@@ -11893,6 +11893,50 @@ riscv_expand_usadd (rtx dest, rtx x, rtx y)
emit_move_insn (dest, gen_lowpart (mode, xmode_dest));
}
+/* Generate a REG rtx of Xmode from the given rtx and mode.
+ The rtx x can be REG (QI/HI/SI/DI) or const_int.
+ The machine_mode mode is the original mode from define pattern.
+
+ If rtx is REG, the gen_lowpart of Xmode will be returned.
+
+ If rtx is const_int, a new REG rtx will be created to hold the value of
+ const_int and then returned.
+
+ According to the gccint doc, the constants generated for modes with fewer
+ bits than in HOST_WIDE_INT must be sign extended to full width. Thus there
+ will be two cases here, take QImode as example.
+
+ For .SAT_SUB (127, y) in QImode, we have (const_int 127) and one simple
+ mov from const_int to the new REG rtx is good enough here.
+
+ For .SAT_SUB (254, y) in QImode, we have (const_int -2) after define_expand.
+ Aka 0xfffffffffffffffe in Xmode of RV64 but we actually need 0xfe in Xmode
+ of RV64. So we need to cleanup the highest 56 bits of the new REG rtx moved
+ from the (const_int -2).
+
+ Then the underlying expanding can perform the code generation based on
+ the REG rtx of Xmode, instead of taking care of these in expand func. */
+
+static rtx
+riscv_gen_unsigned_xmode_reg (rtx x, machine_mode mode)
+{
+ if (!CONST_INT_P (x))
+ return gen_lowpart (Xmode, x);
+
+ rtx xmode_x = gen_reg_rtx (Xmode);
+
+ if (mode == Xmode)
+ emit_move_insn (xmode_x, x);
+ else
+ {
+ rtx reg_x = gen_reg_rtx (mode);
+ emit_move_insn (reg_x, x);
+ riscv_emit_unary (ZERO_EXTEND, xmode_x, reg_x);
+ }
+
+ return xmode_x;
+}
+
/* Implements the unsigned saturation sub standard name usadd for int mode.
z = SAT_SUB(x, y).
@@ -11906,7 +11950,7 @@ void
riscv_expand_ussub (rtx dest, rtx x, rtx y)
{
machine_mode mode = GET_MODE (dest);
- rtx xmode_x = gen_lowpart (Xmode, x);
+ rtx xmode_x = riscv_gen_unsigned_xmode_reg (x, mode);
rtx xmode_y = gen_lowpart (Xmode, y);
rtx xmode_lt = gen_reg_rtx (Xmode);
rtx xmode_minus = gen_reg_rtx (Xmode);
@@ -4369,7 +4369,7 @@ (define_expand "usadd<mode>3"
(define_expand "ussub<mode>3"
[(match_operand:ANYI 0 "register_operand")
- (match_operand:ANYI 1 "register_operand")
+ (match_operand:ANYI 1 "reg_or_int_operand")
(match_operand:ANYI 2 "register_operand")]
""
{
@@ -201,6 +201,13 @@ sat_u_sub_##T##_fmt_12 (T x, T y) \
return !overflow ? ret : 0; \
}
+#define DEF_SAT_U_SUB_IMM_FMT_1(T, IMM) \
+T __attribute__((noinline)) \
+sat_u_sub_imm##IMM##_##T##_fmt_1 (T y) \
+{ \
+ return (T)IMM >= y ? (T)IMM - y : 0; \
+}
+
#define RUN_SAT_U_SUB_FMT_1(T, x, y) sat_u_sub_##T##_fmt_1(x, y)
#define RUN_SAT_U_SUB_FMT_2(T, x, y) sat_u_sub_##T##_fmt_2(x, y)
#define RUN_SAT_U_SUB_FMT_3(T, x, y) sat_u_sub_##T##_fmt_3(x, y)
@@ -214,6 +221,9 @@ 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)
+#define RUN_SAT_U_SUB_IMM_FMT_1(T, IMM, y, expect) \
+ if (sat_u_sub_imm##IMM##_##T##_fmt_1(y) != expect) __builtin_abort ()
+
/******************************************************************************/
/* Saturation Truncate (unsigned and signed) */
/******************************************************************************/
new file mode 100644
@@ -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_sub_imm11_uint8_t_fmt_1:
+** li\s+[atx][0-9]+,\s*11
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** andi\s+a0,\s*a0,\s*0xff
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 11)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -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_sub_imm128_uint8_t_fmt_1:
+** li\s+[atx][0-9]+,\s*128
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** andi\s+a0,\s*a0,\s*0xff
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 128)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -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_sub_imm253_uint8_t_fmt_1:
+** li\s+[atx][0-9]+,\s*253
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** andi\s+a0,\s*a0,\s*0xff
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 253)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { 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_sub_imm6_uint16_t_fmt_1:
+** li\s+[atx][0-9]+,\s*6
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** slli\s+a0,\s*a0,\s*48
+** srli\s+a0,\s*a0,\s*48
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 6)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { 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_sub_imm32768_uint16_t_fmt_1:
+** li\s+[atx][0-9]+,\s*32768
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** slli\s+a0,\s*a0,\s*48
+** srli\s+a0,\s*a0,\s*48
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 32768)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,22 @@
+/* { 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_sub_imm65533_uint16_t_fmt_1:
+** li\s+[atx][0-9]+,\s*65536
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-3
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** slli\s+a0,\s*a0,\s*48
+** srli\s+a0,\s*a0,\s*48
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 65533)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -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_sub_imm255_uint32_t_fmt_1:
+** li\s+[atx][0-9]+,\s*255
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** sext\.w\s+a0,\s*a0
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 255)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { 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_sub_imm2147483648_uint32_t_fmt_1:
+** li\s+[atx][0-9]+,\s*1
+** slli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*31
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** sext\.w\s+a0,\s*a0
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 2147483648)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,22 @@
+/* { 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_sub_imm68719476732_uint32_t_fmt_1:
+** li\s+[atx][0-9]+,\s*1
+** slli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*32
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-4
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** sext\.w\s+a0,\s*a0
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 68719476732)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -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_sub_imm82_uint64_t_fmt_1:
+** li\s+[atx][0-9]+,\s*82
+** sub\s+[atx][0-9]+,\s*[atx][0-9]+,\s*a0
+** sltu\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+a0,\s*a0,\s*-1
+** and\s+a0,\s*a0,\s*[atx][0-9]+
+** ret
+*/
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint64_t, 82)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,56 @@
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99" } */
+
+#include "sat_arith.h"
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 0)
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 1)
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 5)
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 127)
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 128)
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 254)
+DEF_SAT_U_SUB_IMM_FMT_1(uint8_t, 255)
+
+#define T uint8_t
+#define RUN(T, imm, op, expect) RUN_SAT_U_SUB_IMM_FMT_1(T, imm, op, expect)
+
+T d[][3] = {
+ /* arg_0, arg_1, expect */
+ { 0, 0, 0, },
+ { 1, 0, 1, },
+ { 1, 255, 0, },
+ { 254, 254, 0, },
+ { 254, 255, 0, },
+ { 254, 2, 252, },
+ { 255, 254, 1, },
+ { 255, 0, 255, },
+ { 5, 2, 3, },
+ { 5, 6, 0, },
+ { 127, 0, 127, },
+ { 128, 129, 0, },
+};
+
+int
+main ()
+{
+ RUN (T, 0, d[0][1], d[0][2]);
+
+ RUN (T, 1, d[1][1], d[1][2]);
+ RUN (T, 1, d[2][1], d[2][2]);
+
+ RUN (T, 254, d[3][1], d[3][2]);
+ RUN (T, 254, d[4][1], d[4][2]);
+ RUN (T, 254, d[5][1], d[5][2]);
+
+ RUN (T, 255, d[6][1], d[6][2]);
+ RUN (T, 255, d[7][1], d[7][2]);
+
+ RUN (T, 5, d[8][1], d[8][2]);
+ RUN (T, 5, d[9][1], d[9][2]);
+
+ RUN (T, 127, d[10][1], d[10][2]);
+
+ RUN (T, 128, d[11][1], d[11][2]);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,56 @@
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99" } */
+
+#include "sat_arith.h"
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 0)
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 1)
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 5)
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 32767)
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 32768)
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 65534)
+DEF_SAT_U_SUB_IMM_FMT_1(uint16_t, 65535)
+
+#define T uint16_t
+#define RUN(T, imm, op, expect) RUN_SAT_U_SUB_IMM_FMT_1(T, imm, op, expect)
+
+T d[][3] = {
+ /* arg_0, arg_1, expect */
+ { 0, 0, 0, },
+ { 1, 0, 1, },
+ { 1, 65535, 0, },
+ { 65534, 65534, 0, },
+ { 65534, 65535, 0, },
+ { 65534, 2, 65532, },
+ { 65535, 65534, 1, },
+ { 65535, 0, 65535, },
+ { 5, 2, 3, },
+ { 5, 6, 0, },
+ { 32767, 0, 32767, },
+ { 32768, 32767, 1, },
+};
+
+int
+main ()
+{
+ RUN (T, 0, d[0][1], d[0][2]);
+
+ RUN (T, 1, d[1][1], d[1][2]);
+ RUN (T, 1, d[2][1], d[2][2]);
+
+ RUN (T, 65534, d[3][1], d[3][2]);
+ RUN (T, 65534, d[4][1], d[4][2]);
+ RUN (T, 65534, d[5][1], d[5][2]);
+
+ RUN (T, 65535, d[6][1], d[6][2]);
+ RUN (T, 65535, d[7][1], d[7][2]);
+
+ RUN (T, 5, d[8][1], d[8][2]);
+ RUN (T, 5, d[9][1], d[9][2]);
+
+ RUN (T, 32767, d[10][1], d[10][2]);
+
+ RUN (T, 32768, d[11][1], d[11][2]);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99" } */
+
+#include "sat_arith.h"
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 0)
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 1)
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 5)
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 2147483647)
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 2147483648)
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 4294967294)
+DEF_SAT_U_SUB_IMM_FMT_1(uint32_t, 4294967295)
+
+#define T uint32_t
+#define RUN(T, imm, op, expect) RUN_SAT_U_SUB_IMM_FMT_1(T, imm, op, expect)
+
+T d[][3] = {
+ /* arg_0, arg_1, expect */
+ { 0, 0, 0, },
+ { 1, 0, 1, },
+ { 1, 4294967295, 0, },
+ { 4294967294, 4294967294, 0, },
+ { 4294967294, 4294967295, 0, },
+ { 4294967294, 2, 4294967292, },
+ { 4294967295, 4294967294, 1, },
+ { 4294967295, 0, 4294967295, },
+ { 5, 2, 3, },
+ { 5, 6, 0, },
+ { 2147483647, 0, 2147483647, },
+ { 2147483648, 2147483647, 1, },
+};
+
+int
+main ()
+{
+ RUN (T, 0, d[0][1], d[0][2]);
+
+ RUN (T, 1, d[1][1], d[1][2]);
+ RUN (T, 1, d[2][1], d[2][2]);
+
+ RUN (T, 4294967294, d[3][1], d[3][2]);
+ RUN (T, 4294967294, d[4][1], d[4][2]);
+ RUN (T, 4294967294, d[5][1], d[5][2]);
+
+ RUN (T, 4294967295, d[6][1], d[6][2]);
+ RUN (T, 4294967295, d[7][1], d[7][2]);
+
+ RUN (T, 5, d[8][1], d[8][2]);
+ RUN (T, 5, d[9][1], d[9][2]);
+
+ RUN (T, 2147483647, d[10][1], d[10][2]);
+ RUN (T, 2147483648, d[11][1], d[11][2]);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,48 @@
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99" } */
+
+#include "sat_arith.h"
+
+DEF_SAT_U_SUB_IMM_FMT_1(uint64_t, 0)
+DEF_SAT_U_SUB_IMM_FMT_1(uint64_t, 1)
+DEF_SAT_U_SUB_IMM_FMT_1(uint64_t, 5)
+DEF_SAT_U_SUB_IMM_FMT_1(uint64_t, 18446744073709551614u)
+DEF_SAT_U_SUB_IMM_FMT_1(uint64_t, 18446744073709551615u)
+
+#define T uint64_t
+#define RUN(T, imm, op, expect) RUN_SAT_U_SUB_IMM_FMT_1(T, imm, op, expect)
+
+T d[][3] = {
+ /* arg_0, arg_1, expect */
+ { 0, 0, 0, },
+ { 1, 0, 1, },
+ { 1, 18446744073709551615u, 0, },
+ { 18446744073709551614u, 18446744073709551614u, 0, },
+ { 18446744073709551614u, 18446744073709551615u, 0, },
+ { 18446744073709551614u, 2, 18446744073709551612u, },
+ { 18446744073709551615u, 18446744073709551614u, 1, },
+ { 18446744073709551615u, 0, 18446744073709551615u, },
+ { 5, 2, 3, },
+ { 5, 6, 0, },
+};
+
+int
+main ()
+{
+ RUN (T, 0, d[0][1], d[0][2]);
+
+ RUN (T, 1, d[1][1], d[1][2]);
+ RUN (T, 1, d[2][1], d[2][2]);
+
+ RUN (T, 18446744073709551614u, d[3][1], d[3][2]);
+ RUN (T, 18446744073709551614u, d[4][1], d[4][2]);
+ RUN (T, 18446744073709551614u, d[5][1], d[5][2]);
+
+ RUN (T, 18446744073709551615u, d[6][1], d[6][2]);
+ RUN (T, 18446744073709551615u, d[7][1], d[7][2]);
+
+ RUN (T, 5, d[8][1], d[8][2]);
+ RUN (T, 5, d[9][1], d[9][2]);
+
+ return 0;
+}