target/arm: Implement MVE integer vector-vs-scalar comparisons

Implement the MVE integer vector comparison instructions that compare
each element against a scalar from a general purpose register.  These
are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)"
encodings T4, T5 and T6.

We have to move the decodetree pattern for VPST, because it
overlaps with VCMP T4 with size = 0b11.

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

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index ca5a6ab..4f9903e 100644 (file)
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -512,3 +512,35 @@ DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
+DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmpne_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpne_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmphi_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmphi_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmphi_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmpge_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpge_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmplt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmplt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32)

diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 76bbf9a..ef708ba 100644 (file)
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -38,6 +38,7 @@
 &vidup qd rn size imm
 &viwdup qd rn rm size imm
 &vcmp qm qn size mask
+&vcmp_scalar qn rm size mask
 
 @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
 # Note that both Rn and Qd are 3 bits only (no D bit)
@@ -90,6 +91,8 @@
 # Vector comparison; 4-bit Qm but 3-bit Qn
 %mask_22_13      22:1 13:3
 @vcmp    .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13
+@vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \
+             mask=%mask_22_13
 
 # Vector loads and stores
 
@@ -349,9 +352,6 @@ VQRDMULH_scalar  1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
                  rdahi=%rdahi rdalo=%rdalo
 }
 
-# Predicate operations
-VPST             1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
-
 # Logical immediate operations (1 reg and modified-immediate)
 
 # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but
@@ -474,3 +474,15 @@ VCMPGE            1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp
 VCMPLT            1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp
 VCMPGT            1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp
 VCMPLE            1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp
+
+{
+  VPST            1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
+  VCMPEQ_scalar   1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar
+}
+VCMPNE_scalar     1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar
+VCMPCS_scalar     1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar
+VCMPHI_scalar     1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar
+VCMPGE_scalar     1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar
+VCMPLT_scalar     1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar
+VCMPGT_scalar     1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar
+VCMPLE_scalar     1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar

diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index b0b380b..1a021a9 100644 (file)
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1787,15 +1787,43 @@ DO_VIWDUP_ALL(vdwdup, do_sub_wrap)
         mve_advance_vpt(env);                                           \
     }
 
-#define DO_VCMP_S(OP, FN)                       \
-    DO_VCMP(OP##b, 1, int8_t, FN)               \
-    DO_VCMP(OP##h, 2, int16_t, FN)              \
-    DO_VCMP(OP##w, 4, int32_t, FN)
-
-#define DO_VCMP_U(OP, FN)                       \
-    DO_VCMP(OP##b, 1, uint8_t, FN)              \
-    DO_VCMP(OP##h, 2, uint16_t, FN)             \
-    DO_VCMP(OP##w, 4, uint32_t, FN)
+#define DO_VCMP_SCALAR(OP, ESIZE, TYPE, FN)                             \
+    void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn,             \
+                                uint32_t rm)                            \
+    {                                                                   \
+        TYPE *n = vn;                                                   \
+        uint16_t mask = mve_element_mask(env);                          \
+        uint16_t eci_mask = mve_eci_mask(env);                          \
+        uint16_t beatpred = 0;                                          \
+        uint16_t emask = MAKE_64BIT_MASK(0, ESIZE);                     \
+        unsigned e;                                                     \
+        for (e = 0; e < 16 / ESIZE; e++) {                              \
+            bool r = FN(n[H##ESIZE(e)], (TYPE)rm);                      \
+            /* Comparison sets 0/1 bits for each byte in the element */ \
+            beatpred |= r * emask;                                      \
+            emask <<= ESIZE;                                            \
+        }                                                               \
+        beatpred &= mask;                                               \
+        env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) |           \
+            (beatpred & eci_mask);                                      \
+        mve_advance_vpt(env);                                           \
+    }
+
+#define DO_VCMP_S(OP, FN)                               \
+    DO_VCMP(OP##b, 1, int8_t, FN)                       \
+    DO_VCMP(OP##h, 2, int16_t, FN)                      \
+    DO_VCMP(OP##w, 4, int32_t, FN)                      \
+    DO_VCMP_SCALAR(OP##_scalarb, 1, int8_t, FN)         \
+    DO_VCMP_SCALAR(OP##_scalarh, 2, int16_t, FN)        \
+    DO_VCMP_SCALAR(OP##_scalarw, 4, int32_t, FN)
+
+#define DO_VCMP_U(OP, FN)                               \
+    DO_VCMP(OP##b, 1, uint8_t, FN)                      \
+    DO_VCMP(OP##h, 2, uint16_t, FN)                     \
+    DO_VCMP(OP##w, 4, uint32_t, FN)                     \
+    DO_VCMP_SCALAR(OP##_scalarb, 1, uint8_t, FN)        \
+    DO_VCMP_SCALAR(OP##_scalarh, 2, uint16_t, FN)       \
+    DO_VCMP_SCALAR(OP##_scalarw, 4, uint32_t, FN)
 
 #define DO_EQ(N, M) ((N) == (M))
 #define DO_NE(N, M) ((N) != (M))

diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 2d7211b..6c6f159 100644 (file)
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -44,6 +44,7 @@ typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64);
 typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32);
 typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32);
 typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
+typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
 
 /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
 static inline long mve_qreg_offset(unsigned reg)
@@ -1209,6 +1210,37 @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn)
     return true;
 }
 
+static bool do_vcmp_scalar(DisasContext *s, arg_vcmp_scalar *a,
+                           MVEGenScalarCmpFn *fn)
+{
+    TCGv_ptr qn;
+    TCGv_i32 rm;
+
+    if (!dc_isar_feature(aa32_mve, s) || !fn || a->rm == 13) {
+        return false;
+    }
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    qn = mve_qreg_ptr(a->qn);
+    if (a->rm == 15) {
+        /* Encoding Rm=0b1111 means "constant zero" */
+        rm = tcg_constant_i32(0);
+    } else {
+        rm = load_reg(s, a->rm);
+    }
+    fn(cpu_env, qn, rm);
+    tcg_temp_free_ptr(qn);
+    tcg_temp_free_i32(rm);
+    if (a->mask) {
+        /* VPT */
+        gen_vpst(s, a->mask);
+    }
+    mve_update_eci(s);
+    return true;
+}
+
 #define DO_VCMP(INSN, FN)                                       \
     static bool trans_##INSN(DisasContext *s, arg_vcmp *a)      \
     {                                                           \
@@ -1219,6 +1251,17 @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn)
             NULL,                                               \
         };                                                      \
         return do_vcmp(s, a, fns[a->size]);                     \
+    }                                                           \
+    static bool trans_##INSN##_scalar(DisasContext *s,          \
+                                      arg_vcmp_scalar *a)       \
+    {                                                           \
+        static MVEGenScalarCmpFn * const fns[] = {              \
+            gen_helper_mve_##FN##_scalarb,                      \
+            gen_helper_mve_##FN##_scalarh,                      \
+            gen_helper_mve_##FN##_scalarw,                      \
+            NULL,                                               \
+        };                                                      \
+        return do_vcmp_scalar(s, a, fns[a->size]);              \
     }
 
 DO_VCMP(VCMPEQ, vcmpeq)