@@ -367,9 +367,24 @@ sat_s_sub_##T##_fmt_1 (T x, T y) \
#define DEF_SAT_S_SUB_FMT_1_WRAP(T, UT, MIN, MAX) \
DEF_SAT_S_SUB_FMT_1(T, UT, MIN, MAX)
+#define DEF_SAT_S_SUB_FMT_2(T, UT, MIN, MAX) \
+T __attribute__((noinline)) \
+sat_s_sub_##T##_fmt_2 (T x, T y) \
+{ \
+ T minus = (UT)x - (UT)y; \
+ if ((x ^ y) >= 0 || (minus ^ x) >= 0) \
+ return minus; \
+ return x < 0 ? MIN : MAX; \
+}
+#define DEF_SAT_S_SUB_FMT_2_WRAP(T, UT, MIN, MAX) \
+ DEF_SAT_S_SUB_FMT_2(T, UT, MIN, MAX)
+
#define RUN_SAT_S_SUB_FMT_1(T, x, y) sat_s_sub_##T##_fmt_1(x, y)
#define RUN_SAT_S_SUB_FMT_1_WRAP(T, x, y) RUN_SAT_S_SUB_FMT_1(T, x, y)
+#define RUN_SAT_S_SUB_FMT_2(T, x, y) sat_s_sub_##T##_fmt_2(x, y)
+#define RUN_SAT_S_SUB_FMT_2_WRAP(T, x, y) RUN_SAT_S_SUB_FMT_2(T, x, y)
+
/******************************************************************************/
/* Saturation Truncate (unsigned and signed) */
/******************************************************************************/
new file mode 100644
@@ -0,0 +1,30 @@
+/* { 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_s_sub_int16_t_fmt_2:
+** sub\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** srli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*15
+** andi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*1
+** srai\s+[atx][0-9]+,\s*[atx][0-9]+,\s*63
+** li\s+[atx][0-9]+,\s*32768
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
+** xor\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** neg\s+[atx][0-9]+,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** or\s+a0,\s*[atx][0-9]+,\s*[atx][0-9]+
+** slliw\s+a0,\s*a0,\s*16
+** sraiw\s+a0,\s*a0,\s*16
+** ret
+*/
+DEF_SAT_S_SUB_FMT_2(int16_t, uint16_t, INT16_MIN, INT16_MAX)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { 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_s_sub_int32_t_fmt_2:
+** sub\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** srliw\s+[atx][0-9]+,\s*[atx][0-9]+,\s*31
+** srai\s+[atx][0-9]+,\s*[atx][0-9]+,\s*63
+** li\s+[atx][0-9]+,\s*-2147483648
+** xori\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
+** xor\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-7]
+** neg\s+[atx][0-9]+,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** or\s+a0,\s*[atx][0-9]+,\s*[atx][0-9]+
+** sext\.w\s+a0,\s*[atx][0-9]+
+** ret
+*/
+DEF_SAT_S_SUB_FMT_2(int32_t, uint32_t, INT32_MIN, INT32_MAX)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,27 @@
+/* { 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_s_sub_int64_t_fmt_2:
+** sub\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** srli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*63
+** srai\s+[atx][0-9]+,\s*[atx][0-9]+,\s*63
+** li\s+[atx][0-9]+,\s*-1
+** srli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*1
+** xor\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** neg\s+[atx][0-9]+,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** or\s+a0,\s*[atx][0-9]+,\s*[atx][0-9]+
+** ret
+*/
+DEF_SAT_S_SUB_FMT_2(int64_t, uint64_t, INT64_MIN, INT64_MAX)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { 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_s_sub_int8_t_fmt_2:
+** sub\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*a1
+** xor\s+[atx][0-9]+,\s*a0,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** srli\s+[atx][0-9]+,\s*[atx][0-9]+,\s*7
+** andi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*1
+** srai\s+[atx][0-9]+,\s*[atx][0-9]+,\s*63
+** xori\s+[atx][0-9]+,\s*[atx][0-9]+,\s*127
+** neg\s+[atx][0-9]+,\s*[atx][0-9]+
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** addi\s+[atx][0-9]+,\s*[atx][0-9]+,\s*-1
+** and\s+[atx][0-9]+,\s*[atx][0-9]+,\s*[atx][0-9]+
+** or\s+a0,\s*[atx][0-9]+,\s*[atx][0-9]+
+** slliw\s+a0,\s*a0,\s*24
+** sraiw\s+a0,\s*a0,\s*24
+** ret
+*/
+DEF_SAT_S_SUB_FMT_2(int8_t, uint8_t, INT8_MIN, INT8_MAX)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_SUB " 2 "expand" } } */
new file mode 100644
@@ -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 int16_t
+#define T2 uint16_t
+
+DEF_SAT_S_SUB_FMT_2_WRAP(T1, T2, INT16_MIN, INT16_MAX)
+
+#define DATA TEST_BINARY_DATA_WRAP(T1, sssub)
+#define T TEST_BINARY_STRUCT_DECL(T1, sssub)
+#define RUN_BINARY(x, y) RUN_SAT_S_SUB_FMT_2_WRAP(T1, x, y)
+
+#include "scalar_sat_binary_run_xxx.h"
new file mode 100644
@@ -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 int32_t
+#define T2 uint32_t
+
+DEF_SAT_S_SUB_FMT_2_WRAP(T1, T2, INT32_MIN, INT32_MAX)
+
+#define DATA TEST_BINARY_DATA_WRAP(T1, sssub)
+#define T TEST_BINARY_STRUCT_DECL(T1, sssub)
+#define RUN_BINARY(x, y) RUN_SAT_S_SUB_FMT_2_WRAP(T1, x, y)
+
+#include "scalar_sat_binary_run_xxx.h"
new file mode 100644
@@ -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 int64_t
+#define T2 uint64_t
+
+DEF_SAT_S_SUB_FMT_2_WRAP(T1, T2, INT64_MIN, INT64_MAX)
+
+#define DATA TEST_BINARY_DATA_WRAP(T1, sssub)
+#define T TEST_BINARY_STRUCT_DECL(T1, sssub)
+#define RUN_BINARY(x, y) RUN_SAT_S_SUB_FMT_2_WRAP(T1, x, y)
+
+#include "scalar_sat_binary_run_xxx.h"
new file mode 100644
@@ -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 int8_t
+#define T2 uint8_t
+
+DEF_SAT_S_SUB_FMT_2_WRAP(T1, T2, INT8_MIN, INT8_MAX)
+
+#define DATA TEST_BINARY_DATA_WRAP(T1, sssub)
+#define T TEST_BINARY_STRUCT_DECL(T1, sssub)
+#define RUN_BINARY(x, y) RUN_SAT_S_SUB_FMT_2_WRAP(T1, x, y)
+
+#include "scalar_sat_binary_run_xxx.h"