@@ -359,3 +359,19 @@ DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64)
+
+DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
@@ -34,6 +34,7 @@
&2op qd qm qn size
&2scalar qd qn rm size
&1imm qd imm cmode op
+&2shift qd qm shift size
@vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
# Note that both Rn and Qd are 3 bits only (no D bit)
@@ -59,6 +60,10 @@
@2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
@2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
+@2_shl_b .... .... .. 001 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0
+@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
+@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2
+
# Vector loads and stores
# Widening loads and narrowing stores:
@@ -275,3 +280,21 @@ VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
# So we have a single decode line and check the cmode/op in the
# trans function.
Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm
+
+# Shifts by immediate
+
+VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
+VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
+VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
+
+VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b
+VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h
+VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
+
+VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b
+VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h
+VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
+
+VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b
+VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h
+VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w
@@ -733,6 +733,8 @@ DO_2OP_SAT(vqsubsw, 4, int32_t, DO_SQSUB_W)
WRAP_QRSHL_HELPER(do_sqrshl_bhs, N, M, true, satp)
#define DO_UQRSHL_OP(N, M, satp) \
WRAP_QRSHL_HELPER(do_uqrshl_bhs, N, M, true, satp)
+#define DO_SUQSHL_OP(N, M, satp) \
+ WRAP_QRSHL_HELPER(do_suqrshl_bhs, N, M, false, satp)
DO_2OP_SAT_S(vqshls, DO_SQSHL_OP)
DO_2OP_SAT_U(vqshlu, DO_UQSHL_OP)
@@ -1186,3 +1188,58 @@ DO_VADDV(vaddvsw, 4, uint32_t)
DO_VADDV(vaddvub, 1, uint8_t)
DO_VADDV(vaddvuh, 2, uint16_t)
DO_VADDV(vaddvuw, 4, uint32_t)
+
+/* Shifts by immediate */
+#define DO_2SHIFT(OP, ESIZE, TYPE, FN) \
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
+ void *vm, uint32_t shift) \
+ { \
+ TYPE *d = vd, *m = vm; \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned e; \
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
+ mergemask(&d[H##ESIZE(e)], \
+ FN(m[H##ESIZE(e)], shift), mask); \
+ } \
+ mve_advance_vpt(env); \
+ }
+
+#define DO_2SHIFT_SAT(OP, ESIZE, TYPE, FN) \
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
+ void *vm, uint32_t shift) \
+ { \
+ TYPE *d = vd, *m = vm; \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned e; \
+ bool qc = false; \
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
+ bool sat = false; \
+ mergemask(&d[H##ESIZE(e)], \
+ FN(m[H##ESIZE(e)], shift, &sat), mask); \
+ qc |= sat & mask & 1; \
+ } \
+ if (qc) { \
+ env->vfp.qc[0] = qc; \
+ } \
+ mve_advance_vpt(env); \
+ }
+
+/* provide unsigned 2-op shift helpers for all sizes */
+#define DO_2SHIFT_U(OP, FN) \
+ DO_2SHIFT(OP##b, 1, uint8_t, FN) \
+ DO_2SHIFT(OP##h, 2, uint16_t, FN) \
+ DO_2SHIFT(OP##w, 4, uint32_t, FN)
+
+#define DO_2SHIFT_SAT_U(OP, FN) \
+ DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \
+ DO_2SHIFT_SAT(OP##h, 2, uint16_t, FN) \
+ DO_2SHIFT_SAT(OP##w, 4, uint32_t, FN)
+#define DO_2SHIFT_SAT_S(OP, FN) \
+ DO_2SHIFT_SAT(OP##b, 1, int8_t, FN) \
+ DO_2SHIFT_SAT(OP##h, 2, int16_t, FN) \
+ DO_2SHIFT_SAT(OP##w, 4, int32_t, FN)
+
+DO_2SHIFT_U(vshli_u, DO_VSHLU)
+DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP)
+DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP)
+DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
@@ -32,6 +32,7 @@ typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
+typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64);
typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64);
@@ -837,3 +838,53 @@ static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a)
}
return do_1imm(s, a, fn);
}
+
+static bool do_2shift(DisasContext *s, arg_2shift *a, MVEGenTwoOpShiftFn fn,
+ bool negateshift)
+{
+ TCGv_ptr qd, qm;
+ int shift = a->shift;
+
+ if (!dc_isar_feature(aa32_mve, s) ||
+ !mve_check_qreg_bank(s, a->qd | a->qm) ||
+ !fn) {
+ return false;
+ }
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
+ return true;
+ }
+
+ /*
+ * When we handle a right shift insn using a left-shift helper
+ * which permits a negative shift count to indicate a right-shift,
+ * we must negate the shift count.
+ */
+ if (negateshift) {
+ shift = -shift;
+ }
+
+ qd = mve_qreg_ptr(a->qd);
+ qm = mve_qreg_ptr(a->qm);
+ fn(cpu_env, qd, qm, tcg_constant_i32(shift));
+ tcg_temp_free_ptr(qd);
+ tcg_temp_free_ptr(qm);
+ mve_update_eci(s);
+ return true;
+}
+
+#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
+ { \
+ static MVEGenTwoOpShiftFn * const fns[] = { \
+ gen_helper_mve_##FN##b, \
+ gen_helper_mve_##FN##h, \
+ gen_helper_mve_##FN##w, \
+ NULL, \
+ }; \
+ return do_2shift(s, a, fns[a->size], NEGATESHIFT); \
+ }
+
+DO_2SHIFT(VSHLI, vshli_u, false)
+DO_2SHIFT(VQSHLI_S, vqshli_s, false)
+DO_2SHIFT(VQSHLI_U, vqshli_u, false)
+DO_2SHIFT(VQSHLUI, vqshlui_s, false)
Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL and VQSHLU. The size-and-immediate encoding here is the same as Neon, and we handle it the same way neon-dp.decode does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 16 +++++++++++ target/arm/mve.decode | 23 +++++++++++++++ target/arm/mve_helper.c | 57 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 51 ++++++++++++++++++++++++++++++++++ 4 files changed, 147 insertions(+)