This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
[GSoC-19] Expanding Roundeven
- From: Tejas Joshi <tejasjoshi9673 at gmail dot com>
- To: gcc at gcc dot gnu dot org
- Cc: Martin Jambor <mjambor at suse dot cz>, hubicka at ucw dot cz, joseph at codesourcery dot com
- Date: Sat, 29 Jun 2019 19:05:03 +0530
- Subject: [GSoC-19] Expanding Roundeven
Hello.
This was a mail in thread Re: Expanding roundeven on 19th June but as
its gone far inside the thread, I thought of having a fresh one. The
following patch expands roundeven with instruction vroundsd using
-mavx option but without it is giving internal compiler error which I
believe is due to reaching gcc_unreachable (). The doubts I had come
up with :
Test code compiled with attached patch:
double
plusone (double d)
{
return __builtin_roundeven (d) + 1;
}
Compiling the program using -O2 gave internal compiler error which
I believe is because gcc_unreachable() at:
Inside :
(define_expand "<rounding_insn><mode>2"
There is a condition :
if (TARGET_SSE4_1)
emit_insn (gen_sse4_1_round<mode>2
(operands[0], operands[1], GEN_INT (ROUND_<ROUNDING>
| ROUND_NO_EXC)));
I think the above condition matches the criterion which Joseph
previously mentioned? :
> I think the code will be much clearer if it explicitly says
> ROUND_ROUNDEVEN | ROUND_NO_EXC,
else if (TARGET_64BIT || (<MODE>mode != DFmode))
{
if (ROUND_<ROUNDING> == ROUND_FLOOR)
ix86_expand_floorceil (operands[0], operands[1], true);
else if (ROUND_<ROUNDING> == ROUND_CEIL)
ix86_expand_floorceil (operands[0], operands[1], false);
else if (ROUND_<ROUNDING> == ROUND_TRUNC)
ix86_expand_trunc (operands[0], operands[1]);
else
gcc_unreachable ();
}
But with -mavx option, assembly generated the vroundsd insn. Does it
mean ROUNDEVEN
should have a condition in the above else if, but comments above
ix86_expand* functions in i386-expand.c says that those are for SSE2
sequences?
Thanks,
-Tejas
diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index e547dda80f1..40536d7929c 100644
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -906,6 +906,7 @@ BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_floor
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_ceilpd", IX86_BUILTIN_CEILPD, (enum rtx_code) ROUND_CEIL, (int) V2DF_FTYPE_V2DF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_truncpd", IX86_BUILTIN_TRUNCPD, (enum rtx_code) ROUND_TRUNC, (int) V2DF_FTYPE_V2DF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_rintpd", IX86_BUILTIN_RINTPD, (enum rtx_code) ROUND_MXCSR, (int) V2DF_FTYPE_V2DF_ROUND)
+BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_roundevenpd", IX86_BUILTIN_ROUNDEVENPD, (enum rtx_code) ROUND_ROUNDEVEN, (int) V2DF_FTYPE_V2DF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd_vec_pack_sfix, "__builtin_ia32_floorpd_vec_pack_sfix", IX86_BUILTIN_FLOORPD_VEC_PACK_SFIX, (enum rtx_code) ROUND_FLOOR, (int) V4SI_FTYPE_V2DF_V2DF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundpd_vec_pack_sfix, "__builtin_ia32_ceilpd_vec_pack_sfix", IX86_BUILTIN_CEILPD_VEC_PACK_SFIX, (enum rtx_code) ROUND_CEIL, (int) V4SI_FTYPE_V2DF_V2DF_ROUND)
@@ -917,6 +918,7 @@ BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps, "__builtin_ia32_floor
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps, "__builtin_ia32_ceilps", IX86_BUILTIN_CEILPS, (enum rtx_code) ROUND_CEIL, (int) V4SF_FTYPE_V4SF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps, "__builtin_ia32_truncps", IX86_BUILTIN_TRUNCPS, (enum rtx_code) ROUND_TRUNC, (int) V4SF_FTYPE_V4SF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps, "__builtin_ia32_rintps", IX86_BUILTIN_RINTPS, (enum rtx_code) ROUND_MXCSR, (int) V4SF_FTYPE_V4SF_ROUND)
+BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps, "__builtin_ia32_roundevenps", IX86_BUILTIN_ROUNDEVENPS, (enum rtx_code) ROUND_ROUNDEVEN, (int) V4SF_FTYPE_V4SF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps_sfix, "__builtin_ia32_floorps_sfix", IX86_BUILTIN_FLOORPS_SFIX, (enum rtx_code) ROUND_FLOOR, (int) V4SI_FTYPE_V4SF_ROUND)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps_sfix, "__builtin_ia32_ceilps_sfix", IX86_BUILTIN_CEILPS_SFIX, (enum rtx_code) ROUND_CEIL, (int) V4SI_FTYPE_V4SF_ROUND)
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 01213ccb82c..ce58b5e5c28 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2468,6 +2468,7 @@ enum ix86_stack_slot
SLOT_CW_TRUNC,
SLOT_CW_FLOOR,
SLOT_CW_CEIL,
+ SLOT_CW_ROUNDEVEN,
SLOT_STV_TEMP,
MAX_386_STACK_LOCALS
};
@@ -2479,6 +2480,7 @@ enum ix86_entity
I387_TRUNC,
I387_FLOOR,
I387_CEIL,
+ I387_ROUNDEVEN,
MAX_386_ENTITIES
};
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 01338e294ab..b11af2f4308 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -144,6 +144,7 @@
UNSPEC_FRNDINT_FLOOR
UNSPEC_FRNDINT_CEIL
UNSPEC_FRNDINT_TRUNC
+ UNSPEC_FRNDINT_ROUNDEVEN
UNSPEC_FIST_FLOOR
UNSPEC_FIST_CEIL
@@ -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" "trunc,floor,ceil,roundeven,uninitialized,any"
(const_string "any"))
;; Define attribute to indicate AVX insns with partial XMM register update.
@@ -16254,7 +16256,8 @@
(define_int_iterator FRNDINT_ROUNDING
[UNSPEC_FRNDINT_FLOOR
UNSPEC_FRNDINT_CEIL
- UNSPEC_FRNDINT_TRUNC])
+ UNSPEC_FRNDINT_TRUNC
+ UNSPEC_FRNDINT_ROUNDEVEN])
(define_int_iterator FIST_ROUNDING
[UNSPEC_FIST_FLOOR
@@ -16265,6 +16268,7 @@
[(UNSPEC_FRNDINT_FLOOR "floor")
(UNSPEC_FRNDINT_CEIL "ceil")
(UNSPEC_FRNDINT_TRUNC "btrunc")
+ (UNSPEC_FRNDINT_ROUNDEVEN "roundeven")
(UNSPEC_FIST_FLOOR "floor")
(UNSPEC_FIST_CEIL "ceil")])
@@ -16272,6 +16276,7 @@
[(UNSPEC_FRNDINT_FLOOR "floor")
(UNSPEC_FRNDINT_CEIL "ceil")
(UNSPEC_FRNDINT_TRUNC "trunc")
+ (UNSPEC_FRNDINT_ROUNDEVEN "roundeven")
(UNSPEC_FIST_FLOOR "floor")
(UNSPEC_FIST_CEIL "ceil")])
@@ -16279,6 +16284,7 @@
[(UNSPEC_FRNDINT_FLOOR "FLOOR")
(UNSPEC_FRNDINT_CEIL "CEIL")
(UNSPEC_FRNDINT_TRUNC "TRUNC")
+ (UNSPEC_FRNDINT_ROUNDEVEN "ROUNDEVEN")
(UNSPEC_FIST_FLOOR "FLOOR")
(UNSPEC_FIST_CEIL "CEIL")])
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index 016301a58d8..c07d48594e3 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -231,6 +231,7 @@ DEF_INTERNAL_FLT_FLOATN_FN (FLOOR, ECF_CONST, floor, unary)
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. */
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 8af3a2f43fd..839d250b8c6 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -267,6 +267,7 @@ 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")