aboutsummaryrefslogtreecommitdiff
path: root/gcc/config/rs6000/rs6000.cc
diff options
context:
space:
mode:
Diffstat (limited to 'gcc/config/rs6000/rs6000.cc')
-rw-r--r--gcc/config/rs6000/rs6000.cc102
1 files changed, 48 insertions, 54 deletions
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 737c3d6..764b499 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -55,7 +55,6 @@
#include "output.h"
#include "common/common-target.h"
#include "langhooks.h"
-#include "reload.h"
#include "sched-int.h"
#include "gimplify.h"
#include "gimple-iterator.h"
@@ -4952,10 +4951,19 @@ static bool
rs6000_builtin_support_vector_misalignment (machine_mode mode,
const_tree type,
int misalignment,
- bool is_packed)
+ bool is_packed,
+ bool is_gather_scatter)
{
if (TARGET_VSX)
{
+ if (is_gather_scatter)
+ {
+ if (TARGET_ALTIVEC && is_packed)
+ return false;
+ else
+ return true;
+ }
+
if (TARGET_EFFICIENT_UNALIGNED_VSX)
return true;
@@ -5166,6 +5174,7 @@ public:
protected:
void update_target_cost_per_stmt (vect_cost_for_stmt, stmt_vec_info,
+ slp_tree node,
vect_cost_model_location, unsigned int);
void density_test (loop_vec_info);
void adjust_vect_cost_per_loop (loop_vec_info);
@@ -5313,6 +5322,7 @@ rs6000_adjust_vect_cost_per_stmt (enum vect_cost_for_stmt kind,
void
rs6000_cost_data::update_target_cost_per_stmt (vect_cost_for_stmt kind,
stmt_vec_info stmt_info,
+ slp_tree node,
vect_cost_model_location where,
unsigned int orig_count)
{
@@ -5373,12 +5383,12 @@ rs6000_cost_data::update_target_cost_per_stmt (vect_cost_for_stmt kind,
or may not need to apply. When finalizing the cost of the loop,
the extra penalty is applied when the load density heuristics
are satisfied. */
- if (kind == vec_construct && stmt_info
- && STMT_VINFO_TYPE (stmt_info) == load_vec_info_type
- && (STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info) == VMAT_ELEMENTWISE
- || STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info) == VMAT_STRIDED_SLP))
+ if (kind == vec_construct && node
+ && SLP_TREE_TYPE (node) == load_vec_info_type
+ && (SLP_TREE_MEMORY_ACCESS_TYPE (node) == VMAT_ELEMENTWISE
+ || SLP_TREE_MEMORY_ACCESS_TYPE (node) == VMAT_STRIDED_SLP))
{
- tree vectype = STMT_VINFO_VECTYPE (stmt_info);
+ tree vectype = SLP_TREE_VECTYPE (node);
unsigned int nunits = vect_nunits_for_cost (vectype);
/* As PR103702 shows, it's possible that vectorizer wants to do
costings for only one unit here, it's no need to do any
@@ -5407,7 +5417,7 @@ rs6000_cost_data::update_target_cost_per_stmt (vect_cost_for_stmt kind,
unsigned
rs6000_cost_data::add_stmt_cost (int count, vect_cost_for_stmt kind,
- stmt_vec_info stmt_info, slp_tree,
+ stmt_vec_info stmt_info, slp_tree node,
tree vectype, int misalign,
vect_cost_model_location where)
{
@@ -5425,7 +5435,7 @@ rs6000_cost_data::add_stmt_cost (int count, vect_cost_for_stmt kind,
retval = adjust_cost_for_freq (stmt_info, where, count * stmt_cost);
m_costs[where] += retval;
- update_target_cost_per_stmt (kind, stmt_info, where, orig_count);
+ update_target_cost_per_stmt (kind, stmt_info, node, where, orig_count);
}
return retval;
@@ -9259,8 +9269,7 @@ rs6000_debug_legitimize_address (rtx x, rtx oldx, machine_mode mode)
start_sequence ();
ret = rs6000_legitimize_address (x, oldx, mode);
- insns = get_insns ();
- end_sequence ();
+ insns = end_sequence ();
if (ret != x)
{
@@ -10311,15 +10320,18 @@ can_be_rotated_to_negative_lis (HOST_WIDE_INT c, int *rot)
/* case b. xx0..01..1xx: some of 15 x's (and some of 16 0's) are
rotated over the highest bit. */
- int pos_one = clz_hwi ((c << 16) >> 16);
- middle_zeros = ctz_hwi (c >> (HOST_BITS_PER_WIDE_INT - pos_one));
- int middle_ones = clz_hwi (~(c << pos_one));
- if (middle_zeros >= 16 && middle_ones >= 33)
+ unsigned HOST_WIDE_INT uc = c;
+ int pos_one = clz_hwi ((HOST_WIDE_INT) (uc << 16) >> 16);
+ if (pos_one != 0)
{
- *rot = pos_one;
- return true;
+ middle_zeros = ctz_hwi (c >> (HOST_BITS_PER_WIDE_INT - pos_one));
+ int middle_ones = clz_hwi (~(uc << pos_one));
+ if (middle_zeros >= 16 && middle_ones >= 33)
+ {
+ *rot = pos_one;
+ return true;
+ }
}
-
return false;
}
@@ -10436,7 +10448,8 @@ can_be_built_by_li_and_rldic (HOST_WIDE_INT c, int *shift, HOST_WIDE_INT *mask)
if (lz >= HOST_BITS_PER_WIDE_INT)
return false;
- int middle_ones = clz_hwi (~(c << lz));
+ unsigned HOST_WIDE_INT uc = c;
+ int middle_ones = clz_hwi (~(uc << lz));
if (tz + lz + middle_ones >= ones
&& (tz - lz) < HOST_BITS_PER_WIDE_INT
&& tz < HOST_BITS_PER_WIDE_INT)
@@ -10470,7 +10483,7 @@ can_be_built_by_li_and_rldic (HOST_WIDE_INT c, int *shift, HOST_WIDE_INT *mask)
if (!IN_RANGE (pos_first_1, 1, HOST_BITS_PER_WIDE_INT-1))
return false;
- middle_ones = clz_hwi (~c << pos_first_1);
+ middle_ones = clz_hwi ((~(unsigned HOST_WIDE_INT) c) << pos_first_1);
middle_zeros = ctz_hwi (c >> (HOST_BITS_PER_WIDE_INT - pos_first_1));
if (pos_first_1 < HOST_BITS_PER_WIDE_INT
&& middle_ones + middle_zeros < HOST_BITS_PER_WIDE_INT
@@ -10572,7 +10585,8 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c, int *num_insns)
{
/* li/lis; rldicX */
unsigned HOST_WIDE_INT imm = (c | ~mask);
- imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
+ if (shift != 0)
+ imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
count_or_emit_insn (temp, GEN_INT (imm));
if (shift != 0)
@@ -25314,7 +25328,6 @@ rs6000_get_function_versions_dispatcher (void *decl)
struct cgraph_node *node = NULL;
struct cgraph_node *default_node = NULL;
struct cgraph_function_version_info *node_v = NULL;
- struct cgraph_function_version_info *first_v = NULL;
tree dispatch_decl = NULL;
@@ -25334,38 +25347,16 @@ rs6000_get_function_versions_dispatcher (void *decl)
if (node_v->dispatcher_resolver != NULL)
return node_v->dispatcher_resolver;
- /* Find the default version and make it the first node. */
- first_v = node_v;
- /* Go to the beginning of the chain. */
- while (first_v->prev != NULL)
- first_v = first_v->prev;
-
- default_version_info = first_v;
- while (default_version_info != NULL)
- {
- const tree decl2 = default_version_info->this_node->decl;
- if (is_function_default_version (decl2))
- break;
- default_version_info = default_version_info->next;
- }
+ /* The default node is always the beginning of the chain. */
+ default_version_info = node_v;
+ while (default_version_info->prev)
+ default_version_info = default_version_info->prev;
+ default_node = default_version_info->this_node;
/* If there is no default node, just return NULL. */
- if (default_version_info == NULL)
+ if (!is_function_default_version (default_node->decl))
return NULL;
- /* Make default info the first node. */
- if (first_v != default_version_info)
- {
- default_version_info->prev->next = default_version_info->next;
- if (default_version_info->next)
- default_version_info->next->prev = default_version_info->prev;
- first_v->prev = default_version_info;
- default_version_info->next = first_v;
- default_version_info->prev = NULL;
- }
-
- default_node = default_version_info->this_node;
-
#ifndef TARGET_LIBC_PROVIDES_HWCAP_IN_TCB
error_at (DECL_SOURCE_LOCATION (default_node->decl),
"%<target_clones%> attribute needs GLIBC (2.23 and newer) that "
@@ -25765,10 +25756,13 @@ rs6000_can_inline_p (tree caller, tree callee)
}
}
- /* Ignore -mpower8-fusion and -mpower10-fusion options for inlining
- purposes. */
- callee_isa &= ~(OPTION_MASK_P8_FUSION | OPTION_MASK_P10_FUSION);
- explicit_isa &= ~(OPTION_MASK_P8_FUSION | OPTION_MASK_P10_FUSION);
+ /* Ignore -mpower8-fusion, -mpower10-fusion and -msave-toc-indirect options
+ for inlining purposes. */
+ HOST_WIDE_INT ignored_isas = (OPTION_MASK_P8_FUSION
+ | OPTION_MASK_P10_FUSION
+ | OPTION_MASK_SAVE_TOC_INDIRECT);
+ callee_isa &= ~ignored_isas;
+ explicit_isa &= ~ignored_isas;
/* The callee's options must be a subset of the caller's options, i.e.
a vsx function may inline an altivec function, but a no-vsx function
generated by cgit v1.1 at 2025-08-08 22:12:30 +0000