target/arm: Implement MVE VBRSR

Implement the MVE VBRSR insn, which reverses a specified
number of bits in each element, setting the rest to zero.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-26-peter.maydell@linaro.org

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 52086d7..1b807e1 100644 (file)
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -173,6 +173,10 @@ DEF_HELPER_FLAGS_4(mve_vhsubu_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vhsubu_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vhsubu_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(mve_vbrsrb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vbrsrh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vbrsrw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)

diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 5c332b0..a3dbdb7 100644 (file)
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -167,3 +167,4 @@ VHADD_S_scalar   1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
 VHADD_U_scalar   1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
 VHSUB_S_scalar   1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar
 VHSUB_U_scalar   1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar
+VBRSR            1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar

diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index d76168a..441bc84 100644 (file)
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -523,6 +523,49 @@ DO_2OP_SCALAR_U(vhaddu_scalar, do_vhadd_u)
 DO_2OP_SCALAR_S(vhsubs_scalar, do_vhsub_s)
 DO_2OP_SCALAR_U(vhsubu_scalar, do_vhsub_u)
 
+static inline uint32_t do_vbrsrb(uint32_t n, uint32_t m)
+{
+    m &= 0xff;
+    if (m == 0) {
+        return 0;
+    }
+    n = revbit8(n);
+    if (m < 8) {
+        n >>= 8 - m;
+    }
+    return n;
+}
+
+static inline uint32_t do_vbrsrh(uint32_t n, uint32_t m)
+{
+    m &= 0xff;
+    if (m == 0) {
+        return 0;
+    }
+    n = revbit16(n);
+    if (m < 16) {
+        n >>= 16 - m;
+    }
+    return n;
+}
+
+static inline uint32_t do_vbrsrw(uint32_t n, uint32_t m)
+{
+    m &= 0xff;
+    if (m == 0) {
+        return 0;
+    }
+    n = revbit32(n);
+    if (m < 32) {
+        n >>= 32 - m;
+    }
+    return n;
+}
+
+DO_2OP_SCALAR(vbrsrb, 1, uint8_t, do_vbrsrb)
+DO_2OP_SCALAR(vbrsrh, 2, uint16_t, do_vbrsrh)
+DO_2OP_SCALAR(vbrsrw, 4, uint32_t, do_vbrsrw)
+
 /*
  * Multiply add long dual accumulate ops.
  */

diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 4b379bf..6320064 100644 (file)
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -433,6 +433,7 @@ DO_2OP_SCALAR(VHADD_S_scalar, vhadds_scalar)
 DO_2OP_SCALAR(VHADD_U_scalar, vhaddu_scalar)
 DO_2OP_SCALAR(VHSUB_S_scalar, vhsubs_scalar)
 DO_2OP_SCALAR(VHSUB_U_scalar, vhsubu_scalar)
+DO_2OP_SCALAR(VBRSR, vbrsr)
 
 static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a,
                              MVEGenDualAccOpFn *fn)