[Qemu-devel] [PATCH v2 19/42] target/arm: Convert VFP VMLS to decodetree

[Peter Maydell <peter.maydell@linaro.org>]

Convert the VFP VMLS instruction to decodetree.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-vfp.inc.c | 38 ++++++++++++++++++++++++++++++++++
 target/arm/translate.c         |  8 +------
 target/arm/vfp.decode          |  5 +++++
 3 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
index 4f922dc8405..00f64401dda 100644
--- a/target/arm/translate-vfp.inc.c
+++ b/target/arm/translate-vfp.inc.c
@@ -1303,3 +1303,41 @@ static bool trans_VMLA_dp(DisasContext *s, arg_VMLA_sp *a)
 {
     return do_vfp_3op_dp(s, gen_VMLA_dp, a->vd, a->vn, a->vm, true);
 }
+
+static void gen_VMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst)
+{
+    /*
+     * VMLS: vd = vd + -(vn * vm)
+     * Note that order of inputs to the add matters for NaNs.
+     */
+    TCGv_i32 tmp = tcg_temp_new_i32();
+
+    gen_helper_vfp_muls(tmp, vn, vm, fpst);
+    gen_helper_vfp_negs(tmp, tmp);
+    gen_helper_vfp_adds(vd, vd, tmp, fpst);
+    tcg_temp_free_i32(tmp);
+}
+
+static bool trans_VMLS_sp(DisasContext *s, arg_VMLS_sp *a)
+{
+    return do_vfp_3op_sp(s, gen_VMLS_sp, a->vd, a->vn, a->vm, true);
+}
+
+static void gen_VMLS_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst)
+{
+    /*
+     * VMLS: vd = vd + -(vn * vm)
+     * Note that order of inputs to the add matters for NaNs.
+     */
+    TCGv_i64 tmp = tcg_temp_new_i64();
+
+    gen_helper_vfp_muld(tmp, vn, vm, fpst);
+    gen_helper_vfp_negd(tmp, tmp);
+    gen_helper_vfp_addd(vd, vd, tmp, fpst);
+    tcg_temp_free_i64(tmp);
+}
+
+static bool trans_VMLS_dp(DisasContext *s, arg_VMLS_sp *a)
+{
+    return do_vfp_3op_dp(s, gen_VMLS_dp, a->vd, a->vn, a->vm, true);
+}
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 4e40a8562c4..bddc0d20447 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -3134,7 +3134,7 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
             rn = VFP_SREG_N(insn);
 
             switch (op) {
-            case 0:
+            case 0 ... 1:
                 /* Already handled by decodetree */
                 return 1;
             default:
@@ -3320,12 +3320,6 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
             for (;;) {
                 /* Perform the calculation.  */
                 switch (op) {
-                case 1: /* VMLS: fd + -(fn * fm) */
-                    gen_vfp_mul(dp);
-                    gen_vfp_F1_neg(dp);
-                    gen_mov_F0_vreg(dp, rd);
-                    gen_vfp_add(dp);
-                    break;
                 case 2: /* VNMLS: -fd + (fn * fm) */
                     /* Note that it isn't valid to replace (-A + B) with (B - A)
                      * or similar plausible looking simplifications
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index 9530e17ae02..7bcf2260eec 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -102,3 +102,8 @@ VMLA_sp      ---- 1110 0.00 .... .... 1010 .0.0 .... \
              vm=%vm_sp vn=%vn_sp vd=%vd_sp
 VMLA_dp      ---- 1110 0.00 .... .... 1011 .0.0 .... \
              vm=%vm_dp vn=%vn_dp vd=%vd_dp
+
+VMLS_sp      ---- 1110 0.00 .... .... 1010 .1.0 .... \
+             vm=%vm_sp vn=%vn_sp vd=%vd_sp
+VMLS_dp      ---- 1110 0.00 .... .... 1011 .1.0 .... \
+             vm=%vm_dp vn=%vn_dp vd=%vd_dp
-- 
2.20.1