Re: [Qemu-devel] [PATCH v5 16/35] target/arm: Implement SVE floating-point compare vectors

[Richard Henderson]

On 06/25/2018 10:20 AM, Peter Maydell wrote:
>> +#define DO_FCMGE(TYPE, X, Y, ST)  TYPE##_compare(Y, X, ST) <= 0
> 
> I was expecting the RHS of this to be TYPE##_le(Y, X, ST).
> This prompted me to notice that softfloat has as well as
> the generic 'compare' routines also specialized _le/lt/unordered
> etc functions for float64 and float32 but not float16, which is
> a bit inconsistent...

Yes.  I have a mild preference to using floatN_compare everywhere and removing
the other functions entirely.  But that's a medium sized job across multiple
targets.  I also agree that in the meantime the inconsistency is surprising.


r~

Re: [Qemu-devel] [PATCH v5 16/35] target/arm: Implement SVE floating-point compare vectors

[Peter Maydell]

On 21 June 2018 at 02:53, Richard Henderson
 wrote:
> Signed-off-by: Richard Henderson 
> ---
>  target/arm/helper-sve.h| 49 ++
>  target/arm/sve_helper.c| 62 ++
>  target/arm/translate-sve.c | 40 
>  target/arm/sve.decode  | 11 +++
>  4 files changed, 162 insertions(+)


> +#define DO_FCMGE(TYPE, X, Y, ST)  TYPE##_compare(Y, X, ST) <= 0

I was expecting the RHS of this to be TYPE##_le(Y, X, ST).
This prompted me to notice that softfloat has as well as
the generic 'compare' routines also specialized _le/lt/unordered
etc functions for float64 and float32 but not float16, which is
a bit inconsistent...

> +#define DO_FCMGT(TYPE, X, Y, ST)  TYPE##_compare(Y, X, ST) < 0
> +#define DO_FCMEQ(TYPE, X, Y, ST)  TYPE##_compare_quiet(X, Y, ST) == 0
> +#define DO_FCMNE(TYPE, X, Y, ST)  TYPE##_compare_quiet(X, Y, ST) != 0
> +#define DO_FCMUO(TYPE, X, Y, ST)  \
> +TYPE##_compare_quiet(X, Y, ST) == float_relation_unordered
> +#define DO_FACGE(TYPE, X, Y, ST)  \
> +TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) <= 0
> +#define DO_FACGT(TYPE, X, Y, ST)  \
> +TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) < 0

Anyway,
Reviewed-by: Peter Maydell 

thanks
-- PMM

[Qemu-devel] [PATCH v5 16/35] target/arm: Implement SVE floating-point compare vectors

[Richard Henderson]

Signed-off-by: Richard Henderson 
---
 target/arm/helper-sve.h| 49 ++
 target/arm/sve_helper.c| 62 ++
 target/arm/translate-sve.c | 40 
 target/arm/sve.decode  | 11 +++
 4 files changed, 162 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 55e8a908d4..6089b3a53f 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -839,6 +839,55 @@ DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_6(sve_fcmge_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmge_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmge_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmgt_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmgt_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmgt_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmeq_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmeq_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmeq_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmne_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmne_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmne_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmuo_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmuo_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmuo_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_facge_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facge_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facge_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_facgt_h, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facgt_s, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facgt_d, TCG_CALL_NO_RWG,
+   void, ptr, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 38f7cc2274..2fd34d722b 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -3193,6 +3193,68 @@ void HELPER(sve_fnmls_zpzzz_d)(CPUARMState *env, void 
*vg, uint32_t desc)
 do_fmla_zpzzz_d(env, vg, desc, 0, INT64_MIN);
 }
 
+/* Two operand floating-point comparison controlled by a predicate.
+ * Unlike the integer version, we are not allowed to optimistically
+ * compare operands, since the comparison may have side effects wrt
+ * the FPSR.
+ */
+#define DO_FPCMP_PPZZ(NAME, TYPE, H, OP)\
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg,   \
+  void *status, uint32_t desc)  \
+{   \
+intptr_t i = simd_oprsz(desc), j = (i - 1) >> 6;\
+uint64_t *d = vd, *g = vg;  \
+do {\
+uint64_t out = 0, pg = g[j];\
+do {\
+i -= sizeof(TYPE), out <<= sizeof(TYPE);\
+if (likely((pg >> (i & 63)) & 1)) { \
+TYPE nn = *(TYPE *)(vn + H(i)); \
+TYPE mm = *(TYPE *)(vm + H(i)); \
+out |= OP(TYPE, nn, mm, status);\
+}   \
+} while (i & 63);   \
+d[j--] = out;   \
+} while (i > 0);\