fpu: Add conversions between bfloat16 and [u]int8

We missed these functions when upstreaming the bfloat16 support.

Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Message-Id: <20230531065458.2082-1-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

2 files changed, 70 insertions, 0 deletions

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 0cc130a..2a33967 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -3126,6 +3126,15 @@ int64_t float64_to_int64_scalbn(float64 a, FloatRoundMode rmode, int scale,
     return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s);
 }
 
+int8_t bfloat16_to_int8_scalbn(bfloat16 a, FloatRoundMode rmode, int scale,
+                               float_status *s)
+{
+    FloatParts64 p;
+
+    bfloat16_unpack_canonical(&p, a, s);
+    return parts_float_to_sint(&p, rmode, scale, INT8_MIN, INT8_MAX, s);
+}
+
 int16_t bfloat16_to_int16_scalbn(bfloat16 a, FloatRoundMode rmode, int scale,
                                  float_status *s)
 {
@@ -3392,6 +3401,11 @@ int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *s)
     return floatx80_to_int64_scalbn(a, float_round_to_zero, 0, s);
 }
 
+int8_t bfloat16_to_int8(bfloat16 a, float_status *s)
+{
+    return bfloat16_to_int8_scalbn(a, s->float_rounding_mode, 0, s);
+}
+
 int16_t bfloat16_to_int16(bfloat16 a, float_status *s)
 {
     return bfloat16_to_int16_scalbn(a, s->float_rounding_mode, 0, s);
@@ -3407,6 +3421,11 @@ int64_t bfloat16_to_int64(bfloat16 a, float_status *s)
     return bfloat16_to_int64_scalbn(a, s->float_rounding_mode, 0, s);
 }
 
+int8_t bfloat16_to_int8_round_to_zero(bfloat16 a, float_status *s)
+{
+    return bfloat16_to_int8_scalbn(a, float_round_to_zero, 0, s);
+}
+
 int16_t bfloat16_to_int16_round_to_zero(bfloat16 a, float_status *s)
 {
     return bfloat16_to_int16_scalbn(a, float_round_to_zero, 0, s);
@@ -3534,6 +3553,15 @@ uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale,
     return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s);
 }
 
+uint8_t bfloat16_to_uint8_scalbn(bfloat16 a, FloatRoundMode rmode,
+                                 int scale, float_status *s)
+{
+    FloatParts64 p;
+
+    bfloat16_unpack_canonical(&p, a, s);
+    return parts_float_to_uint(&p, rmode, scale, UINT8_MAX, s);
+}
+
 uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode,
                                    int scale, float_status *s)
 {
@@ -3759,6 +3787,11 @@ Int128 float128_to_uint128_round_to_zero(float128 a, float_status *s)
     return float128_to_uint128_scalbn(a, float_round_to_zero, 0, s);
 }
 
+uint8_t bfloat16_to_uint8(bfloat16 a, float_status *s)
+{
+    return bfloat16_to_uint8_scalbn(a, s->float_rounding_mode, 0, s);
+}
+
 uint16_t bfloat16_to_uint16(bfloat16 a, float_status *s)
 {
     return bfloat16_to_uint16_scalbn(a, s->float_rounding_mode, 0, s);
@@ -3774,6 +3807,11 @@ uint64_t bfloat16_to_uint64(bfloat16 a, float_status *s)
     return bfloat16_to_uint64_scalbn(a, s->float_rounding_mode, 0, s);
 }
 
+uint8_t bfloat16_to_uint8_round_to_zero(bfloat16 a, float_status *s)
+{
+    return bfloat16_to_uint8_scalbn(a, float_round_to_zero, 0, s);
+}
+
 uint16_t bfloat16_to_uint16_round_to_zero(bfloat16 a, float_status *s)
 {
     return bfloat16_to_uint16_scalbn(a, float_round_to_zero, 0, s);
@@ -3929,6 +3967,11 @@ bfloat16 int16_to_bfloat16_scalbn(int16_t a, int scale, float_status *status)
     return int64_to_bfloat16_scalbn(a, scale, status);
 }
 
+bfloat16 int8_to_bfloat16_scalbn(int8_t a, int scale, float_status *status)
+{
+    return int64_to_bfloat16_scalbn(a, scale, status);
+}
+
 bfloat16 int64_to_bfloat16(int64_t a, float_status *status)
 {
     return int64_to_bfloat16_scalbn(a, 0, status);
@@ -3944,6 +3987,11 @@ bfloat16 int16_to_bfloat16(int16_t a, float_status *status)
     return int64_to_bfloat16_scalbn(a, 0, status);
 }
 
+bfloat16 int8_to_bfloat16(int8_t a, float_status *status)
+{
+    return int64_to_bfloat16_scalbn(a, 0, status);
+}
+
 float128 int128_to_float128(Int128 a, float_status *status)
 {
     FloatParts128 p = { };
@@ -4139,6 +4187,11 @@ bfloat16 uint16_to_bfloat16_scalbn(uint16_t a, int scale, float_status *status)
     return uint64_to_bfloat16_scalbn(a, scale, status);
 }
 
+bfloat16 uint8_to_bfloat16_scalbn(uint8_t a, int scale, float_status *status)
+{
+    return uint64_to_bfloat16_scalbn(a, scale, status);
+}
+
 bfloat16 uint64_to_bfloat16(uint64_t a, float_status *status)
 {
     return uint64_to_bfloat16_scalbn(a, 0, status);
@@ -4154,6 +4207,11 @@ bfloat16 uint16_to_bfloat16(uint16_t a, float_status *status)
     return uint64_to_bfloat16_scalbn(a, 0, status);
 }
 
+bfloat16 uint8_to_bfloat16(uint8_t a, float_status *status)
+{
+    return uint64_to_bfloat16_scalbn(a, 0, status);
+}
+
 float128 uint64_to_float128(uint64_t a, float_status *status)
 {
     FloatParts128 p;
diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index cd13056..eb64075 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -366,6 +366,8 @@ float32 bfloat16_to_float32(bfloat16, float_status *status);
 bfloat16 float64_to_bfloat16(float64 a, float_status *status);
 float64 bfloat16_to_float64(bfloat16 a, float_status *status);
 
+int8_t bfloat16_to_int8_scalbn(bfloat16, FloatRoundMode,
+                               int, float_status *status);
 int16_t bfloat16_to_int16_scalbn(bfloat16, FloatRoundMode,
                                  int, float_status *status);
 int32_t bfloat16_to_int32_scalbn(bfloat16, FloatRoundMode,
@@ -373,14 +375,18 @@ int32_t bfloat16_to_int32_scalbn(bfloat16, FloatRoundMode,
 int64_t bfloat16_to_int64_scalbn(bfloat16, FloatRoundMode,
                                  int, float_status *status);
 
+int8_t bfloat16_to_int8(bfloat16, float_status *status);
 int16_t bfloat16_to_int16(bfloat16, float_status *status);
 int32_t bfloat16_to_int32(bfloat16, float_status *status);
 int64_t bfloat16_to_int64(bfloat16, float_status *status);
 
+int8_t bfloat16_to_int8_round_to_zero(bfloat16, float_status *status);
 int16_t bfloat16_to_int16_round_to_zero(bfloat16, float_status *status);
 int32_t bfloat16_to_int32_round_to_zero(bfloat16, float_status *status);
 int64_t bfloat16_to_int64_round_to_zero(bfloat16, float_status *status);
 
+uint8_t bfloat16_to_uint8_scalbn(bfloat16 a, FloatRoundMode,
+                                 int, float_status *status);
 uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode,
                                    int, float_status *status);
 uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode,
@@ -388,24 +394,30 @@ uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode,
 uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode,
                                    int, float_status *status);
 
+uint8_t bfloat16_to_uint8(bfloat16 a, float_status *status);
 uint16_t bfloat16_to_uint16(bfloat16 a, float_status *status);
 uint32_t bfloat16_to_uint32(bfloat16 a, float_status *status);
 uint64_t bfloat16_to_uint64(bfloat16 a, float_status *status);
 
+uint8_t bfloat16_to_uint8_round_to_zero(bfloat16 a, float_status *status);
 uint16_t bfloat16_to_uint16_round_to_zero(bfloat16 a, float_status *status);
 uint32_t bfloat16_to_uint32_round_to_zero(bfloat16 a, float_status *status);
 uint64_t bfloat16_to_uint64_round_to_zero(bfloat16 a, float_status *status);
 
+bfloat16 int8_to_bfloat16_scalbn(int8_t a, int, float_status *status);
 bfloat16 int16_to_bfloat16_scalbn(int16_t a, int, float_status *status);
 bfloat16 int32_to_bfloat16_scalbn(int32_t a, int, float_status *status);
 bfloat16 int64_to_bfloat16_scalbn(int64_t a, int, float_status *status);
+bfloat16 uint8_to_bfloat16_scalbn(uint8_t a, int, float_status *status);
 bfloat16 uint16_to_bfloat16_scalbn(uint16_t a, int, float_status *status);
 bfloat16 uint32_to_bfloat16_scalbn(uint32_t a, int, float_status *status);
 bfloat16 uint64_to_bfloat16_scalbn(uint64_t a, int, float_status *status);
 
+bfloat16 int8_to_bfloat16(int8_t a, float_status *status);
 bfloat16 int16_to_bfloat16(int16_t a, float_status *status);
 bfloat16 int32_to_bfloat16(int32_t a, float_status *status);
 bfloat16 int64_to_bfloat16(int64_t a, float_status *status);
+bfloat16 uint8_to_bfloat16(uint8_t a, float_status *status);
 bfloat16 uint16_to_bfloat16(uint16_t a, float_status *status);
 bfloat16 uint32_to_bfloat16(uint32_t a, float_status *status);
 bfloat16 uint64_to_bfloat16(uint64_t a, float_status *status);