target/arm: Implement MVE vector shift right by immediate insns

Implement the MVE vector shift right by immediate insns VSHRI and
VRSHRI.  As with Neon, we implement these by using helper functions
which perform left shifts but allow negative shift counts to indicate
right shifts.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-9-peter.maydell@linaro.org

6 files changed, 72 insertions, 18 deletions

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 8cd7c6a..288a8fa 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -360,6 +360,10 @@ 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_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
 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)
@@ -375,3 +379,11 @@ 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)
+
+DEF_HELPER_FLAGS_4(mve_vrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 183eb73..8be0458 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -64,6 +64,18 @@
 @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
 
+# Right shifts are encoded as N - shift, where N is the element size in bits.
+%rshift_i5  16:5 !function=rsub_32
+%rshift_i4  16:4 !function=rsub_16
+%rshift_i3  16:3 !function=rsub_8
+
+@2_shr_b .... .... .. 001 ... .... .... .... .... &2shift qd=%qd qm=%qm \
+         size=0 shift=%rshift_i3
+@2_shr_h .... .... .. 01 .... .... .... .... .... &2shift qd=%qd qm=%qm \
+         size=1 shift=%rshift_i4
+@2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \
+         size=2 shift=%rshift_i5
+
 # Vector loads and stores
 
 # Widening loads and narrowing stores:
@@ -298,3 +310,19 @@ 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
+
+VSHRI_S           111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b
+VSHRI_S           111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h
+VSHRI_S           111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w
+
+VSHRI_U           111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b
+VSHRI_U           111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h
+VSHRI_U           111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w
+
+VRSHRI_S          111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
+VRSHRI_S          111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
+VRSHRI_S          111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
+
+VRSHRI_U          111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
+VRSHRI_U          111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
+VRSHRI_U          111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 285c8b5..ac720c9 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1229,6 +1229,10 @@ DO_VADDV(vaddvuw, 4, uint32_t)
     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_S(OP, FN)                     \
+    DO_2SHIFT(OP##b, 1, int8_t, FN)             \
+    DO_2SHIFT(OP##h, 2, int16_t, FN)            \
+    DO_2SHIFT(OP##w, 4, int32_t, FN)
 
 #define DO_2SHIFT_SAT_U(OP, FN)                 \
     DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN)        \
@@ -1240,6 +1244,9 @@ DO_VADDV(vaddvuw, 4, uint32_t)
     DO_2SHIFT_SAT(OP##w, 4, int32_t, FN)
 
 DO_2SHIFT_U(vshli_u, DO_VSHLU)
+DO_2SHIFT_S(vshli_s, DO_VSHLS)
 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)
+DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
+DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index fc8a2da..4030ee0 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -888,3 +888,8 @@ 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)
+/* These right shifts use a left-shift helper with negated shift count */
+DO_2SHIFT(VSHRI_S, vshli_s, true)
+DO_2SHIFT(VSHRI_U, vshli_u, true)
+DO_2SHIFT(VRSHRI_S, vrshli_s, true)
+DO_2SHIFT(VRSHRI_U, vrshli_u, true)
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index f915f70..a45616c 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -33,24 +33,6 @@ static inline int plus1(DisasContext *s, int x)
     return x + 1;
 }
 
-static inline int rsub_64(DisasContext *s, int x)
-{
-    return 64 - x;
-}
-
-static inline int rsub_32(DisasContext *s, int x)
-{
-    return 32 - x;
-}
-static inline int rsub_16(DisasContext *s, int x)
-{
-    return 16 - x;
-}
-static inline int rsub_8(DisasContext *s, int x)
-{
-    return 8 - x;
-}
-
 static inline int neon_3same_fp_size(DisasContext *s, int x)
 {
     /* Convert 0==fp32, 1==fp16 into a MO_* value */
diff --git a/target/arm/translate.h b/target/arm/translate.h
index e2f056c..4b5db93 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -161,6 +161,26 @@ static inline int times_2_plus_1(DisasContext *s, int x)
     return x * 2 + 1;
 }
 
+static inline int rsub_64(DisasContext *s, int x)
+{
+    return 64 - x;
+}
+
+static inline int rsub_32(DisasContext *s, int x)
+{
+    return 32 - x;
+}
+
+static inline int rsub_16(DisasContext *s, int x)
+{
+    return 16 - x;
+}
+
+static inline int rsub_8(DisasContext *s, int x)
+{
+    return 8 - x;
+}
+
 static inline int arm_dc_feature(DisasContext *dc, int feature)
 {
     return (dc->features & (1ULL << feature)) != 0;