[PATCH v2 26/45] target/arm: Implement fp16 for VCEQ, VCGE, VCGT comparisons

[Peter Maydell]

Convert the Neon floating-point vector comparison ops VCEQ,
VCGE and VCGT over to using a gvec helper and use this to
implement the fp16 case.

(We put the float16_ceq() etc functions above the DO_2OP()
macro definition because later when we convert the
compare-against-zero instructions we'll want their
definitions to be visible at that point in the source file.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h             |  9 +++++++
 target/arm/vec_helper.c         | 44 +++++++++++++++++++++++++++++++++
 target/arm/translate-neon.c.inc |  6 ++---
 3 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index aa1ac75571f..a05a0d1a427 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -632,6 +632,15 @@ DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fcgt_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 988d5784e83..f60968f4997 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -656,6 +656,41 @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
+/*
+ * Floating point comparisons producing an integer result (all 1s or all 0s).
+ * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do.
+ * Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires.
+ */
+static uint16_t float16_ceq(float16 op1, float16 op2, float_status *stat)
+{
+    return -float16_eq_quiet(op1, op2, stat);
+}
+
+static uint32_t float32_ceq(float32 op1, float32 op2, float_status *stat)
+{
+    return -float32_eq_quiet(op1, op2, stat);
+}
+
+static uint16_t float16_cge(float16 op1, float16 op2, float_status *stat)
+{
+    return -float16_le(op2, op1, stat);
+}
+
+static uint32_t float32_cge(float32 op1, float32 op2, float_status *stat)
+{
+    return -float32_le(op2, op1, stat);
+}
+
+static uint16_t float16_cgt(float16 op1, float16 op2, float_status *stat)
+{
+    return -float16_lt(op2, op1, stat);
+}
+
+static uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat)
+{
+    return -float32_lt(op2, op1, stat);
+}
+
 #define DO_2OP(NAME, FUNC, TYPE) \
 void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc)  \
 {                                                                 \
@@ -747,6 +782,15 @@ DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64)
 DO_3OP(gvec_fabd_h, float16_abd, float16)
 DO_3OP(gvec_fabd_s, float32_abd, float32)
 
+DO_3OP(gvec_fceq_h, float16_ceq, float16)
+DO_3OP(gvec_fceq_s, float32_ceq, float32)
+
+DO_3OP(gvec_fcge_h, float16_cge, float16)
+DO_3OP(gvec_fcge_s, float32_cge, float32)
+
+DO_3OP(gvec_fcgt_h, float16_cgt, float16)
+DO_3OP(gvec_fcgt_s, float32_cgt, float32)
+
 #ifdef TARGET_AARCH64
 
 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16)
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index a1bf8dcee09..94871f8597d 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -1112,6 +1112,9 @@ DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s, 
gen_helper_gvec_fadd_h)
 DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_h)
 DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_h)
 DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h)
+DO_3S_FP_GVEC(VCEQ, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_h)
+DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h)
+DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h)
 
 /*
  * For all the functions using this macro, size == 1 means fp16,
@@ -1127,9 +1130,6 @@ DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, 
gen_helper_gvec_fmul_h)
         return do_3same_fp(s, a, FUNC, READS_VD);                   \
     }
 
-DO_3S_FP(VCEQ, gen_helper_neon_ceq_f32, false)
-DO_3S_FP(VCGE, gen_helper_neon_cge_f32, false)
-DO_3S_FP(VCGT, gen_helper_neon_cgt_f32, false)
 DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false)
 DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false)
 DO_3S_FP(VMAX, gen_helper_vfp_maxs, false)
-- 
2.20.1