RISC-V: Implement the .SAT_TRUNC for scalar

This patch would like to implement the simple .SAT_TRUNC pattern
in the riscv backend. Aka:

Form 1:
  #define DEF_SAT_U_TRUC_FMT_1(NT, WT)     \
  NT __attribute__((noinline))             \
  sat_u_truc_##WT##_to_##NT##_fmt_1 (WT x) \
  {                                        \
    bool overflow = x > (WT)(NT)(-1);      \
    return ((NT)x) | (NT)-overflow;        \
  }

DEF_SAT_U_TRUC_FMT_1(uint32_t, uint64_t)

Before this patch:
__attribute__((noinline))
uint8_t sat_u_truc_uint16_t_to_uint8_t_fmt_1 (uint16_t x)
{
  _Bool overflow;
  unsigned char _1;
  unsigned char _2;
  unsigned char _3;
  uint8_t _6;

;;   basic block 2, loop depth 0
;;    pred:       ENTRY
  overflow_5 = x_4(D) > 255;
  _1 = (unsigned char) x_4(D);
  _2 = (unsigned char) overflow_5;
  _3 = -_2;
  _6 = _1 | _3;
  return _6;
;;    succ:       EXIT

}

After this patch:
__attribute__((noinline))
uint8_t sat_u_truc_uint16_t_to_uint8_t_fmt_1 (uint16_t x)
{
  uint8_t _6;

;;   basic block 2, loop depth 0
;;    pred:       ENTRY
  _6 = .SAT_TRUNC (x_4(D)); [tail call]
  return _6;
;;    succ:       EXIT

}

The below tests suites are passed for this patch
1. The rv64gcv fully regression test.
2. The rv64gcv build with glibc

gcc/ChangeLog:

	* config/riscv/iterators.md (ANYI_DOUBLE_TRUNC): Add new iterator
	for int double truncation.
	(ANYI_DOUBLE_TRUNCATED): Add new attr for int double truncation.
	(anyi_double_truncated): Ditto but for lowercase.
	* config/riscv/riscv-protos.h (riscv_expand_ustrunc): Add new
	func decl for expanding ustrunc
	* config/riscv/riscv.cc (riscv_expand_ustrunc): Add new func
	impl to expand ustrunc.
	* config/riscv/riscv.md (ustrunc<mode><anyi_double_truncated>2): Impl
	the new pattern ustrunc<m><n>2 for int.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/sat_arith.h: Add test helper macro.
	* gcc.target/riscv/sat_arith_data.h: New test.
	* gcc.target/riscv/sat_u_trunc-1.c: New test.
	* gcc.target/riscv/sat_u_trunc-2.c: New test.
	* gcc.target/riscv/sat_u_trunc-3.c: New test.
	* gcc.target/riscv/sat_u_trunc-run-1.c: New test.
	* gcc.target/riscv/sat_u_trunc-run-2.c: New test.
	* gcc.target/riscv/sat_u_trunc-run-3.c: New test.
	* gcc.target/riscv/scalar_sat_unary.h: New test.

Signed-off-by: Pan Li <pan2.li@intel.com>
This commit is contained in:
Pan Li 2024-07-01 16:36:35 +08:00
parent d1b25543f9
commit 5d2115b850
13 changed files with 259 additions and 0 deletions

View file

@ -65,6 +65,16 @@
;; Iterator for hardware-supported integer modes.
(define_mode_iterator ANYI [QI HI SI (DI "TARGET_64BIT")])
(define_mode_iterator ANYI_DOUBLE_TRUNC [HI SI (DI "TARGET_64BIT")])
(define_mode_attr ANYI_DOUBLE_TRUNCATED [
(HI "QI") (SI "HI") (DI "SI")
])
(define_mode_attr anyi_double_truncated [
(HI "qi") (SI "hi") (DI "si")
])
;; Iterator for hardware-supported floating-point modes.
(define_mode_iterator ANYF [(SF "TARGET_HARD_FLOAT || TARGET_ZFINX")
(DF "TARGET_DOUBLE_FLOAT || TARGET_ZDINX")

View file

@ -135,6 +135,7 @@ riscv_zcmp_valid_stack_adj_bytes_p (HOST_WIDE_INT, int);
extern void riscv_legitimize_poly_move (machine_mode, rtx, rtx, rtx);
extern void riscv_expand_usadd (rtx, rtx, rtx);
extern void riscv_expand_ussub (rtx, rtx, rtx);
extern void riscv_expand_ustrunc (rtx, rtx);
#ifdef RTX_CODE
extern void riscv_expand_int_scc (rtx, enum rtx_code, rtx, rtx, bool *invert_ptr = 0);

View file

@ -11636,6 +11636,46 @@ riscv_expand_ussub (rtx dest, rtx x, rtx y)
emit_move_insn (dest, gen_lowpart (mode, pmode_dest));
}
/* Implement the unsigned saturation truncation for int mode.
b = SAT_TRUNC (a);
=>
1. max = half truncated max
2. lt = a < max
3. lt = lt - 1 (lt 0, ge -1)
4. d = a | lt
5. b = (trunc)d */
void
riscv_expand_ustrunc (rtx dest, rtx src)
{
machine_mode mode = GET_MODE (dest);
rtx xmode_max = gen_reg_rtx (Xmode);
unsigned precision = GET_MODE_PRECISION (mode).to_constant ();
gcc_assert (precision < 64);
uint64_t max = ((uint64_t)1u << precision) - 1u;
rtx xmode_src = gen_lowpart (Xmode, src);
rtx xmode_dest = gen_reg_rtx (Xmode);
rtx xmode_lt = gen_reg_rtx (Xmode);
/* Step-1: max = half truncated max */
emit_move_insn (xmode_max, gen_int_mode (max, Xmode));
/* Step-2: lt = src < max */
riscv_emit_binary (LTU, xmode_lt, xmode_src, xmode_max);
/* Step-3: lt = lt - 1 */
riscv_emit_binary (PLUS, xmode_lt, xmode_lt, CONSTM1_RTX (Xmode));
/* Step-4: xmode_dest = lt | src */
riscv_emit_binary (IOR, xmode_dest, xmode_lt, xmode_src);
/* Step-5: dest = xmode_dest */
emit_move_insn (dest, gen_lowpart (mode, xmode_dest));
}
/* Implement TARGET_C_MODE_FOR_FLOATING_TYPE. Return TFmode for
TI_LONG_DOUBLE_TYPE which is for long double type, go with the
default one for the others. */

View file

@ -4315,6 +4315,16 @@
}
)
(define_expand "ustrunc<mode><anyi_double_truncated>2"
[(match_operand:<ANYI_DOUBLE_TRUNCATED> 0 "register_operand")
(match_operand:ANYI_DOUBLE_TRUNC 1 "register_operand")]
""
{
riscv_expand_ustrunc (operands[0], operands[1]);
DONE;
}
)
;; These are forms of (x << C1) + C2, potentially canonicalized from
;; ((x + C2') << C1. Depending on the cost to load C2 vs C2' we may
;; want to go ahead and recognize this form as C2 may be cheaper to

View file

@ -214,4 +214,20 @@ sat_u_sub_##T##_fmt_12 (T x, T y) \
#define RUN_SAT_U_SUB_FMT_11(T, x, y) sat_u_sub_##T##_fmt_11(x, y)
#define RUN_SAT_U_SUB_FMT_12(T, x, y) sat_u_sub_##T##_fmt_12(x, y)
/******************************************************************************/
/* Saturation Truncate (unsigned and signed) */
/******************************************************************************/
#define DEF_SAT_U_TRUC_FMT_1(NT, WT) \
NT __attribute__((noinline)) \
sat_u_truc_##WT##_to_##NT##_fmt_1 (WT x) \
{ \
bool overflow = x > (WT)(NT)(-1); \
return ((NT)x) | (NT)-overflow; \
}
#define DEF_SAT_U_TRUC_FMT_1_WRAP(NT, WT) DEF_SAT_U_TRUC_FMT_1(NT, WT)
#define RUN_SAT_U_TRUC_FMT_1(NT, WT, x) sat_u_truc_##WT##_to_##NT##_fmt_1 (x)
#define RUN_SAT_U_TRUC_FMT_1_WRAP(NT, WT, x) RUN_SAT_U_TRUC_FMT_1(NT, WT, x)
#endif

View file

@ -0,0 +1,56 @@
#ifndef HAVE_DEFINED_SAT_ARITH_DATA_H
#define HAVE_DEFINED_SAT_ARITH_DATA_H
#define TEST_UNARY_STRUCT_NAME(T1, T2) test_##T1##_##T2##_s
#define TEST_UNARY_STRUCT_DECL(T1, T2) struct TEST_UNARY_STRUCT_NAME(T1, T2)
#define TEST_UNARY_STRUCT(T1, T2) \
struct TEST_UNARY_STRUCT_NAME(T1, T2) \
{ \
T1 to; \
T2 from; \
};
#define TEST_UNARY_DATA(T1, T2) t_##T1##_##T2##_s
#define TEST_UNARY_DATA_WRAP(T1, T2) TEST_UNARY_DATA(T1, T2)
TEST_UNARY_STRUCT (uint8_t, uint16_t)
TEST_UNARY_STRUCT (uint16_t, uint32_t)
TEST_UNARY_STRUCT (uint32_t, uint64_t)
TEST_UNARY_STRUCT_DECL(uint8_t, uint16_t) \
TEST_UNARY_DATA(uint8_t, uint16_t)[] =
{
{ 0, 0},
{ 2, 2},
{254, 254},
{255, 255},
{255, 256},
{255, 65534},
{255, 65535},
};
TEST_UNARY_STRUCT_DECL(uint16_t, uint32_t) \
TEST_UNARY_DATA(uint16_t, uint32_t)[] =
{
{ 0, 0},
{ 5, 5},
{65534, 65534},
{65535, 65535},
{65535, 65536},
{65535, 4294967294},
{65535, 4294967295},
};
TEST_UNARY_STRUCT_DECL(uint32_t, uint64_t) \
TEST_UNARY_DATA(uint32_t, uint64_t)[] =
{
{ 0, 0},
{ 9, 9},
{4294967294, 4294967294},
{4294967295, 4294967295},
{4294967295, 4294967296},
{4294967295, 18446744073709551614u},
{4294967295, 18446744073709551615u},
};
#endif

View file

@ -0,0 +1,17 @@
/* { dg-do compile } */
/* { dg-options "-march=rv64gc -mabi=lp64d -O3 -fdump-rtl-expand-details -fno-schedule-insns -fno-schedule-insns2" } */
/* { dg-final { check-function-bodies "**" "" } } */
#include "sat_arith.h"
/*
** sat_u_truc_uint16_t_to_uint8_t_fmt_1:
** sltiu\s+[atx][0-9]+,\s*a0,\s*255
** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
** or\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
** andi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*0xff
** ret
*/
DEF_SAT_U_TRUC_FMT_1(uint8_t, uint16_t)
/* { dg-final { scan-rtl-dump-times ".SAT_TRUNC " 2 "expand" } } */

View file

@ -0,0 +1,20 @@
/* { dg-do compile } */
/* { dg-options "-march=rv64gc -mabi=lp64d -O3 -fdump-rtl-expand-details -fno-schedule-insns -fno-schedule-insns2" } */
/* { dg-final { check-function-bodies "**" "" } } */
#include "sat_arith.h"
/*
** sat_u_truc_uint32_t_to_uint16_t_fmt_1:
** li\s+[atx][0-9]+,\s*65536
** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
** sltu\s+[atx][0-9]+,\s*a0,\s*[atx][0-9]+
** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
** or\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
** slli\s+a0,\s*a0,\s*48
** srli\s+a0,\s*a0,\s*48
** ret
*/
DEF_SAT_U_TRUC_FMT_1(uint16_t, uint32_t)
/* { dg-final { scan-rtl-dump-times ".SAT_TRUNC " 2 "expand" } } */

View file

@ -0,0 +1,19 @@
/* { dg-do compile } */
/* { dg-options "-march=rv64gc -mabi=lp64d -O3 -fdump-rtl-expand-details -fno-schedule-insns -fno-schedule-insns2" } */
/* { dg-final { check-function-bodies "**" "" } } */
#include "sat_arith.h"
/*
** sat_u_truc_uint64_t_to_uint32_t_fmt_1:
** li\s+[atx][0-9]+,\s*-1
** srli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*32
** sltu\s+[atx][0-9]+,\s*a0,\s*[atx][0-9]+
** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
** or\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
** sext.w\s+a0,\s*a0
** ret
*/
DEF_SAT_U_TRUC_FMT_1(uint32_t, uint64_t)
/* { dg-final { scan-rtl-dump-times ".SAT_TRUNC " 2 "expand" } } */

View file

@ -0,0 +1,16 @@
/* { dg-do run { target { riscv_v } } } */
/* { dg-additional-options "-std=c99" } */
#include "sat_arith.h"
#include "sat_arith_data.h"
#define T1 uint8_t
#define T2 uint16_t
DEF_SAT_U_TRUC_FMT_1_WRAP(T1, T2)
#define DATA TEST_UNARY_DATA_WRAP(T1, T2)
#define T TEST_UNARY_STRUCT_DECL(T1, T2)
#define RUN_UNARY(x) RUN_SAT_U_TRUC_FMT_1_WRAP(T1, T2, x)
#include "scalar_sat_unary.h"

View file

@ -0,0 +1,16 @@
/* { dg-do run { target { riscv_v } } } */
/* { dg-additional-options "-std=c99" } */
#include "sat_arith.h"
#include "sat_arith_data.h"
#define T1 uint16_t
#define T2 uint32_t
DEF_SAT_U_TRUC_FMT_1_WRAP(T1, T2)
#define DATA TEST_UNARY_DATA_WRAP(T1, T2)
#define T TEST_UNARY_STRUCT_DECL(T1, T2)
#define RUN_UNARY(x) RUN_SAT_U_TRUC_FMT_1_WRAP(T1, T2, x)
#include "scalar_sat_unary.h"

View file

@ -0,0 +1,16 @@
/* { dg-do run { target { riscv_v } } } */
/* { dg-additional-options "-std=c99" } */
#include "sat_arith.h"
#include "sat_arith_data.h"
#define T1 uint32_t
#define T2 uint64_t
DEF_SAT_U_TRUC_FMT_1_WRAP(T1, T2)
#define DATA TEST_UNARY_DATA_WRAP(T1, T2)
#define T TEST_UNARY_STRUCT_DECL(T1, T2)
#define RUN_UNARY(x) RUN_SAT_U_TRUC_FMT_1_WRAP(T1, T2, x)
#include "scalar_sat_unary.h"

View file

@ -0,0 +1,22 @@
#ifndef HAVE_DEFINED_SCALAR_SAT_UNARY
#define HAVE_DEFINED_SCALAR_SAT_UNARY
int
main ()
{
unsigned i;
T d;
for (i = 0; i < sizeof (DATA) / sizeof (DATA[0]); i++)
{
d = DATA[i];
if (RUN_UNARY (d.from) != d.to)
__builtin_abort ();
}
return 0;
}
#endif