[PULL 30/47] target/arm: Implement fp16 for Neon VFMA, VMFS

[Peter Maydell]

Convert the neon floating-point vector operations VFMA and VFMS
to use a gvec helper, and use this to implement the fp16 case.

This is the last use of do_3same_fp() so we can now delete
that function.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-32-peter.maydell@linaro.org
---
 target/arm/helper.h             |  6 +++
 target/arm/vec_helper.c         | 33 +++++++++++-
 target/arm/translate-neon.c.inc | 92 +--------------------------------
 3 files changed, 40 insertions(+), 91 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 6f6c96711b7..e6f65c74614 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -665,6 +665,12 @@ DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vfms_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/vec_helper.c b/target/arm/vec_helper.c
index 5da5969c1c0..995f09fb71e 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -867,7 +867,32 @@ static float32 float32_mulsub_nf(float32 dest, float32 
op1, float32 op2,
     return float32_sub(dest, float32_mul(op1, op2, stat), stat);
 }
 
-#define DO_MULADD(NAME, FUNC, TYPE) \
+/* Fused versions; these have the semantics Neon VFMA/VFMS want */
+static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2,
+                                float_status *stat)
+{
+    return float16_muladd(op1, op2, dest, 0, stat);
+}
+
+static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2,
+                                 float_status *stat)
+{
+    return float32_muladd(op1, op2, dest, 0, stat);
+}
+
+static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2,
+                                 float_status *stat)
+{
+    return float16_muladd(float16_chs(op1), op2, dest, 0, stat);
+}
+
+static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2,
+                                 float_status *stat)
+{
+    return float32_muladd(float32_chs(op1), op2, dest, 0, stat);
+}
+
+#define DO_MULADD(NAME, FUNC, TYPE)                                     \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
 {                                                                          \
     intptr_t i, oprsz = simd_oprsz(desc);                                  \
@@ -884,6 +909,12 @@ DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32)
 DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16)
 DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32)
 
+DO_MULADD(gvec_vfma_h, float16_muladd_f, float16)
+DO_MULADD(gvec_vfma_s, float32_muladd_f, float32)
+
+DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
+DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
+
 /* For the indexed ops, SVE applies the index per 128-bit vector segment.
  * For AdvSIMD, there is of course only one such vector segment.
  */
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index ab39127026b..4f2378a19b3 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -1033,55 +1033,6 @@ DO_3SAME_PAIR(VPADD, padd_u)
 DO_3SAME_VQDMULH(VQDMULH, qdmulh)
 DO_3SAME_VQDMULH(VQRDMULH, qrdmulh)
 
-static bool do_3same_fp(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn,
-                        bool reads_vd)
-{
-    /*
-     * FP operations handled elementwise 32 bits at a time.
-     * If reads_vd is true then the old value of Vd will be
-     * loaded before calling the callback function. This is
-     * used for multiply-accumulate type operations.
-     */
-    TCGv_i32 tmp, tmp2;
-    int pass;
-
-    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
-    }
-
-    /* UNDEF accesses to D16-D31 if they don't exist. */
-    if (!dc_isar_feature(aa32_simd_r32, s) &&
-        ((a->vd | a->vn | a->vm) & 0x10)) {
-        return false;
-    }
-
-    if ((a->vn | a->vm | a->vd) & a->q) {
-        return false;
-    }
-
-    if (!vfp_access_check(s)) {
-        return true;
-    }
-
-    TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD);
-    for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
-        tmp = neon_load_reg(a->vn, pass);
-        tmp2 = neon_load_reg(a->vm, pass);
-        if (reads_vd) {
-            TCGv_i32 tmp_rd = neon_load_reg(a->vd, pass);
-            fn(tmp_rd, tmp, tmp2, fpstatus);
-            neon_store_reg(a->vd, pass, tmp_rd);
-            tcg_temp_free_i32(tmp);
-        } else {
-            fn(tmp, tmp, tmp2, fpstatus);
-            neon_store_reg(a->vd, pass, tmp);
-        }
-        tcg_temp_free_i32(tmp2);
-    }
-    tcg_temp_free_ptr(fpstatus);
-    return true;
-}
-
 #define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC)                              \
     static void WRAPNAME(unsigned vece, uint32_t rd_ofs,                \
                          uint32_t rn_ofs, uint32_t rm_ofs,              \
@@ -1121,6 +1072,8 @@ DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, 
gen_helper_gvec_fmax_h)
 DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h)
 DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h)
 DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h)
+DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h)
+DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h)
 
 WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s)
 WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h)
@@ -1197,47 +1150,6 @@ static bool trans_VRSQRTS_fp_3s(DisasContext *s, 
arg_3same *a)
     return do_3same(s, a, gen_VRSQRTS_fp_3s);
 }
 
-static void gen_VFMA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
-                            TCGv_ptr fpstatus)
-{
-    gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus);
-}
-
-static bool trans_VFMA_fp_3s(DisasContext *s, arg_3same *a)
-{
-    if (!dc_isar_feature(aa32_simdfmac, s)) {
-        return false;
-    }
-
-    if (a->size != 0) {
-        /* TODO fp16 support */
-        return false;
-    }
-
-    return do_3same_fp(s, a, gen_VFMA_fp_3s, true);
-}
-
-static void gen_VFMS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
-                            TCGv_ptr fpstatus)
-{
-    gen_helper_vfp_negs(vn, vn);
-    gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus);
-}
-
-static bool trans_VFMS_fp_3s(DisasContext *s, arg_3same *a)
-{
-    if (!dc_isar_feature(aa32_simdfmac, s)) {
-        return false;
-    }
-
-    if (a->size != 0) {
-        /* TODO fp16 support */
-        return false;
-    }
-
-    return do_3same_fp(s, a, gen_VFMS_fp_3s, true);
-}
-
 static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn)
 {
     /* FP operations handled pairwise 32 bits at a time */
-- 
2.20.1