Tehila Meyzels - Re: [PATCH, i386]: Vectorize conversions for i386 (original) (raw)

This is the mail archive of the gcc-patches@gcc.gnu.orgmailing list for the GCC project.

• From: Tehila Meyzels
• To: Dorit Nuzman
• Cc: GCC Patches , Richard Guenther , Uros Bizjak
• Date: Sun, 11 Feb 2007 00:10:42 +0200
• Subject: Re: [PATCH, i386]: Vectorize conversions for i386

Dorit Nuzman/Haifa/IBM wrote on 09/02/2007 21:04:51:

Uros Bizjak ubizjak@gmail.com wrote on 08/02/2007 16:50:23:

Hello!

This patch implements conversions for i386 and x86_64 targets. Patch

Cool, thanks!

I'd like to join the acknowledgement. Thanks, Uros!

builds on (yet uncommitted) patch that implements vectorized conversions infrastructure by Tehila Meyzels (http://gcc.gnu.org/ml/gcc-patches/2007-02/msg00494.html).

I plan to commit it soonish. The vectorization-of-induction patch that I committed a couple of days ago actually exposed a couple of problems in this patch - I'm fixing it now - will commit the fixed version (and submit the fixes to the list) this weekend.

Dorit, thanks a lot for handling this. Anything I can help with ?

Tehila.

dorit

Patch was bootstrapped on x86_64-pc-linux-gnu and regression tested for

c,c++ and gfortran.

This patch also includes two testcases from original patch, changed to account for i386 and x86_64 targets and a testcase that checks float-int conversions.

2007-02-08 Uros Bizjak ubizjak@gmail.com

    * config/i386/i386.c (TARGET_VECTORIZE_BUILTIN_CONVERSION):

Define. (ix86_builtin_conversion): New function.

testsuite/ChangeLog:

    * gcc.dg/vect/vect-intfloat-conversion-1.c: Scan for vectorized

loop also for i?86-- and x86_64-- targets. * gcc.dg/vect/vect-intfloat-conversion-2.c: Ditto. * gcc.dg/vect/vect-floatint-conversion-1.c: New.

Uros.

Index: config/i386/i386.c

--- config/i386/i386.c (revision 121711) +++ config/i386/i386.c (working copy) @@ -1516,6 +1516,7 @@ static void ix86_init_builtins (void); static rtx ix86_expand_builtin (tree, rtx, rtx, enum machine_mode, int); static tree ix86_builtin_vectorized_function (enum built_in_function, tree, tree); +static tree ix86_builtin_conversion (enum tree_code, tree); static const char *ix86_mangle_fundamental_type (tree); static tree ix86_stack_protect_fail (void); static rtx ix86_internal_arg_pointer (void); @@ -1580,8 +1581,11 @@ #define TARGET_INIT_BUILTINS ix86_init_builtins #undef TARGET_EXPAND_BUILTIN #define TARGET_EXPAND_BUILTIN ix86_expand_builtin + #undef TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION #define TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION ix86_builtin_vectorized_function +#undef TARGET_VECTORIZE_BUILTIN_CONVERSION +#define TARGET_VECTORIZE_BUILTIN_CONVERSION ix86_builtin_conversion

#undef TARGET_ASM_FUNCTION_EPILOGUE #define TARGET_ASM_FUNCTION_EPILOGUE ix86_output_function_epilogue @@ -18056,6 +18060,40 @@ return NULL_TREE; }

+/* Returns a decl of a function that implements conversion of the + input vector of type TYPE, or NULL_TREE if it is not available. / + +static tree +ix86_builtin_conversion (enum tree_code code, tree type) +{ + if (TREE_CODE (type) != VECTOR_TYPE) + return NULL_TREE; + + switch (code) + { + case FLOAT_EXPR: + switch (TYPE_MODE (type)) + { + case V4SImode: + return ix86_builtins[IX86_BUILTIN_CVTDQ2PS]; + default: + return NULL_TREE; + } + + case FIX_TRUNC_EXPR: + switch (TYPE_MODE (type)) + { + case V4SFmode: + return ix86_builtins[IX86_BUILTIN_CVTTPS2DQ]; + default: + return NULL_TREE; + } + default: + return NULL_TREE; + + } +} + / Store OPERAND to the memory after reload is completed. This means that we can't easily use assign_stack_local. */ rtx Index: testsuite/gcc.dg/vect/vect-intfloat-conversion-1.c

--- testsuite/gcc.dg/vect/vect-intfloat-conversion-1.c (revision 0) +++ testsuite/gcc.dg/vect/vect-intfloat-conversion-1.c (revision 0) @@ -0,0 +1,38 @@ +/* { dg-require-effective-target vect_int } / + +#include <stdarg.h> +#include "tree-vect.h" + +#define N 32 + +int main1 () +{ + int i; + int ib[N] = {0,3,6,9,12,15,18,21,24,27,30,33,36,39,42,45,0,3,6,9, 12,15,18,21,24,27,30,33,36,39,42,45}; + float fa[N]; + + / int -> float / + for (i = 0; i < N; i++) + { + fa[i] = (float) ib[i]; + } + + / check results: / + for (i = 0; i < N; i++) + { + if (fa[i] != (float) ib[i]) + abort (); + } + + return 0; +} + +int main (void) +{ + check_vect (); + + return main1 (); +} + +/ { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target powerpc*-- i?86-- x86_64-- } } } / +/ { dg-final { cleanup-tree-dump "vect" } } */ Index: testsuite/gcc.dg/vect/vect-intfloat-conversion-2.c

--- testsuite/gcc.dg/vect/vect-intfloat-conversion-2.c (revision 0) +++ testsuite/gcc.dg/vect/vect-intfloat-conversion-2.c (revision 0) @@ -0,0 +1,40 @@ +/* { dg-require-effective-target vect_int } / + +#include <stdarg.h> +#include "tree-vect.h" + +#define N 32 + +int main1 () +{ + int i; + int int_arr[N] = {0,3,6,9,12,15,18,21,24,27,30,33,36,39,42,45,0, 3,6,9,12,15,18,21,24,27,30,33,36,39,42,45}; + float float_arr[N]; + char char_arr[N]; + + for (i = 0; i < N; i++){ + float_arr[i] = (float) int_arr[i]; + char_arr[i] = 0; + } + + / check results: / + for (i = 0; i < N; i++) + { + if (float_arr[i] != (float) int_arr[i]) + abort (); + if (char_arr[i] != 0) + abort (); + } + + return 0; +} + +int main (void) +{ + check_vect (); + + return main1 (); +} + +/ { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target powerpc*-- i?86-- x86_64-- } } } / +/ { dg-final { cleanup-tree-dump "vect" } } */ Index: testsuite/gcc.dg/vect/vect-floatint-conversion-1.c

--- testsuite/gcc.dg/vect/vect-floatint-conversion-1.c (revision 0) +++ testsuite/gcc.dg/vect/vect-floatint-conversion-1.c (revision 0) @@ -0,0 +1,40 @@ +/* { dg-require-effective-target vect_float } */ + +#include <stdarg.h> +#include "tree-vect.h" + +#define N 32 + +int +main1 () +{

• int i;
• float fb[N] = {0.4,3.5,6.6,9.4,12.5,15.6,18.4,21.5,24.6,27.4,30. 5,33.6,36.4,39.5,42.6,45.4,0.5,3.6,6.4,9.5,12.6,15.4,18.5,21.6,24.4, 27.5,30.6,33.4,36.5,39.6,42.4,45.5};
• int ia[N];
• /* float -> int */
• for (i = 0; i < N; i++)
• {

•  ia[i] = (int) fb[i];

• }
• /* check results: */
• for (i = 0; i < N; i++)
• {

•  if (ia[i] != (int) fb[i])

• abort ();
• }
• return 0; +}
• +int +main (void) +{
• check_vect ();
• return main1 (); +}
• +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target i?86-- x86_64-- } } } / +/ { dg-final { cleanup-tree-dump "vect" } } */