Some architectures, as it the case on RISC-V with the proposed
ZiCondOps and the vendor-defined XVentanaCondOps, define a
conditional-zero instruction that is equivalent to:
- the positive form: rd = (rc != 0) ? rs : 0
- the negated form: rd = (rc == 0) ? rs : 0
While noce_try_store_flag_mask will somewhat work for this case, it
will generate a number of atomic RTX that will misdirect the cost
calculation and may be too long (i.e., 4 RTX and more) to successfully
merge at combine-time.
Instead, we add two new transforms that attempt to build up what we
define as the canonical form of a conditional-zero expression:
(set (match_operand 0 "register_operand" "=r")
(and (neg (eq_or_ne (match_operand 1 "register_operand" "r")
(const_int 0)))
(match_operand 2 "register_operand" "r")))
Architectures that provide a conditional-zero are thus expected to
define an instruction matching this pattern in their backend.
Based on this, we support the following cases:
- noce_try_condzero:
a ? a : b
a ? b : 0 (and then/else swapped)
!a ? b : 0 (and then/else swapped)
- noce_try_condzero_arith:
conditional-plus, conditional-minus, conditional-and,
conditional-or, conditional-xor, conditional-shift,
conditional-and
Given that this is hooked into the CE passes, it is less powerful than
a tree-pass (e.g., it can not transform cases where an extension, such
as for uint16_t operations is in either the then or else-branch
together with the arithmetic) but already covers a good array of cases
and triggers across SPEC CPU 2017.
Adding transofmrations in a tree pass will be considered as a future
improvement.
gcc/ChangeLog:
* ifcvt.cc (noce_emit_insn): Add prototype.
(noce_emit_condzero): Helper for noce_try_condzero and
noce_try_condzero_arith transforms.
(noce_try_condzero): New transform.
(noce_try_condzero_arith): New transform for conditional
arithmetic that can be built up by exploiting that the
conditional-zero instruction will inject 0, which acts
as the neutral element for operations.
(noce_process_if_block): Call noce_try_condzero and
noce_try_condzero_arith.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/xventanacondops-and-01.c: New test.
* gcc.target/riscv/xventanacondops-and-02.c: New test.
* gcc.target/riscv/xventanacondops-eq-01.c: New test.
* gcc.target/riscv/xventanacondops-eq-02.c: New test.
* gcc.target/riscv/xventanacondops-lt-01.c: New test.
* gcc.target/riscv/xventanacondops-ne-01.c: New test.
* gcc.target/riscv/xventanacondops-xor-01.c: New test.
Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
---
Changes in v2:
- Ran whitespace-cleanup on xventanacondops-ne-01.c.
gcc/ifcvt.cc | 214 ++++++++++++++++++
.../gcc.target/riscv/xventanacondops-and-01.c | 16 ++
.../gcc.target/riscv/xventanacondops-and-02.c | 15 ++
.../gcc.target/riscv/xventanacondops-eq-01.c | 11 +
.../gcc.target/riscv/xventanacondops-eq-02.c | 14 ++
.../gcc.target/riscv/xventanacondops-lt-01.c | 16 ++
.../gcc.target/riscv/xventanacondops-ne-01.c | 10 +
.../gcc.target/riscv/xventanacondops-xor-01.c | 14 ++
8 files changed, 310 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-and-01.c
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-and-02.c
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-eq-01.c
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-eq-02.c
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-lt-01.c
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-ne-01.c
create mode 100644 gcc/testsuite/gcc.target/riscv/xventanacondops-xor-01.c
@@ -97,6 +97,7 @@ static int find_if_case_2 (basic_block, edge, edge);
static int dead_or_predicable (basic_block, basic_block, basic_block,
edge, int);
static void noce_emit_move_insn (rtx, rtx);
+static rtx_insn *noce_emit_insn (rtx);
static rtx_insn *block_has_only_trap (basic_block);
static void need_cmov_or_rewire (basic_block, hash_set<rtx_insn *> *,
hash_map<rtx_insn *, int> *);
@@ -787,6 +788,9 @@ static rtx noce_get_alt_condition (struct noce_if_info *, rtx, rtx_insn **);
static int noce_try_minmax (struct noce_if_info *);
static int noce_try_abs (struct noce_if_info *);
static int noce_try_sign_mask (struct noce_if_info *);
+static rtx noce_emit_condzero (struct noce_if_info *, rtx, bool = false);
+static int noce_try_condzero (struct noce_if_info *);
+static int noce_try_condzero_arith (struct noce_if_info *);
/* Return the comparison code for reversed condition for IF_INFO,
or UNKNOWN if reversing the condition is not possible. */
@@ -1664,6 +1668,212 @@ noce_try_addcc (struct noce_if_info *if_info)
return FALSE;
}
+/* Helper to noce_try_condzero: cond ? a : 0. */
+static rtx
+noce_emit_condzero (struct noce_if_info *if_info, rtx a, bool reverse)
+{
+ /* The canonical form for a conditional-zero-or-value is:
+ (set (match_operand 0 "register_operand" "=r")
+ (and (neg (eq_or_ne (match_operand 1 "register_operand" "r")
+ (const_int 0)))
+ (match_operand 2 "register_operand" "r")))
+ */
+
+ machine_mode opmode = GET_MODE (if_info->x);
+ enum rtx_code code = GET_CODE (if_info->cond);
+ rtx cond;
+ rtx op_a = XEXP (if_info->cond, 0);
+ rtx op_b = XEXP (if_info->cond, 1);
+
+ /* If it is not a EQ/NE comparison against const0_rtx, canonicalize
+ by first synthesizing a truth-value and then building a NE
+ condition around it. */
+ if ((code != EQ && code != NE) || XEXP (if_info->cond, 1) != const0_rtx)
+ {
+ rtx tmp = gen_reg_rtx (opmode);
+
+ start_sequence ();
+ cond = gen_rtx_fmt_ee (code, opmode, op_a, op_b);
+ if (!noce_emit_insn (gen_rtx_SET (tmp, cond)))
+ {
+ end_sequence ();
+
+ /* If we can't emit this pattern, try to reverse it and
+ invert the polarity of the second test. */
+ start_sequence ();
+ cond = gen_rtx_fmt_ee (reverse_condition (code), opmode, op_a, op_b);
+ if (!noce_emit_insn (gen_rtx_SET (tmp, cond))) {
+ end_sequence ();
+ return NULL_RTX;
+ }
+
+ /* We have recovered by reversing the first comparison,
+ so we need change the second one around as well... */
+ reverse = !reverse;
+ }
+ rtx_insn *seq = get_insns ();
+ end_sequence ();
+ emit_insn (seq);
+
+ /* Set up the second comparison that will be embedded in the
+ canonical conditional-zero-or-value RTX. */
+ code = NE;
+ op_a = tmp;
+ op_b = const0_rtx;
+ }
+
+ cond = gen_rtx_fmt_ee (reverse ? reverse_condition (code) : code,
+ opmode, op_a, op_b);
+
+ /* Build (and (neg (eq_or_ne ... const0_rtx)) (reg <a>)) */
+ rtx target = gen_reg_rtx (opmode);
+ rtx czero = gen_rtx_AND (opmode, gen_rtx_NEG (opmode, cond), a);
+ noce_emit_move_insn (target, czero);
+
+ return target;
+}
+
+/* Use a conditional-zero instruction for "if (test) x = 0;", if available. */
+static int
+noce_try_condzero (struct noce_if_info *if_info)
+{
+ rtx target;
+ rtx_insn *seq;
+ int reversep = 0;
+ rtx orig_b = NULL_RTX;
+ rtx cond = if_info->cond;
+ enum rtx_code code = GET_CODE (cond);
+ rtx cond_arg0 = XEXP (cond, 0);
+ rtx cond_arg1 = XEXP (cond, 1);
+
+ if (!noce_simple_bbs (if_info))
+ return FALSE;
+
+ /* We may encounter the form "(a != 0) ? a : b", which can be
+ simplified to "a | ((a != 0) ? 0 : b)". */
+ if (code == NE && cond_arg1 == const0_rtx &&
+ REG_P (if_info->b) && rtx_equal_p (if_info->b, cond_arg0))
+ {
+ orig_b = if_info->b;
+ if_info->b = const0_rtx;
+ }
+
+ /* We may encounter the form "(a != 0) ? b : a", which can be
+ simplied to "(a != 0) ? b : 0". */
+ if (code == EQ && cond_arg1 == const0_rtx &&
+ REG_P (if_info->b) && rtx_equal_p (if_info->b, cond_arg0))
+ {
+ /* We know that cond_arg0 is const_0, if the THEN branch is
+ taken... so if it is the same as if_info->b (yes, things are
+ backwards!), we can rewrite it with that knowledge. */
+ if_info->b = const0_rtx;
+ }
+
+ start_sequence ();
+
+ if ((if_info->a == const0_rtx
+ && (REG_P (if_info->b) || rtx_equal_p (if_info->b, if_info->x)))
+ || ((reversep = (noce_reversed_cond_code (if_info) != UNKNOWN))
+ && if_info->b == const0_rtx
+ && (REG_P (if_info->a) || rtx_equal_p (if_info->a, if_info->x))))
+ {
+ target = noce_emit_condzero(if_info,
+ reversep ? if_info->a : if_info->b,
+ reversep);
+
+ if (orig_b && target)
+ target = expand_simple_binop (GET_MODE (if_info->x), IOR, orig_b,
+ target, if_info->x, 0, OPTAB_WIDEN);
+
+ if (target)
+ {
+ if (target != if_info->x)
+ noce_emit_move_insn (if_info->x, target);
+
+ seq = end_ifcvt_sequence (if_info);
+ if (!seq || !targetm.noce_conversion_profitable_p (seq, if_info))
+ return FALSE;
+
+ emit_insn_before_setloc (seq, if_info->jump,
+ INSN_LOCATION (if_info->insn_a));
+ if_info->transform_name = "noce_try_condzero";
+
+ return TRUE;
+ }
+ }
+
+ end_sequence ();
+
+ return FALSE;
+}
+
+/* Convert "if (test) x op= a;" to a branchless sequence using the
+ canonical form for a conditional-zero. */
+static int
+noce_try_condzero_arith (struct noce_if_info *if_info)
+{
+ rtx target;
+ rtx_insn *seq;
+ rtx_code op = GET_CODE (if_info->a);
+ const rtx arg0 = XEXP (if_info->a, 0);
+ const rtx arg1 = XEXP (if_info->a, 1);
+
+ if (!noce_simple_bbs (if_info))
+ return FALSE;
+
+ /* Check for no else condition. */
+ if (!rtx_equal_p (if_info->x, if_info->b))
+ return FALSE;
+
+ if (op != PLUS && op != MINUS && op != IOR && op != XOR &&
+ op != ASHIFT && op != ASHIFTRT && op != LSHIFTRT && op != AND)
+ return FALSE;
+
+ if (!rtx_equal_p (if_info->x, arg0))
+ return FALSE;
+
+ start_sequence ();
+
+ target = noce_emit_condzero(if_info, arg1, op != AND ? true : false);
+
+ if (target)
+ {
+ rtx op1 = if_info->x;
+
+ if (op == AND)
+ {
+ /* Emit "tmp = x & val;" followed by "tmp |= !cond ? x : 0;" */
+ op1 = expand_simple_binop (GET_MODE (if_info->x), AND, op1,
+ arg1, NULL_RTX, 0, OPTAB_WIDEN);
+ op = IOR;
+ }
+
+ if (op1)
+ target = expand_simple_binop (GET_MODE (if_info->x), op, op1,
+ target, if_info->x, 0, OPTAB_WIDEN);
+ }
+
+ if (target)
+ {
+ if (target != if_info->x)
+ noce_emit_move_insn (if_info->x, target);
+
+ seq = end_ifcvt_sequence (if_info);
+ if (!seq || !targetm.noce_conversion_profitable_p (seq, if_info))
+ return FALSE;
+
+ emit_insn_before_setloc(seq, if_info->jump,
+ INSN_LOCATION(if_info->insn_a));
+ if_info->transform_name = "noce_try_condzero_arith";
+
+ return TRUE;
+ }
+
+ end_sequence ();
+
+ return FALSE;
+}
+
/* Convert "if (test) x = 0;" to "x &= -(test == 0);" */
static int
@@ -3967,8 +4177,12 @@ noce_process_if_block (struct noce_if_info *if_info)
{
if (noce_try_addcc (if_info))
goto success;
+ if (noce_try_condzero (if_info))
+ goto success;
if (noce_try_store_flag_mask (if_info))
goto success;
+ if (noce_try_condzero_arith (if_info))
+ goto success;
if (HAVE_conditional_move
&& noce_try_cmove_arith (if_info))
goto success;
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" "-Os" "-Oz" } } */
+
+long and1(long a, long b, long c, long d)
+{
+ if (c < d)
+ a &= b;
+
+ return a;
+}
+
+/* { dg-final { scan-assembler-times "and\t" 1 } } */
+/* { dg-final { scan-assembler-times "slt" 1 } } */
+/* { dg-final { scan-assembler-times "vt.maskcn" 1 } } */
+/* { dg-final { scan-assembler-times "or\t" 1 } } */
new file mode 100644
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" "-Os" "-Oz" } } */
+
+int and2(int a, int b, long c)
+{
+ if (c)
+ a &= b;
+
+ return a;
+}
+
+/* { dg-final { scan-assembler-times "and\t" 1 } } */
+/* { dg-final { scan-assembler-times "vt.maskcn" 1 } } */
+/* { dg-final { scan-assembler-times "or\t" 1 } } */
new file mode 100644
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" } } */
+
+long
+eq1 (long a, long b)
+{
+ return (a == 0) ? b : 0;
+}
+
+/* { dg-final { scan-assembler-times "vt.maskcn" 1 } } */
new file mode 100644
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" } } */
+
+long
+eq2 (long a, long b)
+{
+ if (a == 0)
+ return b;
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler-times "vt.maskcn" 1 } } */
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" "-Os" "-Oz" } } */
+
+long long sink (long long);
+
+long long lt3 (long long a, long long b)
+{
+ if (a < b)
+ b = 0;
+
+ return sink(b);
+}
+
+/* { dg-final { scan-assembler-times "vt.maskcn\" 1 } } */
+/* { dg-final { scan-assembler-times "slt\t" 1 } } */
new file mode 100644
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" } } */
+
+long long ne1(long long a, long long b)
+{
+ return (a != 0) ? b : 0;
+}
+
+/* { dg-final { scan-assembler-times "vt.maskc" 1 } } */
new file mode 100644
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_xventanacondops -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" "-Os" "-Oz" } } */
+
+long xor1(long crc, long poly)
+{
+ if (crc & 1)
+ crc ^= poly;
+
+ return crc;
+}
+
+/* { dg-final { scan-assembler-times "vt.maskc" 1 } } */
+/* { dg-final { scan-assembler-times "xor\t" 1 } } */