[PULL 36/47] target/arm: Convert Neon VCVT fixed-point to gvec

[Peter Maydell]

Convert the Neon VCVT float<->fixed-point insns to a
gvec style, in preparation for adding fp16 support.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-38-peter.maydell@linaro.org
---
 target/arm/helper.h             |  5 +++++
 target/arm/vec_helper.c         | 20 +++++++++++++++++++
 target/arm/translate-neon.c.inc | 35 +++++++++++++++++----------------
 3 files changed, 43 insertions(+), 17 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 1d8badf4a21..09e0fa052ef 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -623,6 +623,11 @@ DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 6ea9807b790..6d83953ee8f 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -1845,3 +1845,23 @@ DO_NEON_PAIRWISE(neon_pmax, max)
 DO_NEON_PAIRWISE(neon_pmin, min)
 
 #undef DO_NEON_PAIRWISE
+
+#define DO_VCVT_FIXED(NAME, FUNC, TYPE)                                 \
+    void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc)    \
+    {                                                                   \
+        intptr_t i, oprsz = simd_oprsz(desc);                           \
+        int shift = simd_data(desc);                                    \
+        TYPE *d = vd, *n = vn;                                          \
+        float_status *fpst = stat;                                      \
+        for (i = 0; i < oprsz / sizeof(TYPE); i++) {                    \
+            d[i] = FUNC(n[i], shift, fpst);                             \
+        }                                                               \
+        clear_tail(d, oprsz, simd_maxsz(desc));                         \
+    }
+
+DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t)
+DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t)
+DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t)
+DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t)
+
+#undef DO_VCVT_FIXED
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 5aaea867d8c..7e4324c5397 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -1608,17 +1608,24 @@ static bool trans_VSHLL_U_2sh(DisasContext *s, 
arg_2reg_shift *a)
 }
 
 static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
-                      NeonGenTwoSingleOpFn *fn)
+                      gen_helper_gvec_2_ptr *fn)
 {
     /* FP operations in 2-reg-and-shift group */
-    TCGv_i32 tmp, shiftv;
-    TCGv_ptr fpstatus;
-    int pass;
+    int vec_size = a->q ? 16 : 8;
+    int rd_ofs = neon_reg_offset(a->vd, 0);
+    int rm_ofs = neon_reg_offset(a->vm, 0);
+    TCGv_ptr fpst;
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
     }
 
+    if (a->size != 0) {
+        if (!dc_isar_feature(aa32_fp16_arith, s)) {
+            return false;
+        }
+    }
+
     /* UNDEF accesses to D16-D31 if they don't exist. */
     if (!dc_isar_feature(aa32_simd_r32, s) &&
         ((a->vd | a->vm) & 0x10)) {
@@ -1633,15 +1640,9 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
         return true;
     }
 
-    fpstatus = fpstatus_ptr(FPST_STD);
-    shiftv = tcg_const_i32(a->shift);
-    for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
-        tmp = neon_load_reg(a->vm, pass);
-        fn(tmp, tmp, shiftv, fpstatus);
-        neon_store_reg(a->vd, pass, tmp);
-    }
-    tcg_temp_free_ptr(fpstatus);
-    tcg_temp_free_i32(shiftv);
+    fpst = fpstatus_ptr(a->size ? FPST_STD_F16 : FPST_STD);
+    tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, vec_size, vec_size, a->shift, fn);
+    tcg_temp_free_ptr(fpst);
     return true;
 }
 
@@ -1651,10 +1652,10 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift 
*a,
         return do_fp_2sh(s, a, FUNC);                                   \
     }
 
-DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos)
-DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos)
-DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero)
-DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero)
+DO_FP_2SH(VCVT_SF, gen_helper_gvec_vcvt_sf)
+DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf)
+DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs)
+DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu)
 
 static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
 {
-- 
2.20.1