target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns to decodetree

Convert the Neon VADD, VSUB, VABD 3-reg-same insns to decodetree.
We already have gvec helpers for addition and subtraction, but must
add one for fabd.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200512163904.10918-12-peter.maydell@linaro.org

6 files changed, 48 insertions, 15 deletions

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 1857f4ee46..6e9629c87b 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -396,7 +396,6 @@ DEF_HELPER_FLAGS_2(neon_qneg_s16, TCG_CALL_NO_RWG, i32, env, i32)
 DEF_HELPER_FLAGS_2(neon_qneg_s32, TCG_CALL_NO_RWG, i32, env, i32)
 DEF_HELPER_FLAGS_2(neon_qneg_s64, TCG_CALL_NO_RWG, i64, env, i64)
 
-DEF_HELPER_3(neon_abd_f32, i32, i32, i32, ptr)
 DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr)
 DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr)
 DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr)
@@ -595,6 +594,8 @@ DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index fd32837fb1..0dd02f3b72 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -45,6 +45,10 @@
 @3same_q0        .... ... . . . size:2 .... .... .... . 0 . . .... \
                  &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0
 
+# For FP insns the high bit of 'size' is used as part of opcode decode
+@3same_fp        .... ... . . . . size:1 .... .... .... . q:1 . . .... \
+                 &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp
+
 VHADD_S_3s       1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same
 VHADD_U_3s       1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same
 VQADD_S_3s       1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same
@@ -169,3 +173,7 @@ SHA256SU1_3s     1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \
                  vm=%vm_dp vn=%vn_dp vd=%vd_dp
 
 VQRDMLSH_3s      1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same
+
+VADD_fp_3s       1111 001 0 0 . 0 . .... .... 1101 ... 0 .... @3same_fp
+VSUB_fp_3s       1111 001 0 0 . 1 . .... .... 1101 ... 0 .... @3same_fp
+VABD_fp_3s       1111 001 1 0 . 1 . .... .... 1101 ... 0 .... @3same_fp
diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c
index 2ef75e04c8..b637265691 100644
--- a/target/arm/neon_helper.c
+++ b/target/arm/neon_helper.c
@@ -1825,13 +1825,6 @@ uint64_t HELPER(neon_qneg_s64)(CPUARMState *env, uint64_t x)
 }
 
 /* NEON Float helpers.  */
-uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b, void *fpstp)
-{
-    float_status *fpst = fpstp;
-    float32 f0 = make_float32(a);
-    float32 f1 = make_float32(b);
-    return float32_val(float32_abs(float32_sub(f0, f1, fpst)));
-}
 
 /* Floating point comparisons produce an integer result.
  * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do.
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index f52302f42b..540720f5e0 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -1021,3 +1021,31 @@ DO_3SAME_PAIR(VPADD, padd_u)
 
 DO_3SAME_VQDMULH(VQDMULH, qdmulh)
 DO_3SAME_VQDMULH(VQRDMULH, qrdmulh)
+
+/*
+ * For all the functions using this macro, size == 1 means fp16,
+ * which is an architecture extension we don't implement yet.
+ */
+#define DO_3S_FP_GVEC(INSN,FUNC)                                        \
+    static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
+                                uint32_t rn_ofs, uint32_t rm_ofs,       \
+                                uint32_t oprsz, uint32_t maxsz)         \
+    {                                                                   \
+        TCGv_ptr fpst = get_fpstatus_ptr(1);                            \
+        tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpst,                \
+                           oprsz, maxsz, 0, FUNC);                      \
+        tcg_temp_free_ptr(fpst);                                        \
+    }                                                                   \
+    static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a)     \
+    {                                                                   \
+        if (a->size != 0) {                                             \
+            /* TODO fp16 support */                                     \
+            return false;                                               \
+        }                                                               \
+        return do_3same(s, a, gen_##INSN##_3s);                         \
+    }
+
+
+DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s)
+DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s)
+DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 561cb67286..8a94856cd2 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5445,6 +5445,9 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         switch (op) {
         case NEON_3R_FLOAT_ARITH:
             pairwise = (u && size < 2); /* if VPADD (float) */
+            if (!pairwise) {
+                return 1; /* handled by decodetree */
+            }
             break;
         case NEON_3R_FLOAT_MINMAX:
             pairwise = u; /* if VPMIN/VPMAX (float) */
@@ -5501,16 +5504,9 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         {
             TCGv_ptr fpstatus = get_fpstatus_ptr(1);
             switch ((u << 2) | size) {
-            case 0: /* VADD */
             case 4: /* VPADD */
                 gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
                 break;
-            case 2: /* VSUB */
-                gen_helper_vfp_subs(tmp, tmp, tmp2, fpstatus);
-                break;
-            case 6: /* VABD */
-                gen_helper_neon_abd_f32(tmp, tmp, tmp2, fpstatus);
-                break;
             default:
                 abort();
             }
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index fa33df859e..50a499299f 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -691,6 +691,11 @@ static float64 float64_ftsmul(float64 op1, uint64_t op2, float_status *stat)
     return result;
 }
 
+static float32 float32_abd(float32 op1, float32 op2, float_status *stat)
+{
+    return float32_abs(float32_sub(op1, op2, stat));
+}
+
 #define DO_3OP(NAME, FUNC, TYPE) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
 {                                                                          \
@@ -718,6 +723,8 @@ DO_3OP(gvec_ftsmul_h, float16_ftsmul, float16)
 DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32)
 DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64)
 
+DO_3OP(gvec_fabd_s, float32_abd, float32)
+
 #ifdef TARGET_AARCH64
 
 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16)