[PATCH for-6.2 29/53] target/arm: Implement MVE VMAXA, VMINA

[Peter Maydell]

Implement the MVE VMAXA and VMINA insns, which take the absolute
value of the signed elements in the input vector and then accumulate
the unsigned max or min into the destination vector.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  8 ++++++++
 target/arm/mve.decode      |  4 ++++
 target/arm/mve_helper.c    | 26 ++++++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 40 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index f9345bfafc7..651020aaad8 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -84,6 +84,14 @@ DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, 
ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr)
 
+DEF_HELPER_FLAGS_3(mve_vmaxab, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vmaxah, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vmaxaw, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
+DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
 DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index a05b882f9d9..0955ed0cc22 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -156,6 +156,8 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 
... 0 @2op
   VQMOVUNB       111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op
   VQMOVN_BS      111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op
 
+  VMAXA          111 0 1110 0 . 11 .. 11 ... 0 1110 1 0 . 0 ... 1 @1op
+
   VMULH_S        111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
 }
 
@@ -176,6 +178,8 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 
... 0 @2op
   VQMOVUNT       111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op
   VQMOVN_TS      111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op
 
+  VMINA          111 0 1110 0 . 11 .. 11 ... 1 1110 1 0 . 0 ... 1 @1op
+
   VRMULH_S       111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
 }
 
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 6539012ddd8..d326205cbf0 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2237,3 +2237,29 @@ DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W)
 DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B)
 DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H)
 DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W)
+
+/*
+ * VMAXA, VMINA: vd is unsigned; vm is signed, and we take its
+ * absolute value; we then do an unsigned comparison.
+ */
+#define DO_VMAXMINA(OP, ESIZE, STYPE, UTYPE, FN)                        \
+    void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm)         \
+    {                                                                   \
+        UTYPE *d = vd;                                                  \
+        STYPE *m = vm;                                                  \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            UTYPE r = DO_ABS(m[H##ESIZE(e)]);                           \
+            r = FN(d[H##ESIZE(e)], r);                                  \
+            mergemask(&d[H##ESIZE(e)], r, mask);                        \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
+DO_VMAXMINA(vmaxab, 1, int8_t, uint8_t, DO_MAX)
+DO_VMAXMINA(vmaxah, 2, int16_t, uint16_t, DO_MAX)
+DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX)
+DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN)
+DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN)
+DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index f2213ec8cde..02c26987a2d 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -277,6 +277,8 @@ DO_1OP(VABS, vabs)
 DO_1OP(VNEG, vneg)
 DO_1OP(VQABS, vqabs)
 DO_1OP(VQNEG, vqneg)
+DO_1OP(VMAXA, vmaxa)
+DO_1OP(VMINA, vmina)
 
 /* Narrowing moves: only size 0 and 1 are valid */
 #define DO_VMOVN(INSN, FN) \
-- 
2.20.1