Skip to content

R
riscv-gcc-1
Commit c882a2c2 by Dorit Nuzman Committed by Dorit Nuzman
Options

spu.md (vec_widen_umult_hi_v8hi): New. 

        * config/spu/spu.md (vec_widen_umult_hi_v8hi): New.
        (vec_widen_umult_lo_v8hi, vec_widen_smult_hi_v8hi): New.
        (vec_widen_smult_lo_v8hi): New.
        * config/spu/spu.c (TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_EVEN): Defined.
        (TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_ODD): Defined.
        (spu_builtin_mul_widen_even, spu_builtin_mul_widen_odd): New.

From-SVN: r120073
parent 71f77fd7
Showing with 170 additions and 0 deletions
gcc/ChangeLog
2006-12-20 Dorit Nuzman <dorit@il.ibm.com>
* config/spu/spu.md (vec_widen_umult_hi_v8hi): New.
(vec_widen_umult_lo_v8hi, vec_widen_smult_hi_v8hi): New.
(vec_widen_smult_lo_v8hi): New.
* config/spu/spu.c (TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_EVEN): Defined.
(TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_ODD): Defined.
(spu_builtin_mul_widen_even, spu_builtin_mul_widen_odd): New.
2006-12-20 Jan Hubicka <jh@suse.cz> 2006-12-20 Jan Hubicka <jh@suse.cz>
* cgraph.c: Update overall comment; fix vertical spacing. * cgraph.c: Update overall comment; fix vertical spacing.
......
gcc/config/spu/spu.c
...@@ -130,6 +130,8 @@ static void spu_init_libfuncs (void); ...@@ -130,6 +130,8 @@ static void spu_init_libfuncs (void);
static bool spu_return_in_memory (tree type, tree fntype); static bool spu_return_in_memory (tree type, tree fntype);
static void fix_range (const char *); static void fix_range (const char *);
static void spu_encode_section_info (tree, rtx, int); static void spu_encode_section_info (tree, rtx, int);
static tree spu_builtin_mul_widen_even (tree);
static tree spu_builtin_mul_widen_odd (tree);
static tree spu_builtin_mask_for_load (void); static tree spu_builtin_mask_for_load (void);
extern const char *reg_names[]; extern const char *reg_names[];
...@@ -249,6 +251,12 @@ const struct attribute_spec spu_attribute_table[]; ...@@ -249,6 +251,12 @@ const struct attribute_spec spu_attribute_table[];
#undef TARGET_ENCODE_SECTION_INFO #undef TARGET_ENCODE_SECTION_INFO
#define TARGET_ENCODE_SECTION_INFO spu_encode_section_info #define TARGET_ENCODE_SECTION_INFO spu_encode_section_info
#undef TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_EVEN
#define TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_EVEN spu_builtin_mul_widen_even
#undef TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_ODD
#define TARGET_VECTORIZE_BUILTIN_MUL_WIDEN_ODD spu_builtin_mul_widen_odd
#undef TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD #undef TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD
#define TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD spu_builtin_mask_for_load #define TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD spu_builtin_mask_for_load
...@@ -4993,6 +5001,41 @@ spu_expand_builtin (tree exp, ...@@ -4993,6 +5001,41 @@ spu_expand_builtin (tree exp,
abort (); abort ();
} }
/* Implement targetm.vectorize.builtin_mul_widen_even. */
static tree
spu_builtin_mul_widen_even (tree type)
{
struct spu_builtin_description *d;
switch (TYPE_MODE (type))
{
case V8HImode:
if (TYPE_UNSIGNED (type))
return spu_builtins[SPU_MULE_0].fndecl;
else
return spu_builtins[SPU_MULE_1].fndecl;
break;
default:
return NULL_TREE;
}
}
/* Implement targetm.vectorize.builtin_mul_widen_odd. */
static tree
spu_builtin_mul_widen_odd (tree type)
{
switch (TYPE_MODE (type))
{
case V8HImode:
if (TYPE_UNSIGNED (type))
return spu_builtins[SPU_MULO_1].fndecl;
else
return spu_builtins[SPU_MULO_0].fndecl;
break;
default:
return NULL_TREE;
}
}
/* Implement targetm.vectorize.builtin_mask_for_load. */ /* Implement targetm.vectorize.builtin_mask_for_load. */
static tree static tree
spu_builtin_mask_for_load (void) spu_builtin_mask_for_load (void)
......
gcc/config/spu/spu.md
...@@ -3378,6 +3378,118 @@ selb\t%0,%4,%0,%3" ...@@ -3378,6 +3378,118 @@ selb\t%0,%4,%0,%3"
DONE; DONE;
}") }")
(define_expand "vec_widen_umult_hi_v8hi"
[(set (match_operand:V4SI 0 "register_operand" "=r")
(mult:V4SI
(zero_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 1 "register_operand" "r")
(parallel [(const_int 0)(const_int 1)(const_int 2)(const_int 3)])))
(zero_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 2 "register_operand" "r")
(parallel [(const_int 0)(const_int 1)(const_int 2)(const_int 3)])))))]
""
"
{
rtx ve = gen_reg_rtx (V4SImode);
rtx vo = gen_reg_rtx (V4SImode);
rtx mask = gen_reg_rtx (TImode);
unsigned char arr[16] = {
0x00, 0x01, 0x02, 0x03, 0x10, 0x11, 0x12, 0x13,
0x04, 0x05, 0x06, 0x07, 0x14, 0x15, 0x16, 0x17};
emit_move_insn (mask, array_to_constant (TImode, arr));
emit_insn (gen_spu_mpyhhu (ve, operands[1], operands[2]));
emit_insn (gen_spu_mpyu (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
(define_expand "vec_widen_umult_lo_v8hi"
[(set (match_operand:V4SI 0 "register_operand" "=r")
(mult:V4SI
(zero_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 1 "register_operand" "r")
(parallel [(const_int 4)(const_int 5)(const_int 6)(const_int 7)])))
(zero_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 2 "register_operand" "r")
(parallel [(const_int 4)(const_int 5)(const_int 6)(const_int 7)])))))]
""
"
{
rtx ve = gen_reg_rtx (V4SImode);
rtx vo = gen_reg_rtx (V4SImode);
rtx mask = gen_reg_rtx (TImode);
unsigned char arr[16] = {
0x08, 0x09, 0x0A, 0x0B, 0x18, 0x19, 0x1A, 0x1B,
0x0C, 0x0D, 0x0E, 0x0F, 0x1C, 0x1D, 0x1E, 0x1F};
emit_move_insn (mask, array_to_constant (TImode, arr));
emit_insn (gen_spu_mpyhhu (ve, operands[1], operands[2]));
emit_insn (gen_spu_mpyu (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
(define_expand "vec_widen_smult_hi_v8hi"
[(set (match_operand:V4SI 0 "register_operand" "=r")
(mult:V4SI
(sign_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 1 "register_operand" "r")
(parallel [(const_int 0)(const_int 1)(const_int 2)(const_int 3)])))
(sign_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 2 "register_operand" "r")
(parallel [(const_int 0)(const_int 1)(const_int 2)(const_int 3)])))))]
""
"
{
rtx ve = gen_reg_rtx (V4SImode);
rtx vo = gen_reg_rtx (V4SImode);
rtx mask = gen_reg_rtx (TImode);
unsigned char arr[16] = {
0x00, 0x01, 0x02, 0x03, 0x10, 0x11, 0x12, 0x13,
0x04, 0x05, 0x06, 0x07, 0x14, 0x15, 0x16, 0x17};
emit_move_insn (mask, array_to_constant (TImode, arr));
emit_insn (gen_spu_mpyhh (ve, operands[1], operands[2]));
emit_insn (gen_spu_mpy (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
(define_expand "vec_widen_smult_lo_v8hi"
[(set (match_operand:V4SI 0 "register_operand" "=r")
(mult:V4SI
(sign_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 1 "register_operand" "r")
(parallel [(const_int 4)(const_int 5)(const_int 6)(const_int 7)])))
(sign_extend:V4SI
(vec_select:V4HI
(match_operand:V8HI 2 "register_operand" "r")
(parallel [(const_int 4)(const_int 5)(const_int 6)(const_int 7)])))))]
""
"
{
rtx ve = gen_reg_rtx (V4SImode);
rtx vo = gen_reg_rtx (V4SImode);
rtx mask = gen_reg_rtx (TImode);
unsigned char arr[16] = {
0x08, 0x09, 0x0A, 0x0B, 0x18, 0x19, 0x1A, 0x1B,
0x0C, 0x0D, 0x0E, 0x0F, 0x1C, 0x1D, 0x1E, 0x1F};
emit_move_insn (mask, array_to_constant (TImode, arr));
emit_insn (gen_spu_mpyhh (ve, operands[1], operands[2]));
emit_insn (gen_spu_mpy (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
(define_expand "vec_realign_load_<mode>" (define_expand "vec_realign_load_<mode>"
[(set (match_operand:ALL 0 "register_operand" "=r") [(set (match_operand:ALL 0 "register_operand" "=r")
(unspec:ALL [(match_operand:ALL 1 "register_operand" "r") (unspec:ALL [(match_operand:ALL 1 "register_operand" "r")
......
gcc/testsuite/ChangeLog
2006-12-20 Dorit Nuzman <dorit@il.ibm.com>
* lib/target-supports.exp: Add spu to
check_effective_target_vect_widen_mult_hi_to_si.
2006-12-20 Paul Thomas <pault@gcc.gnu.org> 2006-12-20 Paul Thomas <pault@gcc.gnu.org>
PR fortran/29992 PR fortran/29992
gcc/testsuite/lib/target-supports.exp
...@@ -1641,6 +1641,7 @@ proc check_effective_target_vect_widen_mult_hi_to_si { } { ...@@ -1641,6 +1641,7 @@ proc check_effective_target_vect_widen_mult_hi_to_si { } {
set et_vect_widen_mult_hi_to_si_saved 0 set et_vect_widen_mult_hi_to_si_saved 0
} }
if { [istarget powerpc*-*-*] if { [istarget powerpc*-*-*]
|| [istarget spu-*-*]
|| [istarget i?86-*-*] || [istarget i?86-*-*]
|| [istarget x86_64-*-*] } { || [istarget x86_64-*-*] } {
set et_vect_widen_mult_hi_to_si_saved 1 set et_vect_widen_mult_hi_to_si_saved 1
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment