mirror of git://gcc.gnu.org/git/gcc.git
s390: Optimize fmin/fmax.
On VXE targets, we can directly use the fp min/max instruction instead of calling into libm for fmin/fmax etc. Provide fmin/fmax versions also for vectors even though it cannot be called directly. This will be exploited with a follow-up patch when reductions are introduced. gcc/ChangeLog: * config/s390/s390.md: Update UNSPECs * config/s390/vector.md (fmax<mode>3): New expander. (fmin<mode>3): New expander. * config/s390/vx-builtins.md (*fmin<mode>): New insn. (vfmin<mode>): Redefined to use new insn. (*fmax<mode>): New insn. (vfmax<mode>): Redefined to use new insn. gcc/testsuite/ChangeLog: * gcc.target/s390/fminmax-1.c: New test. * gcc.target/s390/fminmax-2.c: New test. Signed-off-by: Juergen Christ <jchrist@linux.ibm.com>
This commit is contained in:
parent
4b9f760c51
commit
c476f554e3
|
@ -238,9 +238,6 @@
|
|||
|
||||
UNSPEC_VEC_MSUM
|
||||
|
||||
UNSPEC_VEC_VFMIN
|
||||
UNSPEC_VEC_VFMAX
|
||||
|
||||
UNSPEC_VEC_VBLEND
|
||||
UNSPEC_VEC_VEVAL
|
||||
UNSPEC_VEC_VGEM
|
||||
|
@ -253,6 +250,9 @@
|
|||
|
||||
UNSPEC_NNPA_VCFN_V8HI
|
||||
UNSPEC_NNPA_VCNF_V8HI
|
||||
|
||||
UNSPEC_FMAX
|
||||
UNSPEC_FMIN
|
||||
])
|
||||
|
||||
;;
|
||||
|
|
|
@ -89,6 +89,13 @@
|
|||
(define_mode_iterator VF_HW [(V4SF "TARGET_VXE") V2DF (V1TF "TARGET_VXE")
|
||||
(TF "TARGET_VXE")])
|
||||
|
||||
; FP scalar and vector modes
|
||||
(define_mode_iterator VFT_BFP [SF DF
|
||||
(V1SF "TARGET_VXE") (V2SF "TARGET_VXE") (V4SF "TARGET_VXE")
|
||||
V1DF V2DF
|
||||
(V1TF "TARGET_VXE") (TF "TARGET_VXE")])
|
||||
|
||||
|
||||
(define_mode_iterator V_8 [V1QI])
|
||||
(define_mode_iterator V_16 [V2QI V1HI])
|
||||
(define_mode_iterator V_32 [V4QI V2HI V1SI V1SF])
|
||||
|
@ -3602,3 +3609,21 @@
|
|||
(umul_highpart:VIT_HW_VXE3_DT (match_operand:VIT_HW_VXE3_DT 1 "register_operand")
|
||||
(match_operand:VIT_HW_VXE3_DT 2 "register_operand")))]
|
||||
"TARGET_VX")
|
||||
|
||||
; fmax
|
||||
(define_expand "fmax<mode>3"
|
||||
[(set (match_operand:VFT_BFP 0 "register_operand")
|
||||
(unspec:VFT_BFP [(match_operand:VFT_BFP 1 "register_operand")
|
||||
(match_operand:VFT_BFP 2 "register_operand")
|
||||
(const_int 4)]
|
||||
UNSPEC_FMAX))]
|
||||
"TARGET_VXE")
|
||||
|
||||
; fmin
|
||||
(define_expand "fmin<mode>3"
|
||||
[(set (match_operand:VFT_BFP 0 "register_operand")
|
||||
(unspec:VFT_BFP [(match_operand:VFT_BFP 1 "register_operand")
|
||||
(match_operand:VFT_BFP 2 "register_operand")
|
||||
(const_int 4)]
|
||||
UNSPEC_FMIN))]
|
||||
"TARGET_VXE")
|
||||
|
|
|
@ -2134,23 +2134,22 @@
|
|||
"<vw>fche<sdx>bs\t%v2,%v0,%v1"
|
||||
[(set_attr "op_type" "VRR")])
|
||||
|
||||
|
||||
(define_insn "vfmin<mode>"
|
||||
[(set (match_operand:VF_HW 0 "register_operand" "=v")
|
||||
(unspec:VF_HW [(match_operand:VF_HW 1 "register_operand" "v")
|
||||
(match_operand:VF_HW 2 "register_operand" "v")
|
||||
(match_operand:QI 3 "const_mask_operand" "C")]
|
||||
UNSPEC_VEC_VFMIN))]
|
||||
[(set (match_operand:VFT_BFP 0 "register_operand" "=v")
|
||||
(unspec:VFT_BFP [(match_operand:VFT_BFP 1 "register_operand" "v")
|
||||
(match_operand:VFT_BFP 2 "register_operand" "v")
|
||||
(match_operand:QI 3 "const_mask_operand" "C")]
|
||||
UNSPEC_FMIN))]
|
||||
"TARGET_VXE"
|
||||
"<vw>fmin<sdx>b\t%v0,%v1,%v2,%b3"
|
||||
[(set_attr "op_type" "VRR")])
|
||||
|
||||
(define_insn "vfmax<mode>"
|
||||
[(set (match_operand:VF_HW 0 "register_operand" "=v")
|
||||
(unspec:VF_HW [(match_operand:VF_HW 1 "register_operand" "v")
|
||||
(match_operand:VF_HW 2 "register_operand" "v")
|
||||
(match_operand:QI 3 "const_mask_operand" "C")]
|
||||
UNSPEC_VEC_VFMAX))]
|
||||
[(set (match_operand:VFT_BFP 0 "register_operand" "=v")
|
||||
(unspec:VFT_BFP [(match_operand:VFT_BFP 1 "register_operand" "v")
|
||||
(match_operand:VFT_BFP 2 "register_operand" "v")
|
||||
(match_operand:QI 3 "const_mask_operand" "C")]
|
||||
UNSPEC_FMAX))]
|
||||
"TARGET_VXE"
|
||||
"<vw>fmax<sdx>b\t%v0,%v1,%v2,%b3"
|
||||
[(set_attr "op_type" "VRR")])
|
||||
|
|
|
@ -0,0 +1,77 @@
|
|||
/* Check fmin/fmax expanders for scalars on VXE targets. */
|
||||
|
||||
/* { dg-do compile } */
|
||||
/* { dg-options "-O2 -march=z14 -mzarch" } */
|
||||
/* { dg-final { check-function-bodies "**" "" } } */
|
||||
|
||||
/*
|
||||
** dofmaxl:
|
||||
** vl (%v.),0\(%r3\),3
|
||||
** vl (%v.),0\(%r4\),3
|
||||
** wfmaxxb (%v.),\1,\2,4
|
||||
** vst \3,0\(%r2\),3
|
||||
** br %r14
|
||||
*/
|
||||
long double
|
||||
dofmaxl (long double d1, long double d2)
|
||||
{
|
||||
return __builtin_fmaxl (d1, d2);
|
||||
}
|
||||
|
||||
/*
|
||||
** dofminl:
|
||||
** vl (%v.),0\(%r3\),3
|
||||
** vl (%v.),0\(%r4\),3
|
||||
** wfminxb (%v.),\1,\2,4
|
||||
** vst \3,0\(%r2\),3
|
||||
** br %r14
|
||||
*/
|
||||
long double
|
||||
dofminl (long double d1, long double d2)
|
||||
{
|
||||
return __builtin_fminl (d1, d2);
|
||||
}
|
||||
|
||||
/*
|
||||
** dofmax:
|
||||
** wfmaxdb %v0,%v0,%v2,4
|
||||
** br %r14
|
||||
*/
|
||||
double
|
||||
dofmax (double d1, double d2)
|
||||
{
|
||||
return __builtin_fmax (d1, d2);
|
||||
}
|
||||
|
||||
/*
|
||||
** dofmin:
|
||||
** wfmindb %v0,%v0,%v2,4
|
||||
** br %r14
|
||||
*/
|
||||
double
|
||||
dofmin (double d1, double d2)
|
||||
{
|
||||
return __builtin_fmin (d1, d2);
|
||||
}
|
||||
|
||||
/*
|
||||
** dofmaxf:
|
||||
** wfmaxsb %v0,%v0,%v2,4
|
||||
** br %r14
|
||||
*/
|
||||
float
|
||||
dofmaxf (float f1, float f2)
|
||||
{
|
||||
return __builtin_fmaxf (f1, f2);
|
||||
}
|
||||
|
||||
/*
|
||||
** dofminf:
|
||||
** wfminsb %v0,%v0,%v2,4
|
||||
** br %r14
|
||||
*/
|
||||
float
|
||||
dofminf (float f1, float f2)
|
||||
{
|
||||
return __builtin_fminf (f1, f2);
|
||||
}
|
|
@ -0,0 +1,29 @@
|
|||
/* Check fmin/fmax expanders for scalars on non-VXE targets. */
|
||||
|
||||
/* { dg-do compile } */
|
||||
/* { dg-options "-O2 -march=z13 -mzarch" } */
|
||||
/* { dg-final { scan-assembler-times "jg" 4 } } */
|
||||
|
||||
double
|
||||
dofmax (double d1, double d2)
|
||||
{
|
||||
return __builtin_fmax (d1, d2);
|
||||
}
|
||||
|
||||
double
|
||||
dofmin (double d1, double d2)
|
||||
{
|
||||
return __builtin_fmin (d1, d2);
|
||||
}
|
||||
|
||||
float
|
||||
dofmaxf (float f1, float f2)
|
||||
{
|
||||
return __builtin_fmaxf (f1, f2);
|
||||
}
|
||||
|
||||
float
|
||||
dofminf (float f1, float f2)
|
||||
{
|
||||
return __builtin_fminf (f1, f2);
|
||||
}
|
Loading…
Reference in New Issue