On Wed, 24 Jun 2026, [email protected] wrote:
> From: Reshma Roy <[email protected]>
>
> Transform uniform gather operations into optimized scalar load + broadcast
> instead of emulated gather with N individual scalar loads.
>
> BEFORE (Emulated Gather - 8 loads for VF=8):
> for each lane i in 0..7:
> offset[i] = BIT_FIELD_REF<offset_vector, i>
> addr[i] = base + offset[i] * scale
> result[i] = MEM[addr[i]]
> result_vector = {result[0], ..., result[7]}
>
> AFTER (Broadcast - 1 load):
> offset = BIT_FIELD_REF<offset_vector, 0>
> addr = base + offset * scale
> scalar_val = MEM[addr]
> result_vector = VEC_DUPLICATE_EXPR(scalar_val)
>
> v2 changes:
> - Keep the full loop (k = 0 ??? const_nunits-1) but only
> perform the scalar load once and reuse elt for all lanes
> - Since VEC_DUPLICATE_EXPR is for VLA/scalable vector types only
> removed that and added constructor
> - Removed the SSA copy by refactoring the code
>
> gcc/ChangeLog:
>
> * tree-vect-stmts.cc (vectorizable_load): Generate broadcast for
> uniform gather offsets.
>
> gcc/testsuite/ChangeLog:
>
> * g++.dg/vect/vect-uniform-broadcast-neg.c: New test.
> * g++.dg/vect/vect-uniform-broadcast-op2-var.c: New test.
> * g++.dg/vect/vect-uniform-broadcast.c: New test.
>
> ---
>
> Hi Richard,
>
> The comments were addressed and the updated patch is attached.
>
> Thanks,
> Reshma Roy
>
> Original Message-----
> > From: Richard Biener <[email protected]>
> > Sent: Tuesday, June 9, 2026 7:31 PM
> > To: Roy, Reshma <[email protected]>
> > Cc: [email protected]; Kumar, Venkataramanan
> > <[email protected]>
> > Subject: Re: [PATCH 2/2] Loop Vectorizer: Generate broadcast for uniform
> > gather
> > offsets
> >
> > Caution: This message originated from an External Source. Use proper caution
> > when opening attachments, clicking links, or responding.
> >
> >
> > On Mon, 25 May 2026, [email protected] wrote:
> >
> > > From: Reshma Roy <[email protected]>
> > >
> > > Transform uniform gather operations into optimized scalar load +
> > > broadcast instead of emulated gather with N individual scalar loads.
> > >
> > > BEFORE (Emulated Gather - 8 loads for VF=8):
> > > for each lane i in 0..7:
> > > offset[i] = BIT_FIELD_REF<offset_vector, i>
> > > addr[i] = base + offset[i] * scale
> > > result[i] = MEM[addr[i]]
> > > result_vector = {result[0], ..., result[7]}
> > >
> > > AFTER (Broadcast - 1 load):
> > > offset = BIT_FIELD_REF<offset_vector, 0>
> > > addr = base + offset * scale
> > > scalar_val = MEM[addr]
> > > result_vector = VEC_DUPLICATE_EXPR(scalar_val)
> > >
> > > gcc/ChangeLog:
> > >
> > > * tree-vect-stmts.cc (vectorizable_load): Generate broadcast for
> > > uniform gather offsets.
> > >
> > > gcc/testsuite/ChangeLog:
> > > * g++.dg/vect/vect-uniform-broadcast-neg.c: New test.
> > > * g++.dg/vect/vect-uniform-broadcast-op2-var.c: New test.
> > > * g++.dg/vect/vect-uniform-broadcast.c: New test.
> > >
> > > ---
> > > .../g++.dg/vect/vect-uniform-broadcast-neg.c | 29 +++++++++
> > > .../vect/vect-uniform-broadcast-op2-var.c | 38 ++++++++++++
> > > .../g++.dg/vect/vect-uniform-broadcast.c | 29 +++++++++
> > > gcc/tree-vect-stmts.cc | 59 ++++++++++++++++---
> > > 4 files changed, 148 insertions(+), 7 deletions(-) create mode
> > > 100644 gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> > > create mode 100644
> > > gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> > > create mode 100644 gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> > >
> > > diff --git a/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> > > b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> > > new file mode 100644
> > > index 00000000000..590706d3b51
> > > --- /dev/null
> > > +++ b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> > > @@ -0,0 +1,29 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-additional-options "-O3 -std=c++11 -march=znver5
> > > +-fdump-tree-vect-details" } */
> > > +/* Negative test: loop i starts at 1 -> SCEV {1, +, 1}. POC only handles
> > > + {0, +, 1}, so offset is not treated as uniform -> no broadcast
> > > + (vec_duplicate_expr must not appear for this gather). */ #include
> > > +<bitset> #include <vector> class Foo {
> > > + public:
> > > + void fun (unsigned boardsize, bool check);
> > > + std::vector<int> m_mcowner;
> > > +};
> > > +void Foo::fun (unsigned boardsize, bool check) {
> > > + std::bitset<21*21> blacksq;
> > > + __asm__ ("" : "+g" (blacksq));
> > > + for (int i = 0; i < boardsize; i++) {
> > > + if (i % 2 == 0)
> > > + blacksq[i] = true;
> > > + }
> > > + unsigned int i = 1;
> > > + do {
> > > + if (blacksq[i])
> > > + m_mcowner[i]++;
> > > + } while (++i < blacksq.size ());
> > > +}
> > > +/* { dg-final { scan-tree-dump-not "\.vec_duplicate_expr" "vect" } }
> > > +*/
> > > +
> > > diff --git
> > > a/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> > > b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> > > new file mode 100644
> > > index 00000000000..b212b3d56be
> > > --- /dev/null
> > > +++ b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> > > @@ -0,0 +1,38 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-additional-options "-O3 -std=c++11 -march=znver5
> > > +-fdump-tree-vect-details" } */
> > > +/* Gather load with PLUS (hi, lo). The second operand of the offset PLUS
> > > is a
> > > + variable, hence does not emit vec_duplicate_expr. The inner loop still
> > > + vectorizes as a normal gather */
> > > +
> > > +#include <vector>
> > > +
> > > +class Foo
> > > +{
> > > + public:
> > > + void fun (unsigned boardsize);
> > > + std::vector<int> m_mcowner;
> > > +};
> > > +
> > > +void
> > > +Foo::fun (unsigned boardsize)
> > > +{
> > > + unsigned nwords = (21 * 21 + 63) / 64 + 2;
> > > + std::vector<unsigned long> words (nwords, 0);
> > > + __asm__ ("" : "+g" (words));
> > > + for (unsigned i = 0; i < boardsize; i++)
> > > + if (i % 2 == 0)
> > > + words[i / 64] |= 1UL << (i % 64);
> > > + unsigned int i = 0;
> > > + do
> > > + {
> > > + unsigned hi = i / 64;
> > > + unsigned lo = i & 1u;
> > > + /* the second operand is ensured to be loop-varying by the SCEV
> > > path */
> > > + if (words[hi + lo])
> > > + m_mcowner[i]++;
> > > + }
> > > + while (++i < 21 * 21);
> > > +}
> > > +
> > > +/* { dg-final { scan-tree-dump-not "\.vec_duplicate_expr" "vect" } }
> > > +*/
> > > +/* { dg-final { scan-tree-dump "gs_offset_uniform_p is set to: 0"
> > > +"vect" } } */
> > > diff --git a/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> > > b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> > > new file mode 100644
> > > index 00000000000..818b7a63c00
> > > --- /dev/null
> > > +++ b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> > > @@ -0,0 +1,29 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-additional-options "-O3 -std=c++11 -march=znver5
> > > +-fdump-tree-vect-details" } */
> > > +/* Test case for generating uniform broadcast instead of gather
> > > + when there is uniform value accross the vector lane */ #include
> > > +<bitset> #include <vector> class Foo {
> > > + public:
> > > + void fun (unsigned boardsize, bool check);
> > > + std::vector<int> m_mcowner;
> > > +};
> > > +void Foo::fun( unsigned boardsize, bool check) {
> > > + std::bitset<21*21> blacksq;
> > > + __asm__ ("" : "+g" (blacksq));
> > > + for (int i = 0; i < boardsize; i++) {
> > > + if(i%2 == 0)
> > > + blacksq[i] = true;
> > > + }
> > > + unsigned int i = 0;
> > > + do{
> > > + if (blacksq[i])
> > > + m_mcowner[i]++;
> > > + }while(++i < blacksq.size());
> > > +
> > > +}
> > > +/* { dg-final { scan-tree-dump "\.vec_duplicate_expr" "vect" } } */
> > > +
> > > diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index
> > > b68fc5072af..71ff138c069 100644
> > > --- a/gcc/tree-vect-stmts.cc
> > > +++ b/gcc/tree-vect-stmts.cc
> > > @@ -11198,6 +11198,25 @@ vectorizable_load (vec_info *vinfo,
> > > unsigned HOST_WIDE_INT const_nunits = nunits.to_constant ();
> > > if (costing_p)
> > > {
> > > + if (slp_node->gs_offset_uniform_p)
> > > + {
> > > + if (dump_enabled_p ())
> > > + dump_printf_loc (MSG_NOTE, vect_location,
> > > + "computing cost for broadcast \n");
> > > + /* Broadcast optimization: 1 extract + 1 load
> > > + + 1 broadcast. */
> > > + inside_cost = record_stmt_cost (cost_vec, 1,
> > > + vec_to_scalar,
> > > slp_node,
> > > + 0, vect_body);
> > > + inside_cost += record_stmt_cost (cost_vec, 1,
> > > scalar_load,
> > > + slp_node, 0,
> > > vect_body);
> > > + inside_cost += record_stmt_cost (cost_vec, 1,
> > > + scalar_to_vec,
> > > slp_node,
> > > + 0, vect_body);
> > > + }
> > > + else
> > > + {
> > > +
> > > /* For emulated gathers N offset vector element
> > > offset add is consumed by the load). */
> > > inside_cost = record_stmt_cost (cost_vec,
> > > const_nunits, @@ -11211,6 +11230,7 @@ vectorizable_load (vec_info *vinfo,
> > > inside_cost
> > > = record_stmt_cost (cost_vec, 1, vec_construct,
> > > slp_node, 0, vect_body);
> > > + }
> > > continue;
> > > }
> > > tree offset_vectype = TREE_TYPE (vec_offsets[0]); @@
> > > -11228,7 +11248,12 @@ vectorizable_load (vec_info *vinfo,
> > > tree idx_type = TREE_TYPE (TREE_TYPE (vec_offset));
> > > tree scale = size_int (SLP_TREE_GS_SCALE (slp_node));
> > > tree ltype = build_aligned_type (TREE_TYPE (vectype), align);
> > > - for (unsigned k = 0; k < const_nunits; ++k)
> > > + tree broadcast_vec = NULL_TREE;
> > > + /* If all lanes are uniform then generate broadcast otherwise
> > > + emulated gathers. */
> > > + unsigned HOST_WIDE_INT vec_lane_loads
> > > + = slp_node->gs_offset_uniform_p ? 1 : const_nunits;
> >
> > instead of this
> >
> > > + for (unsigned k = 0; k < vec_lane_loads; ++k)
> > > {
> > > tree boff = size_binop (MULT_EXPR, TYPE_SIZE (idx_type),
> > > bitsize_int (k + elt_offset));
> > > @@ -11247,13 +11272,33 @@ vectorizable_load (vec_info *vinfo,
> > > new_stmt = gimple_build_assign (elt, ref);
> > > gimple_set_vuse (new_stmt, gimple_vuse (gsi_stmt (*gsi)));
> > > gimple_seq_add_stmt (&stmts, new_stmt);
> > > - CONSTRUCTOR_APPEND_ELT (ctor_elts, NULL_TREE, elt);
> > > + if (!slp_node->gs_offset_uniform_p)
> > > + CONSTRUCTOR_APPEND_ELT (ctor_elts, NULL_TREE, elt);
> > > + else
> > > + /* Broadcast to all lanes. */
> > > + broadcast_vec = gimple_build (&stmts,
> > > + VEC_DUPLICATE_EXPR,
> > > + vectype, elt);
> >
> > break from the loop here. Also use gimple_build_vector_from_val, a
> > VEC_DUPLICATE_EXPR is only valid for VLA vectors, a broadcast for non-VLA
> > vectors should use a uniform CONSTRUCTOR.
> Done.
> >
> > > + }
> > > + if (!slp_node->gs_offset_uniform_p)
> > > + {
> > > + gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
> > > + new_stmt = gimple_build_assign (NULL_TREE,
> > > + build_constructor
> > > (vectype,
> > > +
> > > ctor_elts)
> > > + );
> > > + data_ref = NULL_TREE;
> > > + }
> > > + else
> > > + {
> > > + gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
> > > + new_stmt = gimple_build_assign (NULL_TREE,
> > > + broadcast_vec);
> >
> > you get a SSA copy from this, some refactoring should avoid that. Or
> > simply build
> > that uniform vector above by keeping the loop but only load 'elt' once (but
> > add it
> > nunits time).
> Refactored the code such that SSA copy is removed.
> >
> > > + data_ref = NULL_TREE;
> > > + if (dump_enabled_p ())
> > > + dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, vect_location,
> > > + "generating broadcast instead of
> > > gather "
> > > + "loads (uniform offset lanes)\n");
> > > }
> > > - gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
> > > - new_stmt = gimple_build_assign (NULL_TREE,
> > > - build_constructor (vectype,
> > > -
> > > ctor_elts));
> > > - data_ref = NULL_TREE;
> > > }
> > >
> > > vec_dest = vect_create_destination_var (scalar_dest, vectype);
> > >
> >
> > --
> > Richard Biener <[email protected]>
> > SUSE Software Solutions Germany GmbH,
> > Frankenstrasse 146, 90461 Nuernberg, Germany;
> > GF: Jochen Jaser, Andrew McDonald, Werner Knoblich; (HRB 36809, AG
> > Nuernberg)
>
>
> .../g++.dg/vect/vect-uniform-broadcast-neg.c | 29 ++++++++
> .../vect/vect-uniform-broadcast-op2-var.c | 38 ++++++++++
> .../g++.dg/vect/vect-uniform-broadcast.c | 29 ++++++++
> gcc/tree-vect-stmts.cc | 71 ++++++++++++++-----
> 4 files changed, 149 insertions(+), 18 deletions(-)
> create mode 100644 gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> create mode 100644 gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> create mode 100644 gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
>
> diff --git a/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> new file mode 100644
> index 00000000000..590706d3b51
> --- /dev/null
> +++ b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-neg.c
> @@ -0,0 +1,29 @@
> +/* { dg-do compile } */
> +/* { dg-additional-options "-O3 -std=c++11 -march=znver5
> -fdump-tree-vect-details" } */
> +/* Negative test: loop i starts at 1 -> SCEV {1, +, 1}. POC only handles
> + {0, +, 1}, so offset is not treated as uniform -> no broadcast
> + (vec_duplicate_expr must not appear for this gather). */
> +#include <bitset>
> +#include <vector>
> +class Foo
> +{
> + public:
> + void fun (unsigned boardsize, bool check);
> + std::vector<int> m_mcowner;
> +};
> +void Foo::fun (unsigned boardsize, bool check)
> +{
> + std::bitset<21*21> blacksq;
> + __asm__ ("" : "+g" (blacksq));
> + for (int i = 0; i < boardsize; i++) {
> + if (i % 2 == 0)
> + blacksq[i] = true;
> + }
> + unsigned int i = 1;
> + do {
> + if (blacksq[i])
> + m_mcowner[i]++;
> + } while (++i < blacksq.size ());
> +}
> +/* { dg-final { scan-tree-dump-not "\.vec_duplicate_expr" "vect" } } */
> +
> diff --git a/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> new file mode 100644
> index 00000000000..b212b3d56be
> --- /dev/null
> +++ b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast-op2-var.c
> @@ -0,0 +1,38 @@
> +/* { dg-do compile } */
> +/* { dg-additional-options "-O3 -std=c++11 -march=znver5
> -fdump-tree-vect-details" } */
> +/* Gather load with PLUS (hi, lo). The second operand of the offset PLUS is
> a
> + variable, hence does not emit vec_duplicate_expr. The inner loop still
> + vectorizes as a normal gather */
> +
> +#include <vector>
> +
> +class Foo
> +{
> + public:
> + void fun (unsigned boardsize);
> + std::vector<int> m_mcowner;
> +};
> +
> +void
> +Foo::fun (unsigned boardsize)
> +{
> + unsigned nwords = (21 * 21 + 63) / 64 + 2;
> + std::vector<unsigned long> words (nwords, 0);
> + __asm__ ("" : "+g" (words));
> + for (unsigned i = 0; i < boardsize; i++)
> + if (i % 2 == 0)
> + words[i / 64] |= 1UL << (i % 64);
> + unsigned int i = 0;
> + do
> + {
> + unsigned hi = i / 64;
> + unsigned lo = i & 1u;
> + /* the second operand is ensured to be loop-varying by the SCEV path */
> + if (words[hi + lo])
> + m_mcowner[i]++;
> + }
> + while (++i < 21 * 21);
> +}
> +
> +/* { dg-final { scan-tree-dump-not "\.vec_duplicate_expr" "vect" } } */
> +/* { dg-final { scan-tree-dump "gs_offset_uniform_p is set to: 0" "vect" } }
> */
> diff --git a/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> new file mode 100644
> index 00000000000..818b7a63c00
> --- /dev/null
> +++ b/gcc/testsuite/g++.dg/vect/vect-uniform-broadcast.c
> @@ -0,0 +1,29 @@
> +/* { dg-do compile } */
> +/* { dg-additional-options "-O3 -std=c++11 -march=znver5
> -fdump-tree-vect-details" } */
> +/* Test case for generating uniform broadcast instead of gather
> + when there is uniform value accross the vector lane */
> +#include <bitset>
> +#include <vector>
> +class Foo
> +{
> + public:
> + void fun (unsigned boardsize, bool check);
> + std::vector<int> m_mcowner;
> +};
> +void Foo::fun( unsigned boardsize, bool check)
> +{
> + std::bitset<21*21> blacksq;
> + __asm__ ("" : "+g" (blacksq));
> + for (int i = 0; i < boardsize; i++) {
> + if(i%2 == 0)
> + blacksq[i] = true;
> + }
> + unsigned int i = 0;
> + do{
> + if (blacksq[i])
> + m_mcowner[i]++;
> + }while(++i < blacksq.size());
> +
> +}
> +/* { dg-final { scan-tree-dump "\.vec_duplicate_expr" "vect" } } */
> +
> diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
> index afd5109c9f7..44282f20873 100644
> --- a/gcc/tree-vect-stmts.cc
> +++ b/gcc/tree-vect-stmts.cc
> @@ -11207,6 +11207,25 @@ vectorizable_load (vec_info *vinfo,
> unsigned HOST_WIDE_INT const_nunits = nunits.to_constant ();
> if (costing_p)
> {
> + if (slp_node->gs_offset_uniform_p)
> + {
> + if (dump_enabled_p ())
> + dump_printf_loc (MSG_NOTE, vect_location,
> + "computing cost for broadcast \n");
> + /* Broadcast optimization: 1 extract + 1 load
> + + 1 broadcast. */
> + inside_cost = record_stmt_cost (cost_vec, 1,
> + vec_to_scalar, slp_node,
> + 0, vect_body);
> + inside_cost += record_stmt_cost (cost_vec, 1, scalar_load,
> + slp_node, 0, vect_body);
> + inside_cost += record_stmt_cost (cost_vec, 1,
> + scalar_to_vec, slp_node,
> + 0, vect_body);
> + }
> + else
> + {
> +
> /* For emulated gathers N offset vector element
> offset add is consumed by the load). */
this block now needs re-indenting.
> inside_cost = record_stmt_cost (cost_vec, 1, vec_deconstruct,
> @@ -11219,6 +11238,7 @@ vectorizable_load (vec_info *vinfo,
> inside_cost
> = record_stmt_cost (cost_vec, 1, vec_construct,
> slp_node, 0, vect_body);
> + }
> continue;
> }
> tree offset_vectype = TREE_TYPE (vec_offsets[0]);
> @@ -11236,25 +11256,37 @@ vectorizable_load (vec_info *vinfo,
> tree idx_type = TREE_TYPE (TREE_TYPE (vec_offset));
> tree scale = size_int (SLP_TREE_GS_SCALE (slp_node));
> tree ltype = build_aligned_type (TREE_TYPE (vectype), align);
> + tree first_elt = NULL_TREE;
> for (unsigned k = 0; k < const_nunits; ++k)
> {
> - tree boff = size_binop (MULT_EXPR, TYPE_SIZE (idx_type),
> - bitsize_int (k + elt_offset));
> - tree idx = gimple_build (&stmts, BIT_FIELD_REF, idx_type,
> - vec_offset, TYPE_SIZE (idx_type),
> - boff);
> - idx = gimple_convert (&stmts, sizetype, idx);
> - idx = gimple_build (&stmts, MULT_EXPR, sizetype, idx, scale);
> - tree ptr = gimple_build (&stmts, PLUS_EXPR,
> - TREE_TYPE (dataref_ptr),
> - dataref_ptr, idx);
> - ptr = gimple_convert (&stmts, ptr_type_node, ptr);
> - tree elt = make_ssa_name (TREE_TYPE (vectype));
> - tree ref = build2 (MEM_REF, ltype, ptr,
> - build_int_cst (ref_type, 0));
> - new_stmt = gimple_build_assign (elt, ref);
> - gimple_set_vuse (new_stmt, gimple_vuse (gsi_stmt (*gsi)));
> - gimple_seq_add_stmt (&stmts, new_stmt);
> + tree elt;
> + /* If all lanes are uniform then generate broadcast otherwise
> + emulated gathers. */
> + if (slp_node->gs_offset_uniform_p && k>0)
k > 0
> + elt = first_elt;
> + else
> + {
> +
> + tree boff = size_binop (MULT_EXPR, TYPE_SIZE (idx_type),
> + bitsize_int (k + elt_offset));
> + tree idx = gimple_build (&stmts, BIT_FIELD_REF, idx_type,
> + vec_offset, TYPE_SIZE (idx_type),
> + boff);
> + idx = gimple_convert (&stmts, sizetype, idx);
> + idx = gimple_build (&stmts, MULT_EXPR, sizetype, idx,
> + scale);
> + tree ptr = gimple_build (&stmts, PLUS_EXPR,
> + TREE_TYPE (dataref_ptr),
> + dataref_ptr, idx);
> + ptr = gimple_convert (&stmts, ptr_type_node, ptr);
> + elt = make_ssa_name (TREE_TYPE (vectype));
> + tree ref = build2 (MEM_REF, ltype, ptr,
> + build_int_cst (ref_type, 0));
> + new_stmt = gimple_build_assign (elt, ref);
> + gimple_set_vuse (new_stmt, gimple_vuse (gsi_stmt (*gsi)));
> + gimple_seq_add_stmt (&stmts, new_stmt);
> + first_elt = elt;
> + }
> CONSTRUCTOR_APPEND_ELT (ctor_elts, NULL_TREE, elt);
> }
> gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
> @@ -11262,8 +11294,11 @@ vectorizable_load (vec_info *vinfo,
> build_constructor (vectype,
> ctor_elts));
> data_ref = NULL_TREE;
> + if (slp_node->gs_offset_uniform_p && dump_enabled_p ())
> + dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, vect_location,
> + "generating broadcast instead of gather "
> + "loads (uniform offset lanes)\n");
The extra dump prints are a bit out-of-place, we probably want to
dump (in general) the gather/scatter kind that's being used, but
during analysis and for all cases. We might already do, if we do
you want to ament that.
> }
> -
please avoid spurious whitespace changes
> vec_dest = vect_create_destination_var (scalar_dest, vectype);
> /* DATA_REF is null if we've already built the statement. */
> if (data_ref)
>
--
Richard Biener <[email protected]>
SUSE Software Solutions Germany GmbH,
Frankenstrasse 146, 90461 Nuernberg, Germany;
GF: Jochen Jaser, Andrew McDonald, Werner Knoblich; (HRB 36809, AG Nuernberg)
