pattern from the data collected so far. */
virtual void build (vec_info *) = 0;
@@ -2352,6 +2360,7 @@ class vect_pattern
/* Function pointer to create a new pattern matcher from a generic type. */
typedef vect_pattern* (*vect_pattern_decl_t) (slp_tree_to_load_perm_map_t *,
+ slp_compat_nodes_map_t *,
slp_tree *);
/* List of supported pattern matchers. */
rb15145.patch
Description: rb15145.patch
