[PATCH v2 08/18] target/arm: Implement MVE fp-with-scalar VFMA, VFMAS

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

Implement the MVE fp-with-scalar VFMA and VFMAS insns.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
v1->v2: use float* types
---
 target/arm/helper-mve.h    |  6 ++++++
 target/arm/mve.decode      | 14 +++++++++++---
 target/arm/mve_helper.c    | 37 +++++++++++++++++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 091ec4b4270..cb7b6423239 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -809,3 +809,9 @@ DEF_HELPER_FLAGS_4(mve_vfsub_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(mve_vfmul_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vfmul_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vfma_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vfma_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vfmas_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vfmas_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 5ba8b6deeaa..d2bd6815bc3 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -508,9 +508,17 @@ VSUB_scalar      1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar
   VQRDMULH_scalar 1111  1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
 }
 
-# The U bit (28) is don't-care because it does not affect the result
-VMLA             111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar
-VMLAS            111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
+{
+  VFMA_scalar     111 . 1110 0 . 11 ... 1 ... 0 1110 . 100 .... @2op_fp_scalar
+  # The U bit (28) is don't-care because it does not affect the result
+  VMLA            111 - 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar
+}
+
+{
+  VFMAS_scalar    111 . 1110 0 . 11 ... 1 ... 1 1110 . 100 .... @2op_fp_scalar
+  # The U bit (28) is don't-care because it does not affect the result
+  VMLAS           111 - 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
+}
 
 VQRDMLAH         1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar
 VQRDMLASH        1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index b49975fdc01..36f0910b856 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -3075,3 +3075,40 @@ DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS)
 DO_2OP_FP_SCALAR_ALL(vfadd_scalar, add)
 DO_2OP_FP_SCALAR_ALL(vfsub_scalar, sub)
 DO_2OP_FP_SCALAR_ALL(vfmul_scalar, mul)
+
+#define DO_2OP_FP_ACC_SCALAR(OP, ESIZE, TYPE, FN)                       \
+    void HELPER(glue(mve_, OP))(CPUARMState *env,                       \
+                                void *vd, void *vn, uint32_t rm)        \
+    {                                                                   \
+        TYPE *d = vd, *n = vn;                                          \
+        TYPE r, m = rm;                                                 \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        float_status *fpst;                                             \
+        float_status scratch_fpst;                                      \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) {              \
+                continue;                                               \
+            }                                                           \
+            fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 :    \
+                &env->vfp.standard_fp_status;                           \
+            if (!(mask & 1)) {                                          \
+                /* We need the result but without updating flags */     \
+                scratch_fpst = *fpst;                                   \
+                fpst = &scratch_fpst;                                   \
+            }                                                           \
+            r = FN(n[H##ESIZE(e)], m, d[H##ESIZE(e)], 0, fpst);         \
+            mergemask(&d[H##ESIZE(e)], r, mask);                        \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
+/* VFMAS is vector * vector + scalar, so swap op2 and op3 */
+#define DO_VFMAS_SCALARH(N, M, D, F, S) float16_muladd(N, D, M, F, S)
+#define DO_VFMAS_SCALARS(N, M, D, F, S) float32_muladd(N, D, M, F, S)
+
+/* VFMA is vector * scalar + vector */
+DO_2OP_FP_ACC_SCALAR(vfma_scalarh, 2, float16, float16_muladd)
+DO_2OP_FP_ACC_SCALAR(vfma_scalars, 4, float32, float32_muladd)
+DO_2OP_FP_ACC_SCALAR(vfmas_scalarh, 2, float16, DO_VFMAS_SCALARH)
+DO_2OP_FP_ACC_SCALAR(vfmas_scalars, 4, float32, DO_VFMAS_SCALARS)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index bc4b3f840a0..3627ba227f2 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -979,6 +979,8 @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a)
 DO_2OP_FP_SCALAR(VADD_fp_scalar, vfadd_scalar)
 DO_2OP_FP_SCALAR(VSUB_fp_scalar, vfsub_scalar)
 DO_2OP_FP_SCALAR(VMUL_fp_scalar, vfmul_scalar)
+DO_2OP_FP_SCALAR(VFMA_scalar, vfma_scalar)
+DO_2OP_FP_SCALAR(VFMAS_scalar, vfmas_scalar)
 
 static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a,
                              MVEGenLongDualAccOpFn *fn)
-- 
2.20.1