target/arm: Implement MVE VSRI, VSLI

Implement the MVE VSRI and VSLI insns, which perform a
shift-and-insert operation.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-11-peter.maydell@linaro.org

target/arm/helper-mve.h

@@ -396,3 +396,11 @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vsrib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vsrih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)

target/arm/mve.decode

@@ -371,3 +371,12 @@ VSHLL_TS          111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
 
 VSHLL_TU          111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
 VSHLL_TU          111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
+
+# Shift-and-insert
+VSRI              111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b
+VSRI              111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h
+VSRI              111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w
+
+VSLI              111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
+VSLI              111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
+VSLI              111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w

target/arm/mve_helper.c

@@ -1251,6 +1251,48 @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
 DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
 DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
 
+/* Shift-and-insert; we always work with 64 bits at a time */
+#define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN)                    \
+    void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd,             \
+                                void *vm, uint32_t shift)               \
+    {                                                                   \
+        uint64_t *d = vd, *m = vm;                                      \
+        uint16_t mask;                                                  \
+        uint64_t shiftmask;                                             \
+        unsigned e;                                                     \
+        if (shift == 0 || shift == ESIZE * 8) {                         \
+            /*                                                          \
+             * Only VSLI can shift by 0; only VSRI can shift by <dt>.   \
+             * The generic logic would give the right answer for 0 but  \
+             * fails for <dt>.                                          \
+             */                                                         \
+            goto done;                                                  \
+        }                                                               \
+        assert(shift < ESIZE * 8);                                      \
+        mask = mve_element_mask(env);                                   \
+        /* ESIZE / 2 gives the MO_* value if ESIZE is in [1,2,4] */     \
+        shiftmask = dup_const(ESIZE / 2, MASKFN(ESIZE * 8, shift));     \
+        for (e = 0; e < 16 / 8; e++, mask >>= 8) {                      \
+            uint64_t r = (SHIFTFN(m[H8(e)], shift) & shiftmask) |       \
+                (d[H8(e)] & ~shiftmask);                                \
+            mergemask(&d[H8(e)], r, mask);                              \
+        }                                                               \
+done:                                                                   \
+        mve_advance_vpt(env);                                           \
+    }
+
+#define DO_SHL(N, SHIFT) ((N) << (SHIFT))
+#define DO_SHR(N, SHIFT) ((N) >> (SHIFT))
+#define SHL_MASK(EBITS, SHIFT) MAKE_64BIT_MASK((SHIFT), (EBITS) - (SHIFT))
+#define SHR_MASK(EBITS, SHIFT) MAKE_64BIT_MASK(0, (EBITS) - (SHIFT))
+
+DO_2SHIFT_INSERT(vsrib, 1, DO_SHR, SHR_MASK)
+DO_2SHIFT_INSERT(vsrih, 2, DO_SHR, SHR_MASK)
+DO_2SHIFT_INSERT(vsriw, 4, DO_SHR, SHR_MASK)
+DO_2SHIFT_INSERT(vslib, 1, DO_SHL, SHL_MASK)
+DO_2SHIFT_INSERT(vslih, 2, DO_SHL, SHL_MASK)
+DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK)
+
 /*
  * Long shifts taking half-sized inputs from top or bottom of the input
  * vector and producing a double-width result. ESIZE, TYPE are for

target/arm/translate-mve.c

@@ -894,6 +894,9 @@ DO_2SHIFT(VSHRI_U, vshli_u, true)
 DO_2SHIFT(VRSHRI_S, vrshli_s, true)
 DO_2SHIFT(VRSHRI_U, vrshli_u, true)
 
+DO_2SHIFT(VSRI, vsri, false)
+DO_2SHIFT(VSLI, vsli, false)
+
 #define DO_VSHLL(INSN, FN)                                      \
     static bool trans_##INSN(DisasContext *s, arg_2shift *a)    \
     {                                                           \