target/arm: Implement fp16 for Neon VRECPS

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

1 files changed, 31 insertions, 0 deletions

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 072bcd1a9d..0111a23024 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)