[PULL 32/47] target/arm: Implement fp16 for Neon VRECPS

[Peter Maydell]

Convert the Neon VRECPS insn to using a gvec helper, and
use this to implement the fp16 case.

The phrasing of the new float32_recps_nf() is slightly different from
the old recps_f32() so that it parallels the f16 version; for f16 we
can't assume that flush-to-zero is always enabled.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-34-peter.maydell@linaro.org
---
 target/arm/helper.h             |  4 +++-
 target/arm/vec_helper.c         | 31 +++++++++++++++++++++++++++++++
 target/arm/vfp_helper.c         | 13 -------------
 target/arm/translate-neon.c.inc | 21 +--------------------
 4 files changed, 35 insertions(+), 34 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index bf2b9a7d028..114039c4c33 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -225,7 +225,6 @@ DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr)
 DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr)
 DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr)
 
-DEF_HELPER_3(recps_f32, f32, env, f32, f32)
 DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32)
 DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr)
 DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
@@ -674,6 +673,9 @@ DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, ptr, i3
 DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, 
i32)
 DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, 
i32)
 
+DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, 
i32)
+DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, 
i32)
+
 DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 072bcd1a9d5..0111a230244 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -797,6 +797,34 @@ static float32 float32_abd(float32 op1, float32 op2, 
float_status *stat)
     return float32_abs(float32_sub(op1, op2, stat));
 }
 
+/*
+ * Reciprocal step. These are the AArch32 version which uses a
+ * non-fused multiply-and-subtract.
+ */
+static float16 float16_recps_nf(float16 op1, float16 op2, float_status *stat)
+{
+    op1 = float16_squash_input_denormal(op1, stat);
+    op2 = float16_squash_input_denormal(op2, stat);
+
+    if ((float16_is_infinity(op1) && float16_is_zero(op2)) ||
+        (float16_is_infinity(op2) && float16_is_zero(op1))) {
+        return float16_two;
+    }
+    return float16_sub(float16_two, float16_mul(op1, op2, stat), stat);
+}
+
+static float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat)
+{
+    op1 = float32_squash_input_denormal(op1, stat);
+    op2 = float32_squash_input_denormal(op2, stat);
+
+    if ((float32_is_infinity(op1) && float32_is_zero(op2)) ||
+        (float32_is_infinity(op2) && float32_is_zero(op1))) {
+        return float32_two;
+    }
+    return float32_sub(float32_two, float32_mul(op1, op2, stat), stat);
+}
+
 #define DO_3OP(NAME, FUNC, TYPE) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
 {                                                                          \
@@ -854,6 +882,9 @@ DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32)
 DO_3OP(gvec_fminnum_h, float16_minnum, float16)
 DO_3OP(gvec_fminnum_s, float32_minnum, float32)
 
+DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16)
+DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32)
+
 #ifdef TARGET_AARCH64
 
 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16)
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index 586dfd22e5e..1f452409d4d 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -529,19 +529,6 @@ uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void 
*fpstp, uint32_t ahp_mode)
     return r;
 }
 
-float32 HELPER(recps_f32)(CPUARMState *env, float32 a, float32 b)
-{
-    float_status *s = &env->vfp.standard_fp_status;
-    if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) ||
-        (float32_is_infinity(b) && float32_is_zero_or_denormal(a))) {
-        if (!(float32_is_zero(a) || float32_is_zero(b))) {
-            float_raise(float_flag_input_denormal, s);
-        }
-        return float32_two;
-    }
-    return float32_sub(float32_two, float32_mul(a, b, s), s);
-}
-
 float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b)
 {
     float_status *s = &env->vfp.standard_fp_status;
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 90350c3d531..63e7be8e01d 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -1074,6 +1074,7 @@ 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)
+DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_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)
@@ -1110,26 +1111,6 @@ static bool trans_VMINNM_fp_3s(DisasContext *s, 
arg_3same *a)
     return do_3same(s, a, gen_VMINNM_fp32_3s);
 }
 
-WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32)
-
-static void gen_VRECPS_fp_3s(unsigned vece, uint32_t rd_ofs,
-                             uint32_t rn_ofs, uint32_t rm_ofs,
-                             uint32_t oprsz, uint32_t maxsz)
-{
-    static const GVecGen3 ops = { .fni4 = gen_VRECPS_tramp };
-    tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops);
-}
-
-static bool trans_VRECPS_fp_3s(DisasContext *s, arg_3same *a)
-{
-    if (a->size != 0) {
-        /* TODO fp16 support */
-        return false;
-    }
-
-    return do_3same(s, a, gen_VRECPS_fp_3s);
-}
-
 WRAP_ENV_FN(gen_VRSQRTS_tramp, gen_helper_rsqrts_f32)
 
 static void gen_VRSQRTS_fp_3s(unsigned vece, uint32_t rd_ofs,
-- 
2.20.1