Update RTX costs to reflect better the ARC architecture.
Ok to apply?
Claudiu
gcc/
xxxx-xx-xx Claudiu Zissulescu <claz...@synopsys.com>
* config/arc/arc.c (arc_rtx_costs): Update costs.
/gcc/testsuite
xxxx-xx-xx Claudiu Zissulescu <claz...@synopsys.com>
* gcc.target/arc/jumptables.c: Update test.
---
gcc/config/arc/arc.c | 69 +++++++++++++-----------
gcc/testsuite/gcc.target/arc/jumptable.c | 2 +-
2 files changed, 40 insertions(+), 31 deletions(-)
diff --git a/gcc/config/arc/arc.c b/gcc/config/arc/arc.c
index f398c4a0086..20dfae66370 100644
--- a/gcc/config/arc/arc.c
+++ b/gcc/config/arc/arc.c
@@ -5569,41 +5569,39 @@ arc_rtx_costs (rtx x, machine_mode mode, int outer_code,
case CONST_INT:
{
bool nolimm = false; /* Can we do without long immediate? */
- bool fast = false; /* Is the result available immediately? */
- bool condexec = false; /* Does this allow conditiobnal execution? */
- bool compact = false; /* Is a 16 bit opcode available? */
- /* CONDEXEC also implies that we can have an unconditional
- 3-address operation. */
- nolimm = compact = condexec = false;
+ nolimm = false;
if (UNSIGNED_INT6 (INTVAL (x)))
- nolimm = condexec = compact = true;
+ nolimm = true;
else
{
- if (SMALL_INT (INTVAL (x)))
- nolimm = fast = true;
switch (outer_code)
{
case AND: /* bclr, bmsk, ext[bw] */
if (satisfies_constraint_Ccp (x) /* bclr */
|| satisfies_constraint_C1p (x) /* bmsk */)
- nolimm = fast = condexec = compact = true;
+ nolimm = true;
break;
case IOR: /* bset */
if (satisfies_constraint_C0p (x)) /* bset */
- nolimm = fast = condexec = compact = true;
+ nolimm = true;
break;
case XOR:
if (satisfies_constraint_C0p (x)) /* bxor */
- nolimm = fast = condexec = true;
+ nolimm = true;
break;
+ case SET:
+ if (UNSIGNED_INT8 (INTVAL (x)))
+ nolimm = true;
+ if (satisfies_constraint_Chi (x))
+ nolimm = true;
+ if (satisfies_constraint_Clo (x))
+ nolimm = true;
default:
break;
}
}
- /* FIXME: Add target options to attach a small cost if
- condexec / compact is not true. */
- if (nolimm)
+ if (nolimm && !speed)
{
*total = 0;
return true;
@@ -5616,7 +5614,7 @@ arc_rtx_costs (rtx x, machine_mode mode, int outer_code,
case CONST:
case LABEL_REF:
case SYMBOL_REF:
- *total = COSTS_N_INSNS (1);
+ *total = speed ? COSTS_N_INSNS (1) : COSTS_N_INSNS (4);
return true;
case CONST_DOUBLE:
@@ -5642,16 +5640,10 @@ arc_rtx_costs (rtx x, machine_mode mode, int outer_code,
case LSHIFTRT:
if (TARGET_BARREL_SHIFTER)
{
- /* If we want to shift a constant, we need a LIMM. */
- /* ??? when the optimizers want to know if a constant should be
- hoisted, they ask for the cost of the constant. OUTER_CODE is
- insufficient context for shifts since we don't know which operand
- we are looking at. */
if (CONSTANT_P (XEXP (x, 0)))
{
- *total += (COSTS_N_INSNS (2)
- + rtx_cost (XEXP (x, 1), mode, (enum rtx_code) code,
- 0, speed));
+ *total += rtx_cost (XEXP (x, 1), mode, (enum rtx_code) code,
+ 0, speed);
return true;
}
*total = COSTS_N_INSNS (1);
@@ -5671,7 +5663,13 @@ arc_rtx_costs (rtx x, machine_mode mode, int outer_code,
case DIV:
case UDIV:
- if (speed)
+ if (GET_MODE_CLASS (mode) == MODE_FLOAT
+ && (TARGET_FP_SP_SQRT || TARGET_FP_DP_SQRT))
+ *total = COSTS_N_INSNS(1);
+ else if (GET_MODE_CLASS (mode) == MODE_INT
+ && TARGET_DIVREM)
+ *total = COSTS_N_INSNS(1);
+ else if (speed)
*total = COSTS_N_INSNS(30);
else
*total = COSTS_N_INSNS(1);
@@ -5684,19 +5682,28 @@ arc_rtx_costs (rtx x, machine_mode mode, int outer_code,
*total= arc_multcost;
/* We do not want synth_mult sequences when optimizing
for size. */
- else if (TARGET_MUL64_SET || TARGET_ARC700_MPY)
+ else if (TARGET_ANY_MPY)
*total = COSTS_N_INSNS (1);
else
*total = COSTS_N_INSNS (2);
return false;
+
case PLUS:
+ if (outer_code == MEM && CONST_INT_P (XEXP (x, 1))
+ && RTX_OK_FOR_OFFSET_P (mode, XEXP (x, 1)))
+ {
+ *total = 0;
+ return true;
+ }
+
if ((GET_CODE (XEXP (x, 0)) == ASHIFT
&& _1_2_3_operand (XEXP (XEXP (x, 0), 1), VOIDmode))
|| (GET_CODE (XEXP (x, 0)) == MULT
&& _2_4_8_operand (XEXP (XEXP (x, 0), 1), VOIDmode)))
{
- *total += (rtx_cost (XEXP (x, 1), mode, PLUS, 0, speed)
- + rtx_cost (XEXP (XEXP (x, 0), 0), mode, PLUS, 1, speed));
+ if (CONSTANT_P (XEXP (x, 1)) && !speed)
+ *total += COSTS_N_INSNS (4);
+ *total += rtx_cost (XEXP (XEXP (x, 0), 0), mode, PLUS, 1, speed);
return true;
}
return false;
@@ -5706,11 +5713,13 @@ arc_rtx_costs (rtx x, machine_mode mode, int outer_code,
|| (GET_CODE (XEXP (x, 1)) == MULT
&& _2_4_8_operand (XEXP (XEXP (x, 1), 1), VOIDmode)))
{
- *total += (rtx_cost (XEXP (x, 0), mode, PLUS, 0, speed)
- + rtx_cost (XEXP (XEXP (x, 1), 0), mode, PLUS, 1, speed));
+ if (CONSTANT_P (XEXP (x, 0)) && !speed)
+ *total += COSTS_N_INSNS (4);
+ *total += rtx_cost (XEXP (XEXP (x, 1), 0), mode, PLUS, 1, speed);
return true;
}
return false;
+
case COMPARE:
{
rtx op0 = XEXP (x, 0);
diff --git a/gcc/testsuite/gcc.target/arc/jumptable.c
b/gcc/testsuite/gcc.target/arc/jumptable.c
index fbc58e33149..ffbcf93e164 100644
--- a/gcc/testsuite/gcc.target/arc/jumptable.c
+++ b/gcc/testsuite/gcc.target/arc/jumptable.c
@@ -31,4 +31,4 @@ int switchCase(int value, int b)
}
/* { dg-final { scan-assembler-times "bih" 1 } } */
-/* { dg-final { scan-assembler-times "b_s" 8 } } */
+/* { dg-final { scan-assembler-times "b_s" 6 } } */
--
2.21.0
