public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-06-15 17:19 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-06-15 17:19 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:000aba9eb77810a73e54764f781eef265afcc7cc
commit 000aba9eb77810a73e54764f781eef265afcc7cc
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 75c2cc4f8b7..37eb05ddf4f 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -77,6 +77,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5488,6 +5489,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5607,6 +5800,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5738,6 +5934,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-07-29 14:46 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-07-29 14:46 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:703e50bd774a94229574c561fc75abb569c94937
commit 703e50bd774a94229574c561fc75abb569c94937
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 279f00cc648..ceba25d028c 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -78,6 +78,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5489,6 +5490,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5608,6 +5801,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5739,6 +5935,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-06-25 16:18 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-06-25 16:18 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:9c81728a7f29308f4b39bd8a5a0d4f059d938cf4
commit 9c81728a7f29308f4b39bd8a5a0d4f059d938cf4
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 38f928134f3..70a2be90787 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -77,6 +77,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5488,6 +5489,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5607,6 +5800,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5738,6 +5934,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-04-26 20:51 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-04-26 20:51 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:8873df8c82f64b2fd1cb4a3b34b2cb74e024f71a
commit 8873df8c82f64b2fd1cb4a3b34b2cb74e024f71a
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 844fee88cf3..080e6a70221 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -77,6 +77,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5454,6 +5455,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5573,6 +5766,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5704,6 +5900,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-04-02 22:12 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-04-02 22:12 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:3d8ae5a6d46657d7b7c4115344117c80320b1019
commit 3d8ae5a6d46657d7b7c4115344117c80320b1019
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 34c4edae20e..487c0ac7012 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -77,6 +77,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5450,6 +5451,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5569,6 +5762,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5700,6 +5896,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-04-01 19:50 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-04-01 19:50 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:5f9c71ac442cd426c1644725624dd782b372f382
commit 5f9c71ac442cd426c1644725624dd782b372f382
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 34c4edae20e..487c0ac7012 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -77,6 +77,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5450,6 +5451,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5569,6 +5762,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5700,6 +5896,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions
@ 2021-03-25 15:48 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-03-25 15:48 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:e91e1f30da7e52dada04d8ee8689365aaebf1052
commit e91e1f30da7e52dada04d8ee8689365aaebf1052
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Fri Mar 5 10:45:56 2021 -0600
rs6000: Support for vectorizing built-in functions
2021-03-05 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000.c (rs6000-builtins.h): New include.
(rs6000_new_builtin_vectorized_function): New function.
(rs6000_new_builtin_md_vectorized_function): Likewise.
(rs6000_builtin_vectorized_function): Call
rs6000_new_builtin_vectorized_function.
(rs6000_builtin_md_vectorized_function): Call
rs6000_new_builtin_md_vectorized_function.
Diff:
---
gcc/config/rs6000/rs6000.c | 200 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 200 insertions(+)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 34c4edae20e..487c0ac7012 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -77,6 +77,7 @@
#include "case-cfn-macros.h"
#include "ppc-auxv.h"
#include "rs6000-internal.h"
+#include "rs6000-builtins.h"
#include "opts.h"
/* This file should be included last. */
@@ -5450,6 +5451,198 @@ rs6000_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
return nunroll;
}
+/* Returns a function decl for a vectorized version of the builtin function
+ with builtin function code FN and the result vector type TYPE, or NULL_TREE
+ if it is not available. */
+
+static tree
+rs6000_new_builtin_vectorized_function (unsigned int fn, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr, "rs6000_new_builtin_vectorized_function (%s, %s, %s)\n",
+ combined_fn_name (combined_fn (fn)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ switch (fn)
+ {
+ CASE_CFN_COPYSIGN:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_CPSGNSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_COPYSIGN_V4SF];
+ break;
+ CASE_CFN_CEIL:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIP];
+ break;
+ CASE_CFN_FLOOR:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIM];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIM];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIM];
+ break;
+ CASE_CFN_FMA:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDDP];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVMADDSP];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VMADDFP];
+ break;
+ CASE_CFN_TRUNC:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIZ];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIZ];
+ if (VECTOR_UNIT_ALTIVEC_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRFIZ];
+ break;
+ CASE_CFN_NEARBYINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPI];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && flag_unsafe_math_optimizations
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPI];
+ break;
+ CASE_CFN_RINT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && !flag_trapping_math
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRDPIC];
+ if (VECTOR_UNIT_VSX_P (V4SFmode)
+ && !flag_trapping_math
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_XVRSPIC];
+ break;
+ default:
+ break;
+ }
+
+ /* Generate calls to libmass if appropriate. */
+ if (rs6000_veclib_handler)
+ return rs6000_veclib_handler (combined_fn (fn), type_out, type_in);
+
+ return NULL_TREE;
+}
+
+/* Implement TARGET_VECTORIZE_BUILTIN_MD_VECTORIZED_FUNCTION. */
+
+static tree
+rs6000_new_builtin_md_vectorized_function (tree fndecl, tree type_out,
+ tree type_in)
+{
+ machine_mode in_mode, out_mode;
+ int in_n, out_n;
+
+ if (TARGET_DEBUG_BUILTIN)
+ fprintf (stderr,
+ "rs6000_new_builtin_md_vectorized_function (%s, %s, %s)\n",
+ IDENTIFIER_POINTER (DECL_NAME (fndecl)),
+ GET_MODE_NAME (TYPE_MODE (type_out)),
+ GET_MODE_NAME (TYPE_MODE (type_in)));
+
+ if (TREE_CODE (type_out) != VECTOR_TYPE
+ || TREE_CODE (type_in) != VECTOR_TYPE)
+ return NULL_TREE;
+
+ out_mode = TYPE_MODE (TREE_TYPE (type_out));
+ out_n = TYPE_VECTOR_SUBPARTS (type_out);
+ in_mode = TYPE_MODE (TREE_TYPE (type_in));
+ in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+ enum rs6000_gen_builtins fn
+ = (enum rs6000_gen_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+ switch (fn)
+ {
+ case RS6000_BIF_RSQRTF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRSQRTFP];
+ break;
+ case RS6000_BIF_RSQRT:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RSQRT_2DF];
+ break;
+ case RS6000_BIF_RECIPF:
+ if (VECTOR_UNIT_ALTIVEC_OR_VSX_P (V4SFmode)
+ && out_mode == SFmode && out_n == 4
+ && in_mode == SFmode && in_n == 4)
+ return rs6000_builtin_decls_x[RS6000_BIF_VRECIPFP];
+ break;
+ case RS6000_BIF_RECIP:
+ if (VECTOR_UNIT_VSX_P (V2DFmode)
+ && out_mode == DFmode && out_n == 2
+ && in_mode == DFmode && in_n == 2)
+ return rs6000_builtin_decls_x[RS6000_BIF_RECIP_V2DF];
+ break;
+ default:
+ break;
+ }
+ return NULL_TREE;
+}
+
/* Handler for the Mathematical Acceleration Subsystem (mass) interface to a
library with vectorized intrinsics. */
@@ -5569,6 +5762,9 @@ rs6000_builtin_vectorized_function (unsigned int fn, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_vectorized_function (fn, type_out, type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_vectorized_function (%s, %s, %s)\n",
combined_fn_name (combined_fn (fn)),
@@ -5700,6 +5896,10 @@ rs6000_builtin_md_vectorized_function (tree fndecl, tree type_out,
machine_mode in_mode, out_mode;
int in_n, out_n;
+ if (new_builtins_are_live)
+ return rs6000_new_builtin_md_vectorized_function (fndecl, type_out,
+ type_in);
+
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "rs6000_builtin_md_vectorized_function (%s, %s, %s)\n",
IDENTIFIER_POINTER (DECL_NAME (fndecl)),
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2021-07-29 14:46 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-06-15 17:19 [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Support for vectorizing built-in functions William Schmidt
-- strict thread matches above, loose matches on Subject: below --
2021-07-29 14:46 William Schmidt
2021-06-25 16:18 William Schmidt
2021-04-26 20:51 William Schmidt
2021-04-02 22:12 William Schmidt
2021-04-01 19:50 William Schmidt
2021-03-25 15:48 William Schmidt
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).