OpenE2K/gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add FMADDSUB and FMSUBADD SLP vectorization patterns and optabs

Browse Source 
This adds named expanders for vec_fmaddsub<mode>4 and
vec_fmsubadd<mode>4 which map to x86 vfmaddsubXXXp{ds} and
vfmsubaddXXXp{ds} instructions.  This complements the previous
addition of ADDSUB support.

x86 lacks SUBADD and the negate variants of FMA with mixed
plus minus so I did not add optabs or patterns for those but
it would not be difficult if there's a target that has them.

2021-07-05  Richard Biener  <rguenther@suse.de>

	* doc/md.texi (vec_fmaddsub<mode>4): Document.
	(vec_fmsubadd<mode>4): Likewise.
	* optabs.def (vec_fmaddsub$a4): Add.
	(vec_fmsubadd$a4): Likewise.
	* internal-fn.def (IFN_VEC_FMADDSUB): Add.
	(IFN_VEC_FMSUBADD): Likewise.
	* tree-vect-slp-patterns.c (addsub_pattern::recognize):
	Refactor to handle IFN_VEC_FMADDSUB and IFN_VEC_FMSUBADD.
	(addsub_pattern::build): Likewise.
	* tree-vect-slp.c (vect_optimize_slp): CFN_VEC_FMADDSUB
	and CFN_VEC_FMSUBADD are not transparent for permutes.
	* config/i386/sse.md (vec_fmaddsub<mode>4): New expander.
	(vec_fmsubadd<mode>4): Likewise.

	* gcc.target/i386/vect-fmaddsubXXXpd.c: New testcase.
	* gcc.target/i386/vect-fmaddsubXXXps.c: Likewise.
	* gcc.target/i386/vect-fmsubaddXXXpd.c: Likewise.
	* gcc.target/i386/vect-fmsubaddXXXps.c: Likewise.
This commit is contained in:
Richard Biener 2021-07-05 15:51:49 +02:00
parent 9f489a5731
commit 7d810646d4
10 changed files with 308 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
gcc/config/i386/sse.md
View File

@ -4644,6 +4644,25 @@
;;
;; But this doesn't seem useful in practice.
(define_expand "vec_fmaddsub<mode>4"
[(set (match_operand:VF 0 "register_operand")
(unspec:VF
[(match_operand:VF 1 "nonimmediate_operand")
(match_operand:VF 2 "nonimmediate_operand")
(match_operand:VF 3 "nonimmediate_operand")]
UNSPEC_FMADDSUB))]
"TARGET_FMA || TARGET_FMA4 || (<MODE_SIZE> == 64 || TARGET_AVX512VL)")
(define_expand "vec_fmsubadd<mode>4"
[(set (match_operand:VF 0 "register_operand")
(unspec:VF
[(match_operand:VF 1 "nonimmediate_operand")
(match_operand:VF 2 "nonimmediate_operand")
(neg:VF
(match_operand:VF 3 "nonimmediate_operand"))]
UNSPEC_FMADDSUB))]
"TARGET_FMA || TARGET_FMA4 || (<MODE_SIZE> == 64 || TARGET_AVX512VL)")
(define_expand "fmaddsub_<mode>"
[(set (match_operand:VF 0 "register_operand")
(unspec:VF

14
gcc/doc/md.texi
View File

@ -5688,6 +5688,20 @@ Alternating subtract, add with even lanes doing subtract and odd
lanes doing addition. Operands 1 and 2 and the outout operand are vectors
with mode @var{m}.
@cindex @code{vec_fmaddsub@var{m}4} instruction pattern
@item @samp{vec_fmaddsub@var{m}4}
Alternating multiply subtract, add with even lanes doing subtract and odd
lanes doing addition of the third operand to the multiplication result
of the first two operands. Operands 1, 2 and 3 and the outout operand are vectors
with mode @var{m}.
@cindex @code{vec_fmsubadd@var{m}4} instruction pattern
@item @samp{vec_fmsubadd@var{m}4}
Alternating multiply add, subtract with even lanes doing addition and odd
lanes doing subtraction of the third operand to the multiplication result
of the first two operands. Operands 1, 2 and 3 and the outout operand are vectors
with mode @var{m}.
These instructions are not allowed to @code{FAIL}.
@cindex @code{mulhisi3} instruction pattern

3
gcc/internal-fn.def
View File

@ -282,7 +282,8 @@ DEF_INTERNAL_OPTAB_FN (COMPLEX_ADD_ROT270, ECF_CONST, cadd270, binary)
DEF_INTERNAL_OPTAB_FN (COMPLEX_MUL, ECF_CONST, cmul, binary)
DEF_INTERNAL_OPTAB_FN (COMPLEX_MUL_CONJ, ECF_CONST, cmul_conj, binary)
DEF_INTERNAL_OPTAB_FN (VEC_ADDSUB, ECF_CONST, vec_addsub, binary)
DEF_INTERNAL_OPTAB_FN (VEC_FMADDSUB, ECF_CONST, vec_fmaddsub, ternary)
DEF_INTERNAL_OPTAB_FN (VEC_FMSUBADD, ECF_CONST, vec_fmsubadd, ternary)
/* FP scales. */
DEF_INTERNAL_FLT_FN (LDEXP, ECF_CONST, ldexp, binary)

2
gcc/optabs.def
View File

@ -408,6 +408,8 @@ OPTAB_D (vec_widen_usubl_lo_optab, "vec_widen_usubl_lo_$a")
OPTAB_D (vec_widen_uaddl_hi_optab, "vec_widen_uaddl_hi_$a")
OPTAB_D (vec_widen_uaddl_lo_optab, "vec_widen_uaddl_lo_$a")
OPTAB_D (vec_addsub_optab, "vec_addsub$a3")
OPTAB_D (vec_fmaddsub_optab, "vec_fmaddsub$a4")
OPTAB_D (vec_fmsubadd_optab, "vec_fmsubadd$a4")
OPTAB_D (sync_add_optab, "sync_add$I$a")
OPTAB_D (sync_and_optab, "sync_and$I$a")

34
gcc/testsuite/gcc.target/i386/vect-fmaddsubXXXpd.c Normal file
View File

@ -0,0 +1,34 @@
/* { dg-do run } */
/* { dg-require-effective-target fma } */
/* { dg-options "-O3 -mfma -save-temps" } */
#include "fma-check.h"
void __attribute__((noipa))
check_fmaddsub (double * __restrict a, double *b, double *c, int n)
{
for (int i = 0; i < n; ++i)
{
a[2*i + 0] = b[2*i + 0] * c[2*i + 0] - a[2*i + 0];
a[2*i + 1] = b[2*i + 1] * c[2*i + 1] + a[2*i + 1];
}
}
static void
fma_test (void)
{
double a[4], b[4], c[4];
for (int i = 0; i < 4; ++i)
{
a[i] = i;
b[i] = 3*i;
c[i] = 7*i;
}
check_fmaddsub (a, b, c, 2);
const double d[4] = { 0., 22., 82., 192. };
for (int i = 0; i < 4; ++i)
if (a[i] != d[i])
__builtin_abort ();
}
/* { dg-final { scan-assembler "fmaddsub...pd" } } */

34
gcc/testsuite/gcc.target/i386/vect-fmaddsubXXXps.c Normal file
View File

@ -0,0 +1,34 @@
/* { dg-do run } */
/* { dg-require-effective-target fma } */
/* { dg-options "-O3 -mfma -save-temps" } */
#include "fma-check.h"
void __attribute__((noipa))
check_fmaddsub (float * __restrict a, float *b, float *c, int n)
{
for (int i = 0; i < n; ++i)
{
a[2*i + 0] = b[2*i + 0] * c[2*i + 0] - a[2*i + 0];
a[2*i + 1] = b[2*i + 1] * c[2*i + 1] + a[2*i + 1];
}
}
static void
fma_test (void)
{
float a[4], b[4], c[4];
for (int i = 0; i < 4; ++i)
{
a[i] = i;
b[i] = 3*i;
c[i] = 7*i;
}
check_fmaddsub (a, b, c, 2);
const float d[4] = { 0., 22., 82., 192. };
for (int i = 0; i < 4; ++i)
if (a[i] != d[i])
__builtin_abort ();
}
/* { dg-final { scan-assembler "fmaddsub...ps" } } */

34
gcc/testsuite/gcc.target/i386/vect-fmsubaddXXXpd.c Normal file
View File

@ -0,0 +1,34 @@
/* { dg-do run } */
/* { dg-require-effective-target fma } */
/* { dg-options "-O3 -mfma -save-temps" } */
#include "fma-check.h"
void __attribute__((noipa))
check_fmsubadd (double * __restrict a, double *b, double *c, int n)
{
for (int i = 0; i < n; ++i)
{
a[2*i + 0] = b[2*i + 0] * c[2*i + 0] + a[2*i + 0];
a[2*i + 1] = b[2*i + 1] * c[2*i + 1] - a[2*i + 1];
}
}
static void
fma_test (void)
{
double a[4], b[4], c[4];
for (int i = 0; i < 4; ++i)
{
a[i] = i;
b[i] = 3*i;
c[i] = 7*i;
}
check_fmsubadd (a, b, c, 2);
const double d[4] = { 0., 20., 86., 186. };
for (int i = 0; i < 4; ++i)
if (a[i] != d[i])
__builtin_abort ();
}
/* { dg-final { scan-assembler "fmsubadd...pd" } } */

34
gcc/testsuite/gcc.target/i386/vect-fmsubaddXXXps.c Normal file
View File

@ -0,0 +1,34 @@
/* { dg-do run } */
/* { dg-require-effective-target fma } */
/* { dg-options "-O3 -mfma -save-temps" } */
#include "fma-check.h"
void __attribute__((noipa))
check_fmsubadd (float * __restrict a, float *b, float *c, int n)
{
for (int i = 0; i < n; ++i)
{
a[2*i + 0] = b[2*i + 0] * c[2*i + 0] + a[2*i + 0];
a[2*i + 1] = b[2*i + 1] * c[2*i + 1] - a[2*i + 1];
}
}
static void
fma_test (void)
{
float a[4], b[4], c[4];
for (int i = 0; i < 4; ++i)
{
a[i] = i;
b[i] = 3*i;
c[i] = 7*i;
}
check_fmsubadd (a, b, c, 2);
const float d[4] = { 0., 20., 86., 186. };
for (int i = 0; i < 4; ++i)
if (a[i] != d[i])
__builtin_abort ();
}
/* { dg-final { scan-assembler "fmsubadd...ps" } } */

186
gcc/tree-vect-slp-patterns.c
View File

@ -1496,8 +1496,8 @@ complex_operations_pattern::build (vec_info * /* vinfo */)
class addsub_pattern : public vect_pattern
{
public:
addsub_pattern (slp_tree *node)
: vect_pattern (node, NULL, IFN_VEC_ADDSUB) {};
addsub_pattern (slp_tree *node, internal_fn ifn)
: vect_pattern (node, NULL, ifn) {};
void build (vec_info *);
@ -1510,46 +1510,68 @@ addsub_pattern::recognize (slp_tree_to_load_perm_map_t *, slp_tree *node_)
{
slp_tree node = *node_;
if (SLP_TREE_CODE (node) != VEC_PERM_EXPR
|| SLP_TREE_CHILDREN (node).length () != 2)
|| SLP_TREE_CHILDREN (node).length () != 2
|| SLP_TREE_LANE_PERMUTATION (node).length () % 2)
return NULL;
/* Match a blend of a plus and a minus op with the same number of plus and
minus lanes on the same operands. */
slp_tree sub = SLP_TREE_CHILDREN (node)[0];
slp_tree add = SLP_TREE_CHILDREN (node)[1];
bool swapped_p = false;
if (vect_match_expression_p (sub, PLUS_EXPR))
{
std::swap (add, sub);
swapped_p = true;
}
if (!(vect_match_expression_p (add, PLUS_EXPR)
&& vect_match_expression_p (sub, MINUS_EXPR)))
unsigned l0 = SLP_TREE_LANE_PERMUTATION (node)[0].first;
unsigned l1 = SLP_TREE_LANE_PERMUTATION (node)[1].first;
if (l0 == l1)
return NULL;
if (!((SLP_TREE_CHILDREN (sub)[0] == SLP_TREE_CHILDREN (add)[0]
&& SLP_TREE_CHILDREN (sub)[1] == SLP_TREE_CHILDREN (add)[1])
|| (SLP_TREE_CHILDREN (sub)[0] == SLP_TREE_CHILDREN (add)[1]
&& SLP_TREE_CHILDREN (sub)[1] == SLP_TREE_CHILDREN (add)[0])))
bool l0add_p = vect_match_expression_p (SLP_TREE_CHILDREN (node)[l0],
PLUS_EXPR);
if (!l0add_p
&& !vect_match_expression_p (SLP_TREE_CHILDREN (node)[l0], MINUS_EXPR))
return NULL;
bool l1add_p = vect_match_expression_p (SLP_TREE_CHILDREN (node)[l1],
PLUS_EXPR);
if (!l1add_p
&& !vect_match_expression_p (SLP_TREE_CHILDREN (node)[l1], MINUS_EXPR))
return NULL;
slp_tree l0node = SLP_TREE_CHILDREN (node)[l0];
slp_tree l1node = SLP_TREE_CHILDREN (node)[l1];
if (!((SLP_TREE_CHILDREN (l0node)[0] == SLP_TREE_CHILDREN (l1node)[0]
&& SLP_TREE_CHILDREN (l0node)[1] == SLP_TREE_CHILDREN (l1node)[1])
|| (SLP_TREE_CHILDREN (l0node)[0] == SLP_TREE_CHILDREN (l1node)[1]
&& SLP_TREE_CHILDREN (l0node)[1] == SLP_TREE_CHILDREN (l1node)[0])))
return NULL;
for (unsigned i = 0; i < SLP_TREE_LANE_PERMUTATION (node).length (); ++i)
{
std::pair<unsigned, unsigned> perm = SLP_TREE_LANE_PERMUTATION (node)[i];
if (swapped_p)
perm.first = perm.first == 0 ? 1 : 0;
/* It has to be alternating -, +, -, ...
/* It has to be alternating -, +, -,
While we could permute the .ADDSUB inputs and the .ADDSUB output
that's only profitable over the add + sub + blend if at least
one of the permute is optimized which we can't determine here. */
if (perm.first != (i & 1)
if (perm.first != ((i & 1) ? l1 : l0)
|| perm.second != i)
return NULL;
}
if (!vect_pattern_validate_optab (IFN_VEC_ADDSUB, node))
return NULL;
/* Now we have either { -, +, -, + ... } (!l0add_p) or { +, -, +, - ... }
(l0add_p), see whether we have FMA variants. */
if (!l0add_p
&& vect_match_expression_p (SLP_TREE_CHILDREN (l0node)[0], MULT_EXPR))
{
/* (c * d) -+ a */
if (vect_pattern_validate_optab (IFN_VEC_FMADDSUB, node))
return new addsub_pattern (node_, IFN_VEC_FMADDSUB);
}
else if (l0add_p
&& vect_match_expression_p (SLP_TREE_CHILDREN (l1node)[0], MULT_EXPR))
{
/* (c * d) +- a */
if (vect_pattern_validate_optab (IFN_VEC_FMSUBADD, node))
return new addsub_pattern (node_, IFN_VEC_FMSUBADD);
}
return new addsub_pattern (node_);
if (!l0add_p && vect_pattern_validate_optab (IFN_VEC_ADDSUB, node))
return new addsub_pattern (node_, IFN_VEC_ADDSUB);
return NULL;
}
void
@ -1557,38 +1579,96 @@ addsub_pattern::build (vec_info *vinfo)
{
slp_tree node = *m_node;
slp_tree sub = SLP_TREE_CHILDREN (node)[0];
slp_tree add = SLP_TREE_CHILDREN (node)[1];
if (vect_match_expression_p (sub, PLUS_EXPR))
std::swap (add, sub);
unsigned l0 = SLP_TREE_LANE_PERMUTATION (node)[0].first;
unsigned l1 = SLP_TREE_LANE_PERMUTATION (node)[1].first;
/* Modify the blend node in-place. */
SLP_TREE_CHILDREN (node)[0] = SLP_TREE_CHILDREN (sub)[0];
SLP_TREE_CHILDREN (node)[1] = SLP_TREE_CHILDREN (sub)[1];
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[0])++;
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[1])++;
switch (m_ifn)
{
case IFN_VEC_ADDSUB:
{
slp_tree sub = SLP_TREE_CHILDREN (node)[l0];
slp_tree add = SLP_TREE_CHILDREN (node)[l1];
/* Build IFN_VEC_ADDSUB from the sub representative operands. */
stmt_vec_info rep = SLP_TREE_REPRESENTATIVE (sub);
gcall *call = gimple_build_call_internal (IFN_VEC_ADDSUB, 2,
gimple_assign_rhs1 (rep->stmt),
gimple_assign_rhs2 (rep->stmt));
gimple_call_set_lhs (call, make_ssa_name
(TREE_TYPE (gimple_assign_lhs (rep->stmt))));
gimple_call_set_nothrow (call, true);
gimple_set_bb (call, gimple_bb (rep->stmt));
stmt_vec_info new_rep = vinfo->add_pattern_stmt (call, rep);
SLP_TREE_REPRESENTATIVE (node) = new_rep;
STMT_VINFO_RELEVANT (new_rep) = vect_used_in_scope;
STMT_SLP_TYPE (new_rep) = pure_slp;
STMT_VINFO_VECTYPE (new_rep) = SLP_TREE_VECTYPE (node);
STMT_VINFO_SLP_VECT_ONLY_PATTERN (new_rep) = true;
STMT_VINFO_REDUC_DEF (new_rep) = STMT_VINFO_REDUC_DEF (vect_orig_stmt (rep));
SLP_TREE_CODE (node) = ERROR_MARK;
SLP_TREE_LANE_PERMUTATION (node).release ();
/* Modify the blend node in-place. */
SLP_TREE_CHILDREN (node)[0] = SLP_TREE_CHILDREN (sub)[0];
SLP_TREE_CHILDREN (node)[1] = SLP_TREE_CHILDREN (sub)[1];
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[0])++;
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[1])++;
vect_free_slp_tree (sub);
vect_free_slp_tree (add);
/* Build IFN_VEC_ADDSUB from the sub representative operands. */
stmt_vec_info rep = SLP_TREE_REPRESENTATIVE (sub);
gcall *call = gimple_build_call_internal (IFN_VEC_ADDSUB, 2,
gimple_assign_rhs1 (rep->stmt),
gimple_assign_rhs2 (rep->stmt));
gimple_call_set_lhs (call, make_ssa_name
(TREE_TYPE (gimple_assign_lhs (rep->stmt))));
gimple_call_set_nothrow (call, true);
gimple_set_bb (call, gimple_bb (rep->stmt));
stmt_vec_info new_rep = vinfo->add_pattern_stmt (call, rep);
SLP_TREE_REPRESENTATIVE (node) = new_rep;
STMT_VINFO_RELEVANT (new_rep) = vect_used_in_scope;
STMT_SLP_TYPE (new_rep) = pure_slp;
STMT_VINFO_VECTYPE (new_rep) = SLP_TREE_VECTYPE (node);
STMT_VINFO_SLP_VECT_ONLY_PATTERN (new_rep) = true;
STMT_VINFO_REDUC_DEF (new_rep) = STMT_VINFO_REDUC_DEF (vect_orig_stmt (rep));
SLP_TREE_CODE (node) = ERROR_MARK;
SLP_TREE_LANE_PERMUTATION (node).release ();
vect_free_slp_tree (sub);
vect_free_slp_tree (add);
break;
}
case IFN_VEC_FMADDSUB:
case IFN_VEC_FMSUBADD:
{
slp_tree sub, add;
if (m_ifn == IFN_VEC_FMADDSUB)
{
sub = SLP_TREE_CHILDREN (node)[l0];
add = SLP_TREE_CHILDREN (node)[l1];
}
else /* m_ifn == IFN_VEC_FMSUBADD */
{
sub = SLP_TREE_CHILDREN (node)[l1];
add = SLP_TREE_CHILDREN (node)[l0];
}
slp_tree mul = SLP_TREE_CHILDREN (sub)[0];
/* Modify the blend node in-place. */
SLP_TREE_CHILDREN (node).safe_grow (3, true);
SLP_TREE_CHILDREN (node)[0] = SLP_TREE_CHILDREN (mul)[0];
SLP_TREE_CHILDREN (node)[1] = SLP_TREE_CHILDREN (mul)[1];
SLP_TREE_CHILDREN (node)[2] = SLP_TREE_CHILDREN (sub)[1];
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[0])++;
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[1])++;
SLP_TREE_REF_COUNT (SLP_TREE_CHILDREN (node)[2])++;
/* Build IFN_VEC_FMADDSUB from the mul/sub representative operands. */
stmt_vec_info srep = SLP_TREE_REPRESENTATIVE (sub);
stmt_vec_info mrep = SLP_TREE_REPRESENTATIVE (mul);
gcall *call = gimple_build_call_internal (m_ifn, 3,
gimple_assign_rhs1 (mrep->stmt),
gimple_assign_rhs2 (mrep->stmt),
gimple_assign_rhs2 (srep->stmt));
gimple_call_set_lhs (call, make_ssa_name
(TREE_TYPE (gimple_assign_lhs (srep->stmt))));
gimple_call_set_nothrow (call, true);
gimple_set_bb (call, gimple_bb (srep->stmt));
stmt_vec_info new_rep = vinfo->add_pattern_stmt (call, srep);
SLP_TREE_REPRESENTATIVE (node) = new_rep;
STMT_VINFO_RELEVANT (new_rep) = vect_used_in_scope;
STMT_SLP_TYPE (new_rep) = pure_slp;
STMT_VINFO_VECTYPE (new_rep) = SLP_TREE_VECTYPE (node);
STMT_VINFO_SLP_VECT_ONLY_PATTERN (new_rep) = true;
STMT_VINFO_REDUC_DEF (new_rep) = STMT_VINFO_REDUC_DEF (vect_orig_stmt (srep));
SLP_TREE_CODE (node) = ERROR_MARK;
SLP_TREE_LANE_PERMUTATION (node).release ();
vect_free_slp_tree (sub);
vect_free_slp_tree (add);
break;
}
default:;
}
}
/*******************************************************************************

2
gcc/tree-vect-slp.c
View File

@ -3728,6 +3728,8 @@ vect_optimize_slp (vec_info *vinfo)
case CFN_COMPLEX_MUL:
case CFN_COMPLEX_MUL_CONJ:
case CFN_VEC_ADDSUB:
case CFN_VEC_FMADDSUB:
case CFN_VEC_FMSUBADD:
vertices[idx].perm_in = 0;
vertices[idx].perm_out = 0;
default:;