[PATCH] Fix vector rsqrt discovery (PR tree-optimization/68501)
Richard Biener
rguenther@suse.de
Sat Nov 28 07:50:00 GMT 2015
On November 27, 2015 8:40:56 PM GMT+01:00, Jakub Jelinek <jakub@redhat.com> wrote:
>Hi!
>
>The recent changes where vector sqrt is represented in the IL using
>IFN_SQRT instead of target specific builtins broke the discovery
>of vector rsqrt, as targetm.builtin_reciprocal is called only
>on builtin functions (not internal functions). Furthermore,
>for internal fns, not only the IFN_* is significant, but also the
>types (modes actually) of the lhs and/or arguments.
>
>This patch adjusts the target hook, so that the backends can just
>inspect
>the call (builtin or internal function), whatever it is.
>
>Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
OK. Though the other option would be to add an optab with corresponding IFN.
Richard.
>2015-11-27 Jakub Jelinek <jakub@redhat.com>
>
> PR tree-optimization/68501
> * target.def (builtin_reciprocal): Replace the 3 arguments with
> a gcall * one, adjust description.
> * targhooks.h (default_builtin_reciprocal): Replace the 3 arguments
> with a gcall * one.
> * targhooks.c (default_builtin_reciprocal): Likewise.
> * tree-ssa-math-opts.c (pass_cse_reciprocals::execute): Use
> targetm.builtin_reciprocal even on internal functions, adjust
> the arguments and allow replacing an internal function with normal
> built-in.
> * config/i386/i386.c (ix86_builtin_reciprocal): Replace the 3
>arguments
> with a gcall * one. Handle internal fns too.
> * config/rs6000/rs6000.c (rs6000_builtin_reciprocal): Likewise.
> * config/aarch64/aarch64.c (aarch64_builtin_reciprocal): Likewise.
> * doc/tm.texi (builtin_reciprocal): Document.
>
>--- gcc/target.def.jj 2015-11-18 11:19:19.000000000 +0100
>+++ gcc/target.def 2015-11-27 16:37:07.870823670 +0100
>@@ -2463,13 +2463,9 @@ identical versions.",
> DEFHOOK
> (builtin_reciprocal,
>"This hook should return the DECL of a function that implements
>reciprocal of\n\
>-the builtin function with builtin function code @var{fn}, or\n\
>-@code{NULL_TREE} if such a function is not available. @var{md_fn} is
>true\n\
>-when @var{fn} is a code of a machine-dependent builtin function.
>When\n\
>-@var{sqrt} is true, additional optimizations that apply only to the
>reciprocal\n\
>-of a square root function are performed, and only reciprocals of
>@code{sqrt}\n\
>-function are valid.",
>- tree, (unsigned fn, bool md_fn, bool sqrt),
>+the builtin or internal function call @var{call}, or\n\
>+@code{NULL_TREE} if such a function is not available.",
>+ tree, (gcall *call),
> default_builtin_reciprocal)
>
>/* For a vendor-specific TYPE, return a pointer to a
>statically-allocated
>--- gcc/targhooks.h.jj 2015-11-18 11:19:17.000000000 +0100
>+++ gcc/targhooks.h 2015-11-27 16:37:44.828301093 +0100
>@@ -90,7 +90,7 @@ extern tree default_builtin_vectorized_c
>
>extern int default_builtin_vectorization_cost (enum vect_cost_for_stmt,
>tree, int);
>
>-extern tree default_builtin_reciprocal (unsigned int, bool, bool);
>+extern tree default_builtin_reciprocal (gcall *);
>
> extern HOST_WIDE_INT default_vector_alignment (const_tree);
>
>--- gcc/targhooks.c.jj 2015-11-18 11:19:17.000000000 +0100
>+++ gcc/targhooks.c 2015-11-27 16:38:21.461783097 +0100
>@@ -600,9 +600,7 @@ default_builtin_vectorization_cost (enum
> /* Reciprocal. */
>
> tree
>-default_builtin_reciprocal (unsigned int fn ATTRIBUTE_UNUSED,
>- bool md_fn ATTRIBUTE_UNUSED,
>- bool sqrt ATTRIBUTE_UNUSED)
>+default_builtin_reciprocal (gcall *)
> {
> return NULL_TREE;
> }
>--- gcc/tree-ssa-math-opts.c.jj 2015-11-25 09:57:47.000000000 +0100
>+++ gcc/tree-ssa-math-opts.c 2015-11-27 17:07:22.756162308 +0100
>@@ -601,19 +601,17 @@ pass_cse_reciprocals::execute (function
>
> if (is_gimple_call (stmt1)
> && gimple_call_lhs (stmt1)
>- && (fndecl = gimple_call_fndecl (stmt1))
>- && (DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_NORMAL
>- || DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD))
>+ && (gimple_call_internal_p (stmt1)
>+ || ((fndecl = gimple_call_fndecl (stmt1))
>+ && (DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_NORMAL
>+ || (DECL_BUILT_IN_CLASS (fndecl)
>+ == BUILT_IN_MD)))))
> {
>- enum built_in_function code;
>- bool md_code, fail;
>+ bool fail;
> imm_use_iterator ui;
> use_operand_p use_p;
>
>- code = DECL_FUNCTION_CODE (fndecl);
>- md_code = DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD;
>-
>- fndecl = targetm.builtin_reciprocal (code, md_code, false);
>+ fndecl = targetm.builtin_reciprocal (as_a <gcall *> (stmt1));
> if (!fndecl)
> continue;
>
>@@ -639,8 +637,28 @@ pass_cse_reciprocals::execute (function
> continue;
>
> gimple_replace_ssa_lhs (stmt1, arg1);
>- gimple_call_set_fndecl (stmt1, fndecl);
>- update_stmt (stmt1);
>+ if (gimple_call_internal_p (stmt1))
>+ {
>+ auto_vec<tree, 4> args;
>+ for (unsigned int i = 0;
>+ i < gimple_call_num_args (stmt1); i++)
>+ args.safe_push (gimple_call_arg (stmt1, i));
>+ gcall *stmt2 = gimple_build_call_vec (fndecl, args);
>+ gimple_call_set_lhs (stmt2, arg1);
>+ if (gimple_vdef (stmt1))
>+ {
>+ gimple_set_vdef (stmt2, gimple_vdef (stmt1));
>+ SSA_NAME_DEF_STMT (gimple_vdef (stmt2)) = stmt2;
>+ }
>+ gimple_set_vuse (stmt2, gimple_vuse (stmt1));
>+ gimple_stmt_iterator gsi2 = gsi_for_stmt (stmt1);
>+ gsi_replace (&gsi2, stmt2, true);
>+ }
>+ else
>+ {
>+ gimple_call_set_fndecl (stmt1, fndecl);
>+ update_stmt (stmt1);
>+ }
> reciprocal_stats.rfuncs_inserted++;
>
> FOR_EACH_IMM_USE_STMT (stmt, ui, arg1)
>--- gcc/config/i386/i386.c.jj 2015-11-25 09:49:57.000000000 +0100
>+++ gcc/config/i386/i386.c 2015-11-27 17:24:30.743625244 +0100
>@@ -42680,16 +42680,40 @@ ix86_vectorize_builtin_scatter (const_tr
> reciprocal of the function, or NULL_TREE if not available. */
>
> static tree
>-ix86_builtin_reciprocal (unsigned int fn, bool md_fn, bool)
>+ix86_builtin_reciprocal (gcall *call)
> {
> if (! (TARGET_SSE_MATH && !optimize_insn_for_size_p ()
> && flag_finite_math_only && !flag_trapping_math
> && flag_unsafe_math_optimizations))
> return NULL_TREE;
>
>- if (md_fn)
>+ if (gimple_call_internal_p (call))
>+ switch (gimple_call_internal_fn (call))
>+ {
>+ tree type;
>+ case IFN_SQRT:
>+ type = TREE_TYPE (gimple_call_lhs (call));
>+ switch (TYPE_MODE (type))
>+ {
>+ /* Vectorized version of sqrt to rsqrt conversion. */
>+ case V4SFmode:
>+ return ix86_get_builtin (IX86_BUILTIN_RSQRTPS_NR);
>+
>+ case V8SFmode:
>+ return ix86_get_builtin (IX86_BUILTIN_RSQRTPS_NR256);
>+
>+ default:
>+ return NULL_TREE;
>+ }
>+
>+ default:
>+ return NULL_TREE;
>+ }
>+
>+ tree fndecl = gimple_call_fndecl (call);
>+ if (DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD)
> /* Machine dependent builtins. */
>- switch (fn)
>+ switch (DECL_FUNCTION_CODE (fndecl))
> {
> /* Vectorized version of sqrt to rsqrt conversion. */
> case IX86_BUILTIN_SQRTPS_NR:
>@@ -42703,7 +42727,7 @@ ix86_builtin_reciprocal (unsigned int fn
> }
> else
> /* Normal builtins. */
>- switch (fn)
>+ switch (DECL_FUNCTION_CODE (fndecl))
> {
> /* Sqrt to rsqrt conversion. */
> case BUILT_IN_SQRTF:
>--- gcc/config/rs6000/rs6000.c.jj 2015-11-26 10:41:04.000000000 +0100
>+++ gcc/config/rs6000/rs6000.c 2015-11-27 17:26:11.238203965 +0100
>@@ -32643,14 +32643,42 @@ rs6000_memory_move_cost (machine_mode mo
> reciprocal of the function, or NULL_TREE if not available. */
>
> static tree
>-rs6000_builtin_reciprocal (unsigned int fn, bool md_fn,
>- bool sqrt ATTRIBUTE_UNUSED)
>+rs6000_builtin_reciprocal (gcall *call)
> {
> if (optimize_insn_for_size_p ())
> return NULL_TREE;
>
>- if (md_fn)
>- switch (fn)
>+ if (gimple_call_internal_p (call))
>+ switch (gimple_call_internal_fn (call))
>+ {
>+ tree type;
>+ case IFN_SQRT:
>+ type = TREE_TYPE (gimple_call_lhs (call));
>+ switch (TYPE_MODE (type))
>+ {
>+ case V2DFmode:
>+ if (!RS6000_RECIP_AUTO_RSQRTE_P (V2DFmode))
>+ return NULL_TREE;
>+
>+ return rs6000_builtin_decls[VSX_BUILTIN_RSQRT_2DF];
>+
>+ case V4SFmode:
>+ if (!RS6000_RECIP_AUTO_RSQRTE_P (V4SFmode))
>+ return NULL_TREE;
>+
>+ return rs6000_builtin_decls[VSX_BUILTIN_RSQRT_4SF];
>+
>+ default:
>+ return NULL_TREE;
>+ }
>+
>+ default:
>+ return NULL_TREE;
>+ }
>+
>+ tree fndecl = gimple_call_fndecl (call);
>+ if (DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD)
>+ switch (DECL_FUNCTION_CODE (fndecl))
> {
> case VSX_BUILTIN_XVSQRTDP:
> if (!RS6000_RECIP_AUTO_RSQRTE_P (V2DFmode))
>@@ -32669,7 +32697,7 @@ rs6000_builtin_reciprocal (unsigned int
> }
>
> else
>- switch (fn)
>+ switch (DECL_FUNCTION_CODE (fndecl))
> {
> case BUILT_IN_SQRT:
> if (!RS6000_RECIP_AUTO_RSQRTE_P (DFmode))
>--- gcc/config/aarch64/aarch64.c.jj 2015-11-23 17:13:34.000000000 +0100
>+++ gcc/config/aarch64/aarch64.c 2015-11-27 17:14:22.295230125 +0100
>@@ -7103,19 +7103,21 @@ aarch64_memory_move_cost (machine_mode m
> reciprocal square root builtins. */
>
> static tree
>-aarch64_builtin_reciprocal (unsigned int fn,
>- bool md_fn,
>- bool)
>+aarch64_builtin_reciprocal (gcall *call)
> {
> if (flag_trapping_math
> || !flag_unsafe_math_optimizations
> || optimize_size
> || ! (aarch64_tune_params.extra_tuning_flags
> & AARCH64_EXTRA_TUNE_RECIP_SQRT))
>- {
> return NULL_TREE;
>- }
>
>+ if (gimple_call_internal_p (call)
>+ return NULL_TREE;
>+
>+ tree fndecl = gimple_call_fndecl (call);
>+ enum built_in_function fn = DECL_FUNCTION_CODE (fndecl);
>+ bool md_fn = DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD;
> return aarch64_builtin_rsqrt (fn, md_fn);
> }
>
>--- gcc/doc/tm.texi.jj 2015-11-18 11:19:16.000000000 +0100
>+++ gcc/doc/tm.texi 2015-11-27 16:48:40.388031894 +0100
>@@ -5608,14 +5608,10 @@ be placed in an @code{object_block} stru
> The default version returns true for all decls.
> @end deftypefn
>
>-@deftypefn {Target Hook} tree TARGET_BUILTIN_RECIPROCAL (unsigned
>@var{fn}, bool @var{md_fn}, bool @var{sqrt})
>+@deftypefn {Target Hook} tree TARGET_BUILTIN_RECIPROCAL (gcall
>*@var{call})
>This hook should return the DECL of a function that implements
>reciprocal of
>-the builtin function with builtin function code @var{fn}, or
>-@code{NULL_TREE} if such a function is not available. @var{md_fn} is
>true
>-when @var{fn} is a code of a machine-dependent builtin function. When
>-@var{sqrt} is true, additional optimizations that apply only to the
>reciprocal
>-of a square root function are performed, and only reciprocals of
>@code{sqrt}
>-function are valid.
>+the builtin or internal function call @var{call}, or
>+@code{NULL_TREE} if such a function is not available.
> @end deftypefn
>
>@deftypefn {Target Hook} tree TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD
>(void)
>
> Jakub
More information about the Gcc-patches
mailing list