@@ -179,6 +179,14 @@ DEF_HELPER_FLAGS_4(mve_vqshlub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
DEF_HELPER_FLAGS_4(mve_vqshluh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
DEF_HELPER_FLAGS_4(mve_vqshluw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrshlsb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrshlsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrshlsw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vqrshlub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrshluh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrshluw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
@@ -133,6 +133,9 @@ VQSUB_U 111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 1 ... 0 @2op
VQSHL_S 111 0 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev
VQSHL_U 111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev
+VQRSHL_S 111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev
+VQRSHL_U 111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev
+
# Vector miscellaneous
VCLS 1111 1111 1 . 11 .. 00 ... 0 0100 01 . 0 ... 0 @1op
@@ -637,6 +637,133 @@ DO_2OP_SAT(vqsubsw, 4, int32_t, H4, DO_SQSUB_W)
DO_2OP_SAT_S(vqshls, DO_SQSHL_OP)
DO_2OP_SAT_U(vqshlu, DO_UQSHL_OP)
+#define DO_UQRSHL_OP(src1, src2, satp) \
+ ({ \
+ int8_t tmp; \
+ typeof(src1) dest; \
+ tmp = (int8_t)src2; \
+ if (tmp >= (ssize_t)sizeof(src1) * 8) { \
+ if (src1) { \
+ *satp = true; \
+ dest = ~0; \
+ } else { \
+ dest = 0; \
+ } \
+ } else if (tmp < -(ssize_t)sizeof(src1) * 8) { \
+ dest = 0; \
+ } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \
+ dest = src1 >> (sizeof(src1) * 8 - 1); \
+ } else if (tmp < 0) { \
+ dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \
+ } else { \
+ dest = src1 << tmp; \
+ if ((dest >> tmp) != src1) { \
+ *satp = true; \
+ dest = ~0; \
+ } \
+ } \
+ dest; \
+ })
+
+/*
+ * The addition of the rounding constant may overflow, so we use an
+ * intermediate 64 bit accumulator for the 32-bit version.
+ */
+#define DO_UQRSHL32_OP(src1, src2, satp) \
+ ({ \
+ uint32_t dest; \
+ uint32_t val = src1; \
+ int8_t shift = (int8_t)src2; \
+ if (shift >= 32) { \
+ if (val) { \
+ *satp = true; \
+ dest = ~0; \
+ } else { \
+ dest = 0; \
+ } \
+ } else if (shift < -32) { \
+ dest = 0; \
+ } else if (shift == -32) { \
+ dest = val >> 31; \
+ } else if (shift < 0) { \
+ uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift))); \
+ dest = big_dest >> -shift; \
+ } else { \
+ dest = val << shift; \
+ if ((dest >> shift) != val) { \
+ *satp = true; \
+ dest = ~0; \
+ } \
+ } \
+ dest; \
+ })
+
+#define DO_SQRSHL_OP(src1, src2, satp) \
+ ({ \
+ int8_t tmp; \
+ typeof(src1) dest; \
+ tmp = (int8_t)src2; \
+ if (tmp >= (ssize_t)sizeof(src1) * 8) { \
+ if (src1) { \
+ *satp = true; \
+ dest = (typeof(dest))(1 << (sizeof(src1) * 8 - 1)); \
+ if (src1 > 0) { \
+ dest--; \
+ } \
+ } else { \
+ dest = 0; \
+ } \
+ } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
+ dest = 0; \
+ } else if (tmp < 0) { \
+ dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \
+ } else { \
+ dest = src1 << tmp; \
+ if ((dest >> tmp) != src1) { \
+ *satp = true; \
+ dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \
+ if (src1 > 0) { \
+ dest--; \
+ } \
+ } \
+ } \
+ dest; \
+ })
+
+#define DO_SQRSHL32_OP(src1, src2, satp) \
+ ({ \
+ int32_t dest; \
+ int32_t val = (int32_t)src1; \
+ int8_t shift = (int8_t)src2; \
+ if (shift >= 32) { \
+ if (val) { \
+ *satp = true; \
+ dest = (val >> 31) ^ ~(1U << 31); \
+ } else { \
+ dest = 0; \
+ } \
+ } else if (shift <= -32) { \
+ dest = 0; \
+ } else if (shift < 0) { \
+ int64_t big_dest = ((int64_t)val + (1 << (-1 - shift))); \
+ dest = big_dest >> -shift; \
+ } else { \
+ dest = val << shift; \
+ if ((dest >> shift) != val) { \
+ *satp = true; \
+ dest = (val >> 31) ^ ~(1U << 31); \
+ } \
+ } \
+ dest; \
+ })
+
+DO_2OP_SAT(vqrshlub, 1, uint8_t, H1, DO_UQRSHL_OP)
+DO_2OP_SAT(vqrshluh, 2, uint16_t, H2, DO_UQRSHL_OP)
+DO_2OP_SAT(vqrshluw, 4, uint32_t, H4, DO_UQRSHL32_OP)
+DO_2OP_SAT(vqrshlsb, 1, int8_t, H1, DO_SQRSHL_OP)
+DO_2OP_SAT(vqrshlsh, 2, int16_t, H2, DO_SQRSHL_OP)
+DO_2OP_SAT(vqrshlsw, 4, int32_t, H4, DO_SQRSHL32_OP)
+
#define DO_2OP_SCALAR(OP, ESIZE, TYPE, H, FN) \
void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \
uint32_t rm) \
@@ -423,6 +423,8 @@ DO_2OP(VQSUB_S, vqsubs)
DO_2OP(VQSUB_U, vqsubu)
DO_2OP(VQSHL_S, vqshls)
DO_2OP(VQSHL_U, vqshlu)
+DO_2OP(VQRSHL_S, vqrshls)
+DO_2OP(VQRSHL_U, vqrshlu)
static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
MVEGenTwoOpScalarFn fn)
Implement the MV VQRSHL (vector) insn. Again, the code to perform the actual shifts is borrowed from neon_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 8 +++ target/arm/mve.decode | 3 + target/arm/mve_helper.c | 127 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 + 4 files changed, 140 insertions(+) -- 2.20.1