re PR target/84154 (PowerPC GCC 7 and 8 have regression in converting fp to short/char and returning it)

[gcc]
2018-02-07  Michael Meissner  <meissner@linux.vnet.ibm.com>

	PR target/84154
	* config/rs6000/rs6000.md (fix_trunc<SFDF:mode><QHI:mode>2):
	Convert from define_expand to be define_insn_and_split.  Rework
	float/double/_Float128 conversions to QI/HI/SImode to work with
	both ISA 2.07 (power8) or ISA 3.0 (power9).  Fix regression where
	conversions to QI/HImode types did a store and then a load to
	truncate the value.  For conversions to VSX registers, don't split
	the insn, instead emit the code directly.  Use the code iterator
	any_fix to combine signed and unsigned conversions.
	(fix<uns>_trunc<SFDF:mode>si2_p8): Likewise.
	(fixuns_trunc<SFDF:mode><QHI:mode>2): Likewise.
	(fix_trunc<IEEE128:mode><QHI:mode>2): Likewise.
	(fix<uns>_trunc<SFDF:mode><QHI:mode>2): Likewise.
	(fix_<mode>di2_hw): Likewise.
	(fixuns_<mode>di2_hw): Likewise.
	(fix_<mode>si2_hw): Likewise.
	(fixuns_<mode>si2_hw): Likewise.
	(fix<uns>_<IEEE128:mode><SDI:mode>2_hw): Likewise.
	(fix<uns>_trunc<IEEE128:mode><QHI:mode>2): Likewise.
	(fctiw<u>z_<mode>_smallint): Rename fctiw<u>z_<mode>_smallint to
	fix<uns>_trunc<SFDF:mode>si2_p8.
	(fix_trunc<SFDF:mode><QHI:mode>2_internal): Delete, no longer
	used.
	(fixuns_trunc<SFDF:mode><QHI:mode>2_internal): Likewise.
	(fix<uns>_<mode>_mem): Likewise.
	(fctiw<u>z_<mode>_mem): Likewise.
	(fix<uns>_<mode>_mem): Likewise.
	(fix<uns>_trunc<SFDF:mode><QHSI:mode>2_mem): On ISA 3.0, prevent
	the register allocator from doing a direct move to the GPRs to do
	a store, and instead use the ISA 3.0 store byte/half-word from
	vector register instruction.  For IEEE 128-bit floating point,
	also optimize stores of 32-bit ints.
	(fix<uns>_trunc<IEEE128:mode><QHSI:mode>2_mem): Likewise.

[gcc/testsuite]
2018-02-07  Michael Meissner  <meissner@linux.vnet.ibm.com>

	PR target/84154
	* gcc.target/powerpc/pr84154-1.c: New tests.
	* gcc.target/powerpc/pr84154-2.c: Likewise.
	* gcc.target/powerpc/pr84154-3.c: Likewise.

From-SVN: r257470
This commit is contained in:
Michael Meissner 2018-02-07 22:54:59 +00:00 committed by Michael Meissner
parent 54af445d3c
commit 4253435eca
6 changed files with 293 additions and 130 deletions

View File

@ -1,3 +1,39 @@
2018-02-07 Michael Meissner <meissner@linux.vnet.ibm.com>
PR target/84154
* config/rs6000/rs6000.md (fix_trunc<SFDF:mode><QHI:mode>2):
Convert from define_expand to be define_insn_and_split. Rework
float/double/_Float128 conversions to QI/HI/SImode to work with
both ISA 2.07 (power8) or ISA 3.0 (power9). Fix regression where
conversions to QI/HImode types did a store and then a load to
truncate the value. For conversions to VSX registers, don't split
the insn, instead emit the code directly. Use the code iterator
any_fix to combine signed and unsigned conversions.
(fix<uns>_trunc<SFDF:mode>si2_p8): Likewise.
(fixuns_trunc<SFDF:mode><QHI:mode>2): Likewise.
(fix_trunc<IEEE128:mode><QHI:mode>2): Likewise.
(fix<uns>_trunc<SFDF:mode><QHI:mode>2): Likewise.
(fix_<mode>di2_hw): Likewise.
(fixuns_<mode>di2_hw): Likewise.
(fix_<mode>si2_hw): Likewise.
(fixuns_<mode>si2_hw): Likewise.
(fix<uns>_<IEEE128:mode><SDI:mode>2_hw): Likewise.
(fix<uns>_trunc<IEEE128:mode><QHI:mode>2): Likewise.
(fctiw<u>z_<mode>_smallint): Rename fctiw<u>z_<mode>_smallint to
fix<uns>_trunc<SFDF:mode>si2_p8.
(fix_trunc<SFDF:mode><QHI:mode>2_internal): Delete, no longer
used.
(fixuns_trunc<SFDF:mode><QHI:mode>2_internal): Likewise.
(fix<uns>_<mode>_mem): Likewise.
(fctiw<u>z_<mode>_mem): Likewise.
(fix<uns>_<mode>_mem): Likewise.
(fix<uns>_trunc<SFDF:mode><QHSI:mode>2_mem): On ISA 3.0, prevent
the register allocator from doing a direct move to the GPRs to do
a store, and instead use the ISA 3.0 store byte/half-word from
vector register instruction. For IEEE 128-bit floating point,
also optimize stores of 32-bit ints.
(fix<uns>_trunc<IEEE128:mode><QHSI:mode>2_mem): Likewise.
2018-02-07 Alan Hayward <alan.hayward@arm.com>
* genextract.c (push_pathstr_operand): New function to support

View File

@ -5700,43 +5700,59 @@
xscvdpsxds %x0,%x1"
[(set_attr "type" "fp")])
(define_expand "fix_trunc<SFDF:mode><QHI:mode>2"
[(parallel [(set (match_operand:<QHI:MODE> 0 "nonimmediate_operand")
(fix:QHI (match_operand:SFDF 1 "gpc_reg_operand")))
(clobber (match_scratch:DI 2))])]
"TARGET_P9_VECTOR && TARGET_DIRECT_MOVE_64BIT"
;; If we have ISA 3.0, QI/HImode values can go in both VSX registers and GPR
;; registers. If we have ISA 2.07, we don't allow QI/HImode values in the
;; vector registers, so we need to do direct moves to the GPRs, but SImode
;; values can go in VSX registers. Keeping the direct move part through
;; register allocation prevents the register allocator from doing a direct move
;; of the SImode value to a GPR, and then a store/load.
(define_insn_and_split "fix<uns>_trunc<SFDF:mode><QHI:mode>2"
[(set (match_operand:<QHI:MODE> 0 "gpc_reg_operand" "=wJ,wJwK,r")
(any_fix:QHI (match_operand:SFDF 1 "gpc_reg_operand" "wJ,wJwK,wa")))
(clobber (match_scratch:SI 2 "=X,X,wi"))]
"TARGET_DIRECT_MOVE"
"@
fctiw<u>z %0,%1
xscvdp<su>xws %x0,%x1
#"
"&& reload_completed && int_reg_operand (operands[0], <QHI:MODE>mode)"
[(set (match_dup 2)
(any_fix:SI (match_dup 1)))
(set (match_dup 3)
(match_dup 2))]
{
if (MEM_P (operands[0]))
operands[0] = rs6000_address_for_fpconvert (operands[0]);
})
operands[3] = gen_rtx_REG (SImode, REGNO (operands[0]));
}
[(set_attr "length" "4,4,8")
(set_attr "type" "fp")])
(define_insn_and_split "*fix_trunc<SFDF:mode><QHI:mode>2_internal"
[(set (match_operand:<QHI:MODE> 0 "reg_or_indexed_operand" "=wIwJ,rZ")
(fix:QHI
(match_operand:SFDF 1 "gpc_reg_operand" "<SFDF:Fv>,<SFDF:Fv>")))
(clobber (match_scratch:DI 2 "=X,wi"))]
"TARGET_P9_VECTOR && TARGET_DIRECT_MOVE_64BIT"
(define_insn "*fix<uns>_trunc<SFDF:mode>si2_p8"
[(set (match_operand:SI 0 "gpc_reg_operand" "=d,wa")
(any_fix:SI (match_operand:SFDF 1 "gpc_reg_operand" "d,wa")))]
"TARGET_DIRECT_MOVE"
"@
fctiw<u>z %0,%1
xscvdp<su>xws %x0,%x1"
[(set_attr "type" "fp")])
;; Keep the convert and store together through register allocation to prevent
;; the register allocator from getting clever and doing a direct move to a GPR
;; and then store for reg+offset stores.
(define_insn_and_split "*fix<uns>_trunc<SFDF:mode><QHSI:mode>2_mem"
[(set (match_operand:QHSI 0 "memory_operand" "=Z")
(any_fix:QHSI (match_operand:SFDF 1 "gpc_reg_operand" "wa")))
(clobber (match_scratch:SI 2 "=wa"))]
"(<QHSI:MODE>mode == SImode && TARGET_P8_VECTOR) || TARGET_P9_VECTOR"
"#"
"&& reload_completed"
[(const_int 0)]
[(set (match_dup 2)
(any_fix:SI (match_dup 1)))
(set (match_dup 0)
(match_dup 3))]
{
rtx dest = operands[0];
rtx src = operands[1];
if (vsx_register_operand (dest, <QHI:MODE>mode))
{
rtx di_dest = gen_rtx_REG (DImode, REGNO (dest));
emit_insn (gen_fix_trunc<SFDF:mode>di2 (di_dest, src));
}
else
{
rtx tmp = operands[2];
rtx tmp2 = gen_rtx_REG (<QHI:MODE>mode, REGNO (tmp));
emit_insn (gen_fix_trunc<SFDF:mode>di2 (tmp, src));
emit_move_insn (dest, tmp2);
}
DONE;
operands[3] = (<QHSI:MODE>mode == SImode
? operands[2]
: gen_rtx_REG (<QHSI:MODE>mode, REGNO (operands[2])));
})
(define_expand "fixuns_trunc<mode>si2"
@ -5803,71 +5819,6 @@
xscvdpuxds %x0,%x1"
[(set_attr "type" "fp")])
(define_expand "fixuns_trunc<SFDF:mode><QHI:mode>2"
[(parallel [(set (match_operand:<QHI:MODE> 0 "nonimmediate_operand")
(unsigned_fix:QHI (match_operand:SFDF 1 "gpc_reg_operand")))
(clobber (match_scratch:DI 2))])]
"TARGET_P9_VECTOR && TARGET_DIRECT_MOVE_64BIT"
{
if (MEM_P (operands[0]))
operands[0] = rs6000_address_for_fpconvert (operands[0]);
})
(define_insn_and_split "*fixuns_trunc<SFDF:mode><QHI:mode>2_internal"
[(set (match_operand:<QHI:MODE> 0 "reg_or_indexed_operand" "=wIwJ,rZ")
(unsigned_fix:QHI
(match_operand:SFDF 1 "gpc_reg_operand" "<SFDF:Fv>,<SFDF:Fv>")))
(clobber (match_scratch:DI 2 "=X,wi"))]
"TARGET_P9_VECTOR && TARGET_DIRECT_MOVE_64BIT"
"#"
"&& reload_completed"
[(const_int 0)]
{
rtx dest = operands[0];
rtx src = operands[1];
if (vsx_register_operand (dest, <QHI:MODE>mode))
{
rtx di_dest = gen_rtx_REG (DImode, REGNO (dest));
emit_insn (gen_fixuns_trunc<SFDF:mode>di2 (di_dest, src));
}
else
{
rtx tmp = operands[2];
rtx tmp2 = gen_rtx_REG (<QHI:MODE>mode, REGNO (tmp));
emit_insn (gen_fixuns_trunc<SFDF:mode>di2 (tmp, src));
emit_move_insn (dest, tmp2);
}
DONE;
})
;; If -mvsx-small-integer, we can represent the FIX operation directly. On
;; older machines, we have to use an UNSPEC to produce a SImode and move it
;; to another location, since SImode is not allowed in vector registers.
(define_insn "*fctiw<u>z_<mode>_smallint"
[(set (match_operand:SI 0 "vsx_register_operand" "=d,wi")
(any_fix:SI (match_operand:SFDF 1 "gpc_reg_operand" "<Ff>,<Fv>")))]
"TARGET_HARD_FLOAT && TARGET_DOUBLE_FLOAT && TARGET_P8_VECTOR"
"@
fctiw<u>z %0,%1
xscvdp<su>xws %x0,%x1"
[(set_attr "type" "fp")])
;; Combiner pattern to prevent moving the result of converting a floating point
;; value to 32-bit integer to GPR in order to save it.
(define_insn_and_split "*fctiw<u>z_<mode>_mem"
[(set (match_operand:SI 0 "memory_operand" "=Z")
(any_fix:SI (match_operand:SFDF 1 "gpc_reg_operand" "wa")))
(clobber (match_scratch:SI 2 "=wa"))]
"TARGET_HARD_FLOAT && TARGET_DOUBLE_FLOAT && TARGET_P8_VECTOR"
"#"
"&& reload_completed"
[(set (match_dup 2)
(any_fix:SI (match_dup 1)))
(set (match_dup 0)
(match_dup 2))])
;; Here, we use (set (reg) (unspec:DI [(fix:SI ...)] UNSPEC_FCTIWZ))
;; rather than (set (subreg:SI (reg)) (fix:SI ...))
;; because the first makes it clear that operand 0 is not live
@ -14362,49 +14313,45 @@
(set_attr "length" "8")])
;; Conversion between IEEE 128-bit and integer types
(define_insn "fix_<mode>di2_hw"
[(set (match_operand:DI 0 "altivec_register_operand" "=v")
(fix:DI (match_operand:IEEE128 1 "altivec_register_operand" "v")))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<MODE>mode)"
"xscvqpsdz %0,%1"
;; The fix function for DImode and SImode was declared earlier as a
;; define_expand. It calls into rs6000_expand_float128_convert if we don't
;; have IEEE 128-bit hardware support. QImode and HImode are not provided
;; unless we have the IEEE 128-bit hardware.
;;
;; Unlike the code for converting SFmode/DFmode to QImode/HImode, we don't have
;; to provide a GPR target that used direct move and a conversion in the GPR
;; which works around QImode/HImode not being allowed in vector registers in
;; ISA 2.07 (power8).
(define_insn "fix<uns>_<IEEE128:mode><SDI:mode>2_hw"
[(set (match_operand:SDI 0 "altivec_register_operand" "=v")
(any_fix:SDI (match_operand:IEEE128 1 "altivec_register_operand" "v")))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<IEEE128:MODE>mode)"
"xscvqp<su><wd>z %0,%1"
[(set_attr "type" "vecfloat")
(set_attr "size" "128")])
(define_insn "fixuns_<mode>di2_hw"
[(set (match_operand:DI 0 "altivec_register_operand" "=v")
(unsigned_fix:DI (match_operand:IEEE128 1 "altivec_register_operand" "v")))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<MODE>mode)"
"xscvqpudz %0,%1"
(define_insn "fix<uns>_trunc<IEEE128:mode><QHI:mode>2"
[(set (match_operand:QHI 0 "altivec_register_operand" "=v")
(any_fix:QHI
(match_operand:IEEE128 1 "altivec_register_operand" "v")))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<IEEE128:MODE>mode)"
"xscvqp<su>wz %0,%1"
[(set_attr "type" "vecfloat")
(set_attr "size" "128")])
(define_insn "fix_<mode>si2_hw"
[(set (match_operand:SI 0 "altivec_register_operand" "=v")
(fix:SI (match_operand:IEEE128 1 "altivec_register_operand" "v")))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<MODE>mode)"
"xscvqpswz %0,%1"
[(set_attr "type" "vecfloat")
(set_attr "size" "128")])
(define_insn "fixuns_<mode>si2_hw"
[(set (match_operand:SI 0 "altivec_register_operand" "=v")
(unsigned_fix:SI (match_operand:IEEE128 1 "altivec_register_operand" "v")))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<MODE>mode)"
"xscvqpuwz %0,%1"
[(set_attr "type" "vecfloat")
(set_attr "size" "128")])
;; Combiner pattern to prevent moving the result of converting an IEEE 128-bit
;; floating point value to 32-bit integer to GPR in order to save it.
(define_insn_and_split "*fix<uns>_<mode>_mem"
[(set (match_operand:SI 0 "memory_operand" "=Z")
(any_fix:SI (match_operand:IEEE128 1 "altivec_register_operand" "v")))
(clobber (match_scratch:SI 2 "=v"))]
;; Combiner patterns to prevent moving the result of converting an IEEE 128-bit
;; floating point value to 8/16/32-bit integer to GPR in order to save it.
(define_insn_and_split "*fix<uns>_trunc<IEEE128:mode><QHSI:mode>2_mem"
[(set (match_operand:QHSI 0 "memory_operand" "=Z")
(any_fix:QHSI
(match_operand:IEEE128 1 "altivec_register_operand" "v")))
(clobber (match_scratch:QHSI 2 "=v"))]
"TARGET_FLOAT128_HW && FLOAT128_IEEE_P (<MODE>mode)"
"#"
"&& reload_completed"
[(set (match_dup 2)
(any_fix:SI (match_dup 1)))
(any_fix:QHSI (match_dup 1)))
(set (match_dup 0)
(match_dup 2))])

View File

@ -1,3 +1,10 @@
2018-02-07 Michael Meissner <meissner@linux.vnet.ibm.com>
PR target/84154
* gcc.target/powerpc/pr84154-1.c: New tests.
* gcc.target/powerpc/pr84154-2.c: Likewise.
* gcc.target/powerpc/pr84154-3.c: Likewise.
2018-02-07 Will Schmidt <will_schmidt@vnet.ibm.com>
* gcc.target/powerpc/builtins-mergew-mergeow.c: Update dg-requires.

View File

@ -0,0 +1,55 @@
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "" { powerpc*-*-darwin* } } */
/* { dg-require-effective-target powerpc_p8vector_ok } */
/* { dg-options "-mpower8-vector -O2" } */
/* PR target/84154. Make sure conversion to char/short does not generate a
store and a load on ISA 2.07 and newer systems. */
unsigned char
double_to_uc (double x)
{
return x;
}
signed char
double_to_sc (double x)
{
return x;
}
unsigned short
double_to_us (double x)
{
return x;
}
short
double_to_ss (double x)
{
return x;
}
unsigned int
double_to_ui (double x)
{
return x;
}
int
double_to_si (double x)
{
return x;
}
/* { dg-final { scan-assembler-times {\mextsb\M} 1 } } */
/* { dg-final { scan-assembler-times {\mextsh\M} 1 } } */
/* { dg-final { scan-assembler-times {\mfctiwuz\M|\mxscvdpuxws\M} 3 } } */
/* { dg-final { scan-assembler-times {\mfctiwz\M|\mxscvdpsxws\M} 3 } } */
/* { dg-final { scan-assembler-times {\mmfvsrwz\M} 6 } } */
/* { dg-final { scan-assembler-times {\mrlwinm\M} 2 } } */
/* { dg-final { scan-assembler-not {\mlbz\M} } } */
/* { dg-final { scan-assembler-not {\mlhz\M} } } */
/* { dg-final { scan-assembler-not {\mlha\M} } } */
/* { dg-final { scan-assembler-not {\mmfvsrd\M} } } */
/* { dg-final { scan-assembler-not {\mstw\M} } } */

View File

@ -0,0 +1,58 @@
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "" { powerpc*-*-darwin* } } */
/* { dg-require-effective-target powerpc_p8vector_ok } */
/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
/* { dg-options "-mcpu=power8 -O2" } */
/* PR target/84154. Make sure on ISA 2.07 (power8) that we store the result of
a conversion to char/short using an offsettable address does not generate
direct moves for storing 32-bit integers, but does do a direct move for
8/16-bit integers. */
void
double_to_uc (double x, unsigned char *p)
{
p[3] = x;
}
void
double_to_sc (double x, signed char *p)
{
p[3] = x;
}
void
double_to_us (double x, unsigned short *p)
{
p[3] = x;
}
void
double_to_ss (double x, short *p)
{
p[3] = x;
}
void
double_to_ui (double x, unsigned int *p)
{
p[3] = x;
}
void
double_to_si (double x, int *p)
{
p[3] = x;
}
/* { dg-final { scan-assembler-times {\mfctiwuz\M|\mxscvdpuxws\M} 3 } } */
/* { dg-final { scan-assembler-times {\mfctiwz\M|\mxscvdpsxws\M} 3 } } */
/* { dg-final { scan-assembler-times {\mmfvsrwz\M} 4 } } */
/* { dg-final { scan-assembler-times {\mstfiwx\M|\mstxsiwx\M} 2 } } */
/* { dg-final { scan-assembler-times {\mstb\M} 2 } } */
/* { dg-final { scan-assembler-times {\msth\M} 2 } } */
/* { dg-final { scan-assembler-not {\mlbz\M} } } */
/* { dg-final { scan-assembler-not {\mlhz\M} } } */
/* { dg-final { scan-assembler-not {\mlha\M} } } */
/* { dg-final { scan-assembler-not {\mmfvsrd\M} } } */
/* { dg-final { scan-assembler-not {\mstw\M} } } */

View File

@ -0,0 +1,60 @@
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "" { powerpc*-*-darwin* } } */
/* { dg-require-effective-target powerpc_p9vector_ok } */
/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
/* { dg-options "-mcpu=power9 -O2" } */
/* PR target/84154. Make sure on ISA 3.0 we store the result of a conversion
to char/short using an offsettable address does not generate direct moves
for storing 8/16/32-bit integers. */
void
double_to_uc (double x, unsigned char *p)
{
p[3] = x;
}
void
double_to_sc (double x, signed char *p)
{
p[3] = x;
}
void
double_to_us (double x, unsigned short *p)
{
p[3] = x;
}
void
double_to_ss (double x, short *p)
{
p[3] = x;
}
void
double_to_ui (double x, unsigned int *p)
{
p[3] = x;
}
void
double_to_si (double x, int *p)
{
p[3] = x;
}
/* { dg-final { scan-assembler-times {\maddi\M} 6 } } */
/* { dg-final { scan-assembler-times {\mfctiwuz\M|\mxscvdpuxws\M} 3 } } */
/* { dg-final { scan-assembler-times {\mfctiwz\M|\mxscvdpsxws\M} 3 } } */
/* { dg-final { scan-assembler-times {\mstfiwx\M|\mstxsiwx\M} 2 } } */
/* { dg-final { scan-assembler-times {\mstxsibx\M} 2 } } */
/* { dg-final { scan-assembler-times {\mstxsihx\M} 2 } } */
/* { dg-final { scan-assembler-not {\mlbz\M} } } */
/* { dg-final { scan-assembler-not {\mlhz\M} } } */
/* { dg-final { scan-assembler-not {\mlha\M} } } */
/* { dg-final { scan-assembler-not {\mmfvsrwz\M} } } */
/* { dg-final { scan-assembler-not {\mmfvsrd\M} } } */
/* { dg-final { scan-assembler-not {\mstw\M} } } */
/* { dg-final { scan-assembler-not {\mstb\M} } } */
/* { dg-final { scan-assembler-not {\msth\M} } } */