From: Cesar Philippidis <ce...@codesourcery.com>
Eventually, we want the nvptx BE to use a common shared memory buffer
for both worker and vector state propagation (albeit using different
partitions of shared memory for each logical thread). This patch
renames the worker_bcast variables into a more generic oacc_bcast.
2018-XX-YY Cesar Philippidis <ce...@codesourcery.com>
gcc/
* config/nvptx/nvptx.c (worker_bcast_size): Rename as
oacc_bcast_size.
(worker_bcast_align): Rename as oacc_bcast_align.
(worker_bcast_sym): Rename as oacc_bcast_sym.
(nvptx_option_override): Update usage of oacc_bcast_*.
(struct wcast_data_t): Rename as broadcast_data_t.
(nvptx_gen_wcast): Update type of data argument and usage of
oacc_bcast_align.
(wprop_gen): Update type of data_ and usage of oacc_bcast_align.
(nvptx_wpropagate): Update type of data and usage of
oacc_bcast_{sym,size}.
(nvptx_single): Update type of data and usage of oacc_bcast_size.
(nvptx_file_end): Update usage of oacc_bcast_{sym,align,size}.
diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 521f83e..fb3e0c7 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -129,14 +129,15 @@ struct tree_hasher : ggc_cache_ptr_hash<tree_node>
static GTY((cache)) hash_table<tree_hasher> *declared_fndecls_htab;
static GTY((cache)) hash_table<tree_hasher> *needed_fndecls_htab;
-/* Buffer needed to broadcast across workers. This is used for both
- worker-neutering and worker broadcasting. It is shared by all
- functions emitted. The buffer is placed in shared memory. It'd be
- nice if PTX supported common blocks, because then this could be
- shared across TUs (taking the largest size). */
-static unsigned worker_bcast_size;
-static unsigned worker_bcast_align;
-static GTY(()) rtx worker_bcast_sym;
+/* Buffer needed to broadcast across workers and vectors. This is
+ used for both worker-neutering and worker broadcasting, and
+ vector-neutering and boardcasting when vector_length > 32. It is
+ shared by all functions emitted. The buffer is placed in shared
+ memory. It'd be nice if PTX supported common blocks, because then
+ this could be shared across TUs (taking the largest size). */
+static unsigned oacc_bcast_size;
+static unsigned oacc_bcast_align;
+static GTY(()) rtx oacc_bcast_sym;
/* Buffer needed for worker reductions. This has to be distinct from
the worker broadcast array, as both may be live concurrently. */
@@ -209,9 +210,9 @@ nvptx_option_override (void)
declared_libfuncs_htab
= hash_table<declared_libfunc_hasher>::create_ggc (17);
- worker_bcast_sym = gen_rtx_SYMBOL_REF (Pmode, "__worker_bcast");
- SET_SYMBOL_DATA_AREA (worker_bcast_sym, DATA_AREA_SHARED);
- worker_bcast_align = GET_MODE_ALIGNMENT (SImode) / BITS_PER_UNIT;
+ oacc_bcast_sym = gen_rtx_SYMBOL_REF (Pmode, "__oacc_bcast");
+ SET_SYMBOL_DATA_AREA (oacc_bcast_sym, DATA_AREA_SHARED);
+ oacc_bcast_align = GET_MODE_ALIGNMENT (SImode) / BITS_PER_UNIT;
worker_red_sym = gen_rtx_SYMBOL_REF (Pmode, "__worker_red");
SET_SYMBOL_DATA_AREA (worker_red_sym, DATA_AREA_SHARED);
@@ -1756,7 +1757,7 @@ nvptx_gen_vcast (rtx reg)
/* Structure used when generating a worker-level spill or fill. */
-struct wcast_data_t
+struct broadcast_data_t
{
rtx base; /* Register holding base addr of buffer. */
rtx ptr; /* Iteration var, if needed. */
@@ -1780,7 +1781,7 @@ enum propagate_mask
how many loop iterations will be executed (0 for not a loop). */
static rtx
-nvptx_gen_wcast (rtx reg, propagate_mask pm, unsigned rep, wcast_data_t *data)
+nvptx_gen_wcast (rtx reg, propagate_mask pm, unsigned rep, broadcast_data_t
*data)
{
rtx res;
machine_mode mode = GET_MODE (reg);
@@ -1810,8 +1811,8 @@ nvptx_gen_wcast (rtx reg, propagate_mask pm, unsigned
rep, wcast_data_t *data)
{
unsigned align = GET_MODE_ALIGNMENT (mode) / BITS_PER_UNIT;
- if (align > worker_bcast_align)
- worker_bcast_align = align;
+ if (align > oacc_bcast_align)
+ oacc_bcast_align = align;
data->offset = (data->offset + align - 1) & ~(align - 1);
addr = data->base;
if (data->offset)
@@ -3916,15 +3917,15 @@ nvptx_vpropagate (bool is_call, basic_block block,
rtx_insn *insn)
static rtx
wprop_gen (rtx reg, propagate_mask pm, unsigned rep, void *data_)
{
- wcast_data_t *data = (wcast_data_t *)data_;
+ broadcast_data_t *data = (broadcast_data_t *)data_;
if (pm & PM_loop_begin)
{
/* Starting a loop, initialize pointer. */
unsigned align = GET_MODE_ALIGNMENT (GET_MODE (reg)) / BITS_PER_UNIT;
- if (align > worker_bcast_align)
- worker_bcast_align = align;
+ if (align > oacc_bcast_align)
+ oacc_bcast_align = align;
data->offset = (data->offset + align - 1) & ~(align - 1);
data->ptr = gen_reg_rtx (Pmode);
@@ -3949,7 +3950,7 @@ wprop_gen (rtx reg, propagate_mask pm, unsigned rep, void
*data_)
static bool
nvptx_wpropagate (bool pre_p, bool is_call, basic_block block, rtx_insn *insn)
{
- wcast_data_t data;
+ broadcast_data_t data;
data.base = gen_reg_rtx (Pmode);
data.offset = 0;
@@ -3961,11 +3962,11 @@ nvptx_wpropagate (bool pre_p, bool is_call, basic_block
block, rtx_insn *insn)
if (data.offset)
{
/* Stuff was emitted, initialize the base pointer now. */
- rtx init = gen_rtx_SET (data.base, worker_bcast_sym);
+ rtx init = gen_rtx_SET (data.base, oacc_bcast_sym);
emit_insn_after (init, insn);
- if (worker_bcast_size < data.offset)
- worker_bcast_size = data.offset;
+ if (oacc_bcast_size < data.offset)
+ oacc_bcast_size = data.offset;
}
return empty;
}
@@ -4335,13 +4336,13 @@ nvptx_single (unsigned mask, basic_block from,
basic_block to)
{
/* Includes worker mode, do spill & fill. By construction
we should never have worker mode only. */
- wcast_data_t data;
+ broadcast_data_t data;
- data.base = worker_bcast_sym;
+ data.base = oacc_bcast_sym;
data.ptr = 0;
- if (worker_bcast_size < GET_MODE_SIZE (SImode))
- worker_bcast_size = GET_MODE_SIZE (SImode);
+ if (oacc_bcast_size < GET_MODE_SIZE (SImode))
+ oacc_bcast_size = GET_MODE_SIZE (SImode);
data.offset = 0;
emit_insn_before (nvptx_gen_wcast (pvar, PM_read, 0, &data),
@@ -4967,9 +4968,9 @@ nvptx_file_end (void)
nvptx_record_fndecl (decl);
fputs (func_decls.str().c_str(), asm_out_file);
- if (worker_bcast_size)
- write_worker_buffer (asm_out_file, worker_bcast_sym,
- worker_bcast_align, worker_bcast_size);
+ if (oacc_bcast_size)
+ write_worker_buffer (asm_out_file, oacc_bcast_sym,
+ oacc_bcast_align, oacc_bcast_size);
if (worker_red_size)
write_worker_buffer (asm_out_file, worker_red_sym,
--
2.7.4
