Richard Guenther wrote:
> On Tue, Aug 7, 2012 at 4:56 PM, Ulrich Weigand <[email protected]> wrote:
> > Would it be OK to backport this to 4.7 and possibly 4.6?
> I'll defer the decision to the target maintainers. But please double-check
> for any changes in the vectorizer parts when backporting to 4.6.
And here the change as committed to 4.6. I didn't find any relevant changes
in vectorizer code; however, I had to back-port a couple of testcase changes
(to the vect-peel-* tests) to avoid seeing regressions there.
Bye,
Ulrich
ChangeLog:
Backport from mainline
2012-07-30 Ulrich Weigand <[email protected]>
Richard Earnshaw <[email protected]>
* target.def (vector_alignment): New target hook.
* doc/tm.texi.in (TARGET_VECTOR_ALIGNMENT): Document new hook.
* doc/tm.texi: Regenerate.
* targhooks.c (default_vector_alignment): New function.
* targhooks.h (default_vector_alignment): Add prototype.
* stor-layout.c (layout_type): Use targetm.vector_alignment.
* config/arm/arm.c (arm_vector_alignment): New function.
(TARGET_VECTOR_ALIGNMENT): Define.
* tree-vect-data-refs.c (vect_update_misalignment_for_peel): Use
vector type alignment instead of size.
* tree-vect-loop-manip.c (vect_do_peeling_for_loop_bound): Use
element type size directly instead of computing it from alignment.
Fix variable naming and comment.
testsuite/ChangeLog:
Backport from mainline
2012-07-30 Ulrich Weigand <[email protected]>
* lib/target-supports.exp
(check_effective_target_vect_natural_alignment): New function.
* gcc.dg/align-2.c: Only run on targets with natural alignment
of vector types.
* gcc.dg/vect/slp-25.c: Adjust tests for targets without natural
alignment of vector types.
2011-12-21 Michael Zolotukhin <[email protected]>
* gcc.dg/vect/vect-peel-1.c: Adjust test diag-scans to fix fail on AVX.
* gcc.dg/vect/vect-peel-2.c: Ditto.
2011-06-21 Ira Rosen <[email protected]>
PR testsuite/49443
* gcc.dg/vect/vect-peel-3.c: Expect to fail on vect_no_align
targets.
* gcc.dg/vect/vect-peel-4.c: Likewise.
2011-06-14 Ira Rosen <[email protected]>
* gcc.dg/vect/vect-peel-3.c: Adjust misalignment values
for double-word vectors.
* gcc.dg/vect/vect-peel-4.c: Likewise.
Index: gcc/doc/tm.texi
===================================================================
*** gcc/doc/tm.texi (revision 190202)
--- gcc/doc/tm.texi (working copy)
*************** make it all fit in fewer cache lines.
*** 1118,1123 ****
--- 1118,1131 ----
If the value of this macro has a type, it should be an unsigned type.
@end defmac
+ @deftypefn {Target Hook} HOST_WIDE_INT TARGET_VECTOR_ALIGNMENT (const_tree
@var{type})
+ This hook can be used to define the alignment for a vector of type
+ @var{type}, in order to comply with a platform ABI. The default is to
+ require natural alignment for vector types. The alignment returned by
+ this hook must be a power-of-two multiple of the default alignment of
+ the vector element type.
+ @end deftypefn
+
@defmac STACK_SLOT_ALIGNMENT (@var{type}, @var{mode}, @var{basic-align})
If defined, a C expression to compute the alignment for stack slot.
@var{type} is the data type, @var{mode} is the widest mode available,
Index: gcc/doc/tm.texi.in
===================================================================
*** gcc/doc/tm.texi.in (revision 190202)
--- gcc/doc/tm.texi.in (working copy)
*************** make it all fit in fewer cache lines.
*** 1108,1113 ****
--- 1108,1115 ----
If the value of this macro has a type, it should be an unsigned type.
@end defmac
+ @hook TARGET_VECTOR_ALIGNMENT
+
@defmac STACK_SLOT_ALIGNMENT (@var{type}, @var{mode}, @var{basic-align})
If defined, a C expression to compute the alignment for stack slot.
@var{type} is the data type, @var{mode} is the widest mode available,
Index: gcc/targhooks.c
===================================================================
*** gcc/targhooks.c (revision 190202)
--- gcc/targhooks.c (working copy)
*************** tree default_mangle_decl_assembler_name
*** 979,984 ****
--- 979,991 ----
return id;
}
+ /* Default to natural alignment for vector types. */
+ HOST_WIDE_INT
+ default_vector_alignment (const_tree type)
+ {
+ return tree_low_cst (TYPE_SIZE (type), 0);
+ }
+
bool
default_builtin_vector_alignment_reachable (const_tree type, bool is_packed)
{
Index: gcc/targhooks.h
===================================================================
*** gcc/targhooks.h (revision 190202)
--- gcc/targhooks.h (working copy)
*************** extern int default_builtin_vectorization
*** 85,90 ****
--- 85,92 ----
extern tree default_builtin_reciprocal (unsigned int, bool, bool);
+ extern HOST_WIDE_INT default_vector_alignment (const_tree);
+
extern bool default_builtin_vector_alignment_reachable (const_tree, bool);
extern bool
default_builtin_support_vector_misalignment (enum machine_mode mode,
Index: gcc/target.def
===================================================================
*** gcc/target.def (revision 190202)
--- gcc/target.def (working copy)
*************** DEFHOOK
*** 1611,1616 ****
--- 1611,1626 ----
bool, (enum machine_mode mode),
hook_bool_mode_false)
+ DEFHOOK
+ (vector_alignment,
+ "This hook can be used to define the alignment for a vector of type\n\
+ @var{type}, in order to comply with a platform ABI. The default is to\n\
+ require natural alignment for vector types. The alignment returned by\n\
+ this hook must be a power-of-two multiple of the default alignment of\n\
+ the vector element type.",
+ HOST_WIDE_INT, (const_tree type),
+ default_vector_alignment)
+
/* Compute cost of moving data from a register of class FROM to one of
TO, using MODE. */
DEFHOOK
Index: gcc/tree-vect-loop-manip.c
===================================================================
*** gcc/tree-vect-loop-manip.c (revision 190202)
--- gcc/tree-vect-loop-manip.c (working copy)
*************** vect_do_peeling_for_loop_bound (loop_vec
*** 2008,2014 ****
If the misalignment of DR is known at compile time:
addr_mis = int mis = DR_MISALIGNMENT (dr);
Else, compute address misalignment in bytes:
! addr_mis = addr & (vectype_size - 1)
prolog_niters = min (LOOP_NITERS, ((VF - addr_mis/elem_size)&(VF-1))/step)
--- 2008,2014 ----
If the misalignment of DR is known at compile time:
addr_mis = int mis = DR_MISALIGNMENT (dr);
Else, compute address misalignment in bytes:
! addr_mis = addr & (vectype_align - 1)
prolog_niters = min (LOOP_NITERS, ((VF - addr_mis/elem_size)&(VF-1))/step)
*************** vect_gen_niters_for_prolog_loop (loop_ve
*** 2065,2073 ****
tree ptr_type = TREE_TYPE (start_addr);
tree size = TYPE_SIZE (ptr_type);
tree type = lang_hooks.types.type_for_size (tree_low_cst (size, 1), 1);
! tree vectype_size_minus_1 = build_int_cst (type, vectype_align - 1);
! tree elem_size_log =
! build_int_cst (type, exact_log2 (vectype_align/nelements));
tree nelements_minus_1 = build_int_cst (type, nelements - 1);
tree nelements_tree = build_int_cst (type, nelements);
tree byte_misalign;
--- 2065,2074 ----
tree ptr_type = TREE_TYPE (start_addr);
tree size = TYPE_SIZE (ptr_type);
tree type = lang_hooks.types.type_for_size (tree_low_cst (size, 1), 1);
! tree vectype_align_minus_1 = build_int_cst (type, vectype_align - 1);
! HOST_WIDE_INT elem_size =
! int_cst_value (TYPE_SIZE_UNIT (TREE_TYPE (vectype)));
! tree elem_size_log = build_int_cst (type, exact_log2 (elem_size));
tree nelements_minus_1 = build_int_cst (type, nelements - 1);
tree nelements_tree = build_int_cst (type, nelements);
tree byte_misalign;
*************** vect_gen_niters_for_prolog_loop (loop_ve
*** 2076,2085 ****
new_bb = gsi_insert_seq_on_edge_immediate (pe, new_stmts);
gcc_assert (!new_bb);
! /* Create: byte_misalign = addr & (vectype_size - 1) */
byte_misalign =
fold_build2 (BIT_AND_EXPR, type, fold_convert (type, start_addr),
! vectype_size_minus_1);
/* Create: elem_misalign = byte_misalign / element_size */
elem_misalign =
--- 2077,2086 ----
new_bb = gsi_insert_seq_on_edge_immediate (pe, new_stmts);
gcc_assert (!new_bb);
! /* Create: byte_misalign = addr & (vectype_align - 1) */
byte_misalign =
fold_build2 (BIT_AND_EXPR, type, fold_convert (type, start_addr),
! vectype_align_minus_1);
/* Create: elem_misalign = byte_misalign / element_size */
elem_misalign =
Index: gcc/testsuite/lib/target-supports.exp
===================================================================
*** gcc/testsuite/lib/target-supports.exp (revision 190202)
--- gcc/testsuite/lib/target-supports.exp (working copy)
*************** proc check_effective_target_natural_alig
*** 2976,2981 ****
--- 2976,3001 ----
return $et_natural_alignment_64_saved
}
+ # Return 1 if all vector types are naturally aligned (aligned to their
+ # type-size), 0 otherwise.
+ #
+ # This won't change for different subtargets so cache the result.
+
+ proc check_effective_target_vect_natural_alignment { } {
+ global et_vect_natural_alignment
+
+ if [info exists et_vect_natural_alignment_saved] {
+ verbose "check_effective_target_vect_natural_alignment: using cached
result" 2
+ } else {
+ set et_vect_natural_alignment_saved 1
+ if { [check_effective_target_arm_eabi] } {
+ set et_vect_natural_alignment_saved 0
+ }
+ }
+ verbose "check_effective_target_vect_natural_alignment: returning
$et_vect_natural_alignment_saved" 2
+ return $et_vect_natural_alignment_saved
+ }
+
# Return 1 if vector alignment (for types of size 32 bit or less) is
reachable, 0 otherwise.
#
# This won't change for different subtargets so cache the result.
Index: gcc/testsuite/gcc.dg/align-2.c
===================================================================
*** gcc/testsuite/gcc.dg/align-2.c (revision 190202)
--- gcc/testsuite/gcc.dg/align-2.c (working copy)
***************
*** 1,5 ****
/* PR 17962 */
! /* { dg-do compile } */
/* { dg-options "" } */
typedef float v4 __attribute__((vector_size(sizeof(float)*4)));
--- 1,5 ----
/* PR 17962 */
! /* { dg-do compile { target vect_natural_alignment } } */
/* { dg-options "" } */
typedef float v4 __attribute__((vector_size(sizeof(float)*4)));
Index: gcc/testsuite/gcc.dg/vect/vect-peel-1.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/vect-peel-1.c (revision 190202)
--- gcc/testsuite/gcc.dg/vect/vect-peel-1.c (working copy)
*************** int main (void)
*** 49,54 ****
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
! /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { target vect_element_align } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
--- 49,54 ----
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
! /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { target { { vect_element_align } && { vect_aligned_arrays } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
Index: gcc/testsuite/gcc.dg/vect/vect-peel-2.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/vect-peel-2.c (revision 190202)
--- gcc/testsuite/gcc.dg/vect/vect-peel-2.c (working copy)
*************** int main (void)
*** 50,55 ****
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
! /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { target vect_element_align } } } */
! /* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { target vect_element_align } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
--- 50,55 ----
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
! /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { target { { vect_element_align } && { vect_aligned_arrays } } } } } */
! /* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { target { { vect_element_align } && { vect_aligned_arrays }
} } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
Index: gcc/testsuite/gcc.dg/vect/vect-peel-3.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/vect-peel-3.c (revision 190202)
--- gcc/testsuite/gcc.dg/vect/vect-peel-3.c (working copy)
***************
*** 4,12 ****
#include "tree-vect.h"
#define N 128
! #define RES 21888
!
! /* unaligned store. */
int ib[N+10];
int ia[N+10];
--- 4,10 ----
#include "tree-vect.h"
#define N 128
! #define RES 21640
int ib[N+10];
int ia[N+10];
*************** int main1 ()
*** 18,28 ****
int i, suma = 0, sumb = 0, sumc = 0;
/* ib and ic have same misalignment, we peel to align them. */
! for (i = 1; i <= N; i++)
{
suma += ia[i];
! sumb += ib[i+6];
! sumc += ic[i+2];
}
/* check results: */
--- 16,26 ----
int i, suma = 0, sumb = 0, sumc = 0;
/* ib and ic have same misalignment, we peel to align them. */
! for (i = 0; i <= N; i++)
{
suma += ia[i];
! sumb += ib[i+5];
! sumc += ic[i+1];
}
/* check results: */
*************** int main (void)
*** 49,55 ****
return main1 ();
}
! /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { xfail vect_no_align } } } */
! /* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
--- 47,53 ----
return main1 ();
}
! /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail
vect_no_align } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { xfail vect_no_align } } } */
! /* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { xfail vect_no_align } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
Index: gcc/testsuite/gcc.dg/vect/vect-peel-4.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/vect-peel-4.c (revision 190202)
--- gcc/testsuite/gcc.dg/vect/vect-peel-4.c (working copy)
*************** int main1 ()
*** 16,28 ****
/* Don't peel keeping one load and the store aligned. */
for (i = 0; i <= N; i++)
{
! ia[i] = ib[i] + ib[i+6];
}
/* check results: */
for (i = 1; i <= N; i++)
{
! if (ia[i] != ib[i] + ib[i+6])
abort ();
}
--- 16,28 ----
/* Don't peel keeping one load and the store aligned. */
for (i = 0; i <= N; i++)
{
! ia[i] = ib[i] + ib[i+5];
}
/* check results: */
for (i = 1; i <= N; i++)
{
! if (ia[i] != ib[i] + ib[i+5])
abort ();
}
*************** int main (void)
*** 44,50 ****
return main1 ();
}
! /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { xfail vect_no_align } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
--- 44,50 ----
return main1 ();
}
! /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail
vect_no_align } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1
"vect" { xfail vect_no_align } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
Index: gcc/testsuite/gcc.dg/vect/slp-25.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/slp-25.c (revision 190202)
--- gcc/testsuite/gcc.dg/vect/slp-25.c (working copy)
*************** int main (void)
*** 57,61 ****
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0
"vect" } } */
! /* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 2 "vect" { xfail { vect_no_align } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
--- 57,61 ----
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0
"vect" } } */
! /* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 2 "vect" { xfail { vect_no_align || { ! vect_natural_alignment } } } }
} */
/* { dg-final { cleanup-tree-dump "vect" } } */
Index: gcc/stor-layout.c
===================================================================
*** gcc/stor-layout.c (revision 190202)
--- gcc/stor-layout.c (working copy)
*************** layout_type (tree type)
*** 1927,1935 ****
TYPE_SIZE (type) = int_const_binop (MULT_EXPR, TYPE_SIZE (innertype),
bitsize_int (nunits), 0);
! /* Always naturally align vectors. This prevents ABI changes
! depending on whether or not native vector modes are supported. */
! TYPE_ALIGN (type) = tree_low_cst (TYPE_SIZE (type), 0);
break;
}
--- 1927,1943 ----
TYPE_SIZE (type) = int_const_binop (MULT_EXPR, TYPE_SIZE (innertype),
bitsize_int (nunits), 0);
! /* For vector types, we do not default to the mode's alignment.
! Instead, query a target hook, defaulting to natural alignment.
! This prevents ABI changes depending on whether or not native
! vector modes are supported. */
! TYPE_ALIGN (type) = targetm.vector_alignment (type);
!
! /* However, if the underlying mode requires a bigger alignment than
! what the target hook provides, we cannot use the mode. For now,
! simply reject that case. */
! gcc_assert (TYPE_ALIGN (type)
! >= GET_MODE_ALIGNMENT (TYPE_MODE (type)));
break;
}
Index: gcc/tree-vect-data-refs.c
===================================================================
*** gcc/tree-vect-data-refs.c (revision 190202)
--- gcc/tree-vect-data-refs.c (working copy)
*************** vect_update_misalignment_for_peel (struc
*** 1019,1025 ****
int misal = DR_MISALIGNMENT (dr);
tree vectype = STMT_VINFO_VECTYPE (stmt_info);
misal += negative ? -npeel * dr_size : npeel * dr_size;
! misal &= GET_MODE_SIZE (TYPE_MODE (vectype)) - 1;
SET_DR_MISALIGNMENT (dr, misal);
return;
}
--- 1019,1025 ----
int misal = DR_MISALIGNMENT (dr);
tree vectype = STMT_VINFO_VECTYPE (stmt_info);
misal += negative ? -npeel * dr_size : npeel * dr_size;
! misal &= (TYPE_ALIGN (vectype) / BITS_PER_UNIT) - 1;
SET_DR_MISALIGNMENT (dr, misal);
return;
}
Index: gcc/config/arm/arm.c
===================================================================
*** gcc/config/arm/arm.c (revision 190202)
--- gcc/config/arm/arm.c (working copy)
*************** static bool xscale_sched_adjust_cost (rt
*** 243,248 ****
--- 243,249 ----
static bool fa726te_sched_adjust_cost (rtx, rtx, rtx, int *);
static enum machine_mode arm_preferred_simd_mode (enum machine_mode);
static bool arm_class_likely_spilled_p (reg_class_t);
+ static HOST_WIDE_INT arm_vector_alignment (const_tree type);
static bool arm_vector_alignment_reachable (const_tree type, bool is_packed);
static bool arm_builtin_support_vector_misalignment (enum machine_mode mode,
const_tree type,
*************** static const struct default_options arm_
*** 579,584 ****
--- 580,588 ----
#undef TARGET_CLASS_LIKELY_SPILLED_P
#define TARGET_CLASS_LIKELY_SPILLED_P arm_class_likely_spilled_p
+ #undef TARGET_VECTOR_ALIGNMENT
+ #define TARGET_VECTOR_ALIGNMENT arm_vector_alignment
+
#undef TARGET_VECTORIZE_VECTOR_ALIGNMENT_REACHABLE
#define TARGET_VECTORIZE_VECTOR_ALIGNMENT_REACHABLE \
arm_vector_alignment_reachable
*************** arm_function_arg (CUMULATIVE_ARGS *pcum,
*** 4693,4698 ****
--- 4697,4714 ----
return gen_rtx_REG (mode, pcum->nregs);
}
+ /* The AAPCS sets the maximum alignment of a vector to 64 bits. */
+ static HOST_WIDE_INT
+ arm_vector_alignment (const_tree type)
+ {
+ HOST_WIDE_INT align = tree_low_cst (TYPE_SIZE (type), 0);
+
+ if (TARGET_AAPCS_BASED)
+ align = MIN (align, 64);
+
+ return align;
+ }
+
static unsigned int
arm_function_arg_boundary (enum machine_mode mode, const_tree type)
{
--
Dr. Ulrich Weigand
GNU Toolchain for Linux on System z and Cell BE
[email protected]
