target/arm: Implement MVE VSHRN, VRSHRN

Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN.

do_urshr() is borrowed from sve_helper.c.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-12-peter.maydell@linaro.org

4 files changed, 76 insertions, 0 deletions

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index e452d2ef7a..323ac07fa3 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -404,3 +404,13 @@ 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)
+
+DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index c3b5366617..e2c177f56a 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -380,3 +380,14 @@ 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
+
+# Narrowing shifts (which only support b and h sizes)
+VSHRNB            111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
+VSHRNB            111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
+VSHRNT            111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
+VSHRNT            111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
+
+VRSHRNB           111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
+VRSHRNB           111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
+VRSHRNT           111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
+VRSHRNT           111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 24336d1d28..a97942208b 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1324,3 +1324,43 @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK)
 
 DO_VSHLL_ALL(vshllb, false)
 DO_VSHLL_ALL(vshllt, true)
+
+/*
+ * Narrowing right shifts, taking a double sized input, shifting it
+ * and putting the result in either the top or bottom half of the output.
+ * ESIZE, TYPE are the output, and LESIZE, LTYPE the input.
+ */
+#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN)       \
+    void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd,     \
+                                void *vm, uint32_t shift)       \
+    {                                                           \
+        LTYPE *m = vm;                                          \
+        TYPE *d = vd;                                           \
+        uint16_t mask = mve_element_mask(env);                  \
+        unsigned le;                                            \
+        for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
+            TYPE r = FN(m[H##LESIZE(le)], shift);               \
+            mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask);     \
+        }                                                       \
+        mve_advance_vpt(env);                                   \
+    }
+
+#define DO_VSHRN_ALL(OP, FN)                                    \
+    DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN)        \
+    DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN)       \
+    DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN)         \
+    DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
+
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
+{
+    if (likely(sh < 64)) {
+        return (x >> sh) + ((x >> (sh - 1)) & 1);
+    } else if (sh == 64) {
+        return x >> 63;
+    } else {
+        return 0;
+    }
+}
+
+DO_VSHRN_ALL(vshrn, DO_SHR)
+DO_VSHRN_ALL(vrshrn, do_urshr)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index b031f84966..f1a8f21b77 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -911,3 +911,18 @@ DO_VSHLL(VSHLL_BS, vshllbs)
 DO_VSHLL(VSHLL_BU, vshllbu)
 DO_VSHLL(VSHLL_TS, vshllts)
 DO_VSHLL(VSHLL_TU, vshlltu)
+
+#define DO_2SHIFT_N(INSN, FN)                                   \
+    static bool trans_##INSN(DisasContext *s, arg_2shift *a)    \
+    {                                                           \
+        static MVEGenTwoOpShiftFn * const fns[] = {             \
+            gen_helper_mve_##FN##b,                             \
+            gen_helper_mve_##FN##h,                             \
+        };                                                      \
+        return do_2shift(s, a, fns[a->size], false);            \
+    }
+
+DO_2SHIFT_N(VSHRNB, vshrnb)
+DO_2SHIFT_N(VSHRNT, vshrnt)
+DO_2SHIFT_N(VRSHRNB, vrshrnb)
+DO_2SHIFT_N(VRSHRNT, vrshrnt)