> This patch is for expanding roundeven inline for SSE4.1 and later.
> Note that this patch is to be applied on top of
> <https://gcc.gnu.org/ml/gcc-patches/2019-06/msg01828.html>. The patch
> is bootstrapped and regression tested on x86_64-linux-gnu.
Actually, your patch at [1] is the way to go, but you need several
other changes to get x87 mode switching in order. Please also note
that there is no corresponding non-SSE4 ix86_expand_... function for
roundeven, so non-SSE4 SSE FP-math <rounding_insn><mode>2 expander has
to be disabled for ROUNDEVEN int iterator. Please see (otherwise
untested) attached patch which fixes both issues.
[1] https://gcc.gnu.org/ml/gcc/2019-06/msg00352.html
Uros.
Index: builtins.c
===================================================================
--- builtins.c (revision 273480)
+++ builtins.c (working copy)
@@ -2056,6 +2056,7 @@ mathfn_built_in_2 (tree type, combined_fn fn)
CASE_MATHFN (REMQUO)
CASE_MATHFN_FLOATN (RINT)
CASE_MATHFN_FLOATN (ROUND)
+ CASE_MATHFN_FLOATN (ROUNDEVEN)
CASE_MATHFN (SCALB)
CASE_MATHFN (SCALBLN)
CASE_MATHFN (SCALBN)
Index: builtins.def
===================================================================
--- builtins.def (revision 273480)
+++ builtins.def (working copy)
@@ -548,6 +548,12 @@ DEF_C99_BUILTIN (BUILT_IN_ROUNDL, "roundl",
#define ROUND_TYPE(F) BT_FN_##F##_##F
DEF_EXT_LIB_FLOATN_NX_BUILTINS (BUILT_IN_ROUND, "round", ROUND_TYPE,
ATTR_CONST_NOTHROW_LEAF_LIST)
#undef ROUND_TYPE
+DEF_EXT_LIB_BUILTIN (BUILT_IN_ROUNDEVEN, "roundeven", BT_FN_DOUBLE_DOUBLE,
ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_EXT_LIB_BUILTIN (BUILT_IN_ROUNDEVENF, "roundevenf", BT_FN_FLOAT_FLOAT,
ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_EXT_LIB_BUILTIN (BUILT_IN_ROUNDEVENL, "roundevenl",
BT_FN_LONGDOUBLE_LONGDOUBLE, ATTR_CONST_NOTHROW_LEAF_LIST)
+#define ROUNDEVEN_TYPE(F) BT_FN_##F##_##F
+DEF_EXT_LIB_FLOATN_NX_BUILTINS (BUILT_IN_ROUNDEVEN, "roundeven",
ROUNDEVEN_TYPE, ATTR_CONST_NOTHROW_LEAF_LIST)
+#undef ROUNDEVEN_TYPE
DEF_EXT_LIB_BUILTIN (BUILT_IN_SCALB, "scalb", BT_FN_DOUBLE_DOUBLE_DOUBLE,
ATTR_MATHFN_FPROUNDING_ERRNO)
DEF_EXT_LIB_BUILTIN (BUILT_IN_SCALBF, "scalbf", BT_FN_FLOAT_FLOAT_FLOAT,
ATTR_MATHFN_FPROUNDING_ERRNO)
DEF_EXT_LIB_BUILTIN (BUILT_IN_SCALBL, "scalbl",
BT_FN_LONGDOUBLE_LONGDOUBLE_LONGDOUBLE, ATTR_MATHFN_FPROUNDING_ERRNO)
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c (revision 273480)
+++ config/i386/i386.c (working copy)
@@ -13593,6 +13593,11 @@ ix86_i387_mode_needed (int entity, rtx_insn *insn)
switch (entity)
{
+ case I387_ROUNDEVEN:
+ if (mode == I387_CW_ROUNDEVEN)
+ return mode;
+ break;
+
case I387_TRUNC:
if (mode == I387_CW_TRUNC)
return mode;
@@ -13627,6 +13632,7 @@ ix86_mode_needed (int entity, rtx_insn *insn)
return ix86_dirflag_mode_needed (insn);
case AVX_U128:
return ix86_avx_u128_mode_needed (insn);
+ case I387_ROUNDEVEN:
case I387_TRUNC:
case I387_FLOOR:
case I387_CEIL:
@@ -13687,6 +13693,7 @@ ix86_mode_after (int entity, int mode, rtx_insn *i
return mode;
case AVX_U128:
return ix86_avx_u128_mode_after (mode, insn);
+ case I387_ROUNDEVEN:
case I387_TRUNC:
case I387_FLOOR:
case I387_CEIL:
@@ -13739,6 +13746,7 @@ ix86_mode_entry (int entity)
return ix86_dirflag_mode_entry ();
case AVX_U128:
return ix86_avx_u128_mode_entry ();
+ case I387_ROUNDEVEN:
case I387_TRUNC:
case I387_FLOOR:
case I387_CEIL:
@@ -13776,6 +13784,7 @@ ix86_mode_exit (int entity)
return X86_DIRFLAG_ANY;
case AVX_U128:
return ix86_avx_u128_mode_exit ();
+ case I387_ROUNDEVEN:
case I387_TRUNC:
case I387_FLOOR:
case I387_CEIL:
@@ -13810,6 +13819,12 @@ emit_i387_cw_initialization (int mode)
switch (mode)
{
+ case I387_CW_ROUNDEVEN:
+ /* round to nearest */
+ emit_insn (gen_andhi3 (reg, reg, GEN_INT (~0x0c00)));
+ slot = SLOT_CW_ROUNDEVEN;
+ break;
+
case I387_CW_TRUNC:
/* round toward zero (truncate) */
emit_insn (gen_iorhi3 (reg, reg, GEN_INT (0x0c00)));
@@ -13856,6 +13871,7 @@ ix86_emit_mode_set (int entity, int mode, int prev
if (mode == AVX_U128_CLEAN)
emit_insn (gen_avx_vzeroupper ());
break;
+ case I387_ROUNDEVEN:
case I387_TRUNC:
case I387_FLOOR:
case I387_CEIL:
Index: config/i386/i386.h
===================================================================
--- config/i386/i386.h (revision 273480)
+++ config/i386/i386.h (working copy)
@@ -2471,6 +2471,7 @@ enum ix86_stack_slot
{
SLOT_TEMP = 0,
SLOT_CW_STORED,
+ SLOT_CW_ROUNDEVEN,
SLOT_CW_TRUNC,
SLOT_CW_FLOOR,
SLOT_CW_CEIL,
@@ -2482,6 +2483,7 @@ enum ix86_entity
{
X86_DIRFLAG = 0,
AVX_U128,
+ I387_ROUNDEVEN,
I387_TRUNC,
I387_FLOOR,
I387_CEIL,
@@ -2517,7 +2519,7 @@ enum avx_u128_state
#define NUM_MODES_FOR_MODE_SWITCHING \
{ X86_DIRFLAG_ANY, AVX_U128_ANY, \
- I387_CW_ANY, I387_CW_ANY, I387_CW_ANY }
+ I387_CW_ANY, I387_CW_ANY, I387_CW_ANY, I387_CW_ANY }
/* Avoid renaming of stack registers, as doing so in combination with
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md (revision 273482)
+++ config/i386/i386.md (working copy)
@@ -141,6 +141,7 @@
UNSPEC_FXAM
;; x87 Rounding
+ UNSPEC_FRNDINT_ROUNDEVEN
UNSPEC_FRNDINT_FLOOR
UNSPEC_FRNDINT_CEIL
UNSPEC_FRNDINT_TRUNC
@@ -303,7 +304,8 @@
;; Constants to represent rounding modes in the ROUND instruction
(define_constants
- [(ROUND_FLOOR 0x1)
+ [(ROUND_ROUNDEVEN 0x0)
+ (ROUND_FLOOR 0x1)
(ROUND_CEIL 0x2)
(ROUND_TRUNC 0x3)
(ROUND_MXCSR 0x4)
@@ -779,7 +781,7 @@
;; Defines rounding mode of an FP operation.
-(define_attr "i387_cw" "trunc,floor,ceil,uninitialized,any"
+(define_attr "i387_cw" "roundeven,floor,ceil,trunc,uninitialized,any"
(const_string "any"))
;; Define attribute to indicate AVX insns with partial XMM register update.
@@ -16248,7 +16250,8 @@
})
(define_int_iterator FRNDINT_ROUNDING
- [UNSPEC_FRNDINT_FLOOR
+ [UNSPEC_FRNDINT_ROUNDEVEN
+ UNSPEC_FRNDINT_FLOOR
UNSPEC_FRNDINT_CEIL
UNSPEC_FRNDINT_TRUNC])
@@ -16258,7 +16261,8 @@
;; Base name for define_insn
(define_int_attr rounding_insn
- [(UNSPEC_FRNDINT_FLOOR "floor")
+ [(UNSPEC_FRNDINT_ROUNDEVEN "roundeven")
+ (UNSPEC_FRNDINT_FLOOR "floor")
(UNSPEC_FRNDINT_CEIL "ceil")
(UNSPEC_FRNDINT_TRUNC "btrunc")
(UNSPEC_FIST_FLOOR "floor")
@@ -16265,7 +16269,8 @@
(UNSPEC_FIST_CEIL "ceil")])
(define_int_attr rounding
- [(UNSPEC_FRNDINT_FLOOR "floor")
+ [(UNSPEC_FRNDINT_ROUNDEVEN "roundeven")
+ (UNSPEC_FRNDINT_FLOOR "floor")
(UNSPEC_FRNDINT_CEIL "ceil")
(UNSPEC_FRNDINT_TRUNC "trunc")
(UNSPEC_FIST_FLOOR "floor")
@@ -16272,7 +16277,8 @@
(UNSPEC_FIST_CEIL "ceil")])
(define_int_attr ROUNDING
- [(UNSPEC_FRNDINT_FLOOR "FLOOR")
+ [(UNSPEC_FRNDINT_ROUNDEVEN "ROUNDEVEN")
+ (UNSPEC_FRNDINT_FLOOR "FLOOR")
(UNSPEC_FRNDINT_CEIL "CEIL")
(UNSPEC_FRNDINT_TRUNC "TRUNC")
(UNSPEC_FIST_FLOOR "FLOOR")
@@ -16335,8 +16341,9 @@
|| TARGET_MIX_SSE_I387)
&& (flag_fp_int_builtin_inexact || !flag_trapping_math))
|| (SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH
- && (TARGET_SSE4_1 || flag_fp_int_builtin_inexact
- || !flag_trapping_math))"
+ && (TARGET_SSE4_1
+ || (ROUND_<ROUNDING> != ROUND_ROUNDEVEN
+ && (flag_fp_int_builtin_inexact || !flag_trapping_math))))"
{
if (SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH
&& (TARGET_SSE4_1 || flag_fp_int_builtin_inexact || !flag_trapping_math))
Index: internal-fn.def
===================================================================
--- internal-fn.def (revision 273480)
+++ internal-fn.def (working copy)
@@ -234,6 +234,7 @@ DEF_INTERNAL_FLT_FLOATN_FN (FLOOR, ECF_CONST, floo
DEF_INTERNAL_FLT_FLOATN_FN (NEARBYINT, ECF_CONST, nearbyint, unary)
DEF_INTERNAL_FLT_FLOATN_FN (RINT, ECF_CONST, rint, unary)
DEF_INTERNAL_FLT_FLOATN_FN (ROUND, ECF_CONST, round, unary)
+DEF_INTERNAL_FLT_FLOATN_FN (ROUNDEVEN, ECF_CONST, roundeven, unary)
DEF_INTERNAL_FLT_FLOATN_FN (TRUNC, ECF_CONST, btrunc, unary)
/* Binary math functions. */
Index: optabs.def
===================================================================
--- optabs.def (revision 273480)
+++ optabs.def (working copy)
@@ -268,6 +268,7 @@ OPTAB_D (fnms_optab, "fnms$a4")
OPTAB_D (rint_optab, "rint$a2")
OPTAB_D (round_optab, "round$a2")
+OPTAB_D (roundeven_optab, "roundeven$a2")
OPTAB_D (floor_optab, "floor$a2")
OPTAB_D (ceil_optab, "ceil$a2")
OPTAB_D (btrunc_optab, "btrunc$a2")
Index: reg-stack.c
===================================================================
--- reg-stack.c (revision 273480)
+++ reg-stack.c (working copy)
@@ -1817,6 +1817,7 @@ subst_stack_regs_pat (rtx_insn *insn, stack_ptr re
case UNSPEC_FRNDINT:
case UNSPEC_F2XM1:
+ case UNSPEC_FRNDINT_ROUNDEVEN:
case UNSPEC_FRNDINT_FLOOR:
case UNSPEC_FRNDINT_CEIL:
case UNSPEC_FRNDINT_TRUNC:
