[v2,11/32] arm/translate-a64: add FP16 F[A]C[EQ/GE/GT] to simd_three_reg_same_fp16

Message ID 20180208173157.24705-12-alex.bennee@linaro.org
State New
Headers show
Series
  • Add ARMv8.2 half-precision functions
Related show

Commit Message

Alex Bennée Feb. 8, 2018, 5:31 p.m.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

---
 target/arm/helper-a64.c    | 49 ++++++++++++++++++++++++++++++++++++++++++++++
 target/arm/helper-a64.h    |  5 +++++
 target/arm/translate-a64.c | 15 ++++++++++++++
 3 files changed, 69 insertions(+)

-- 
2.15.1

Comments

Richard Henderson Feb. 8, 2018, 8:54 p.m. | #1
On 02/08/2018 09:31 AM, Alex Bennée wrote:
> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

> ---

>  target/arm/helper-a64.c    | 49 ++++++++++++++++++++++++++++++++++++++++++++++

>  target/arm/helper-a64.h    |  5 +++++

>  target/arm/translate-a64.c | 15 ++++++++++++++

>  3 files changed, 69 insertions(+)

> 

> diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c

> index 25e45121af..78eeda31d1 100644

> --- a/target/arm/helper-a64.c

> +++ b/target/arm/helper-a64.c

> @@ -599,3 +599,52 @@ ADVSIMD_HALFOP(min)

>  ADVSIMD_HALFOP(max)

>  ADVSIMD_HALFOP(minnum)

>  ADVSIMD_HALFOP(maxnum)

> +

> +/*

> + * Floating point comparisons produce an integer result. Softfloat

> + * routines return float_relation types which we convert to the 0/-1

> + * Neon requires.

> + */

> +

> +#define ADVSIMD_CMPRES(test) (test) ? 0xffff : 0

> +

> +uint32_t HELPER(advsimd_ceq_f16)(float16 a, float16 b, void *fpstp)

> +{

> +    float_status *fpst = fpstp;

> +    int compare = float16_compare_quiet(a, b, fpst);

> +    return ADVSIMD_CMPRES(compare == float_relation_equal);


Not using float16_eq etc?

> +}

> +

> +uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp)

> +{

> +    float_status *fpst = fpstp;

> +    int compare = float16_compare(a, b, fpst);

> +    return ADVSIMD_CMPRES(compare == float_relation_greater ||

> +                          compare == float_relation_equal);


Especially float16_le(b, a, fpst).

Otherwise,

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>



r~

Patch

diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index 25e45121af..78eeda31d1 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -599,3 +599,52 @@  ADVSIMD_HALFOP(min)
 ADVSIMD_HALFOP(max)
 ADVSIMD_HALFOP(minnum)
 ADVSIMD_HALFOP(maxnum)
+
+/*
+ * Floating point comparisons produce an integer result. Softfloat
+ * routines return float_relation types which we convert to the 0/-1
+ * Neon requires.
+ */
+
+#define ADVSIMD_CMPRES(test) (test) ? 0xffff : 0
+
+uint32_t HELPER(advsimd_ceq_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    int compare = float16_compare_quiet(a, b, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_equal);
+}
+
+uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    int compare = float16_compare(a, b, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater ||
+                          compare == float_relation_equal);
+}
+
+uint32_t HELPER(advsimd_cgt_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    int compare = float16_compare(a, b, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater);
+}
+
+uint32_t HELPER(advsimd_acge_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    float16 f0 = float16_abs(a);
+    float16 f1 = float16_abs(b);
+    int compare = float16_compare(f0, f1, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater ||
+                          compare == float_relation_equal);
+}
+
+uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    float16 f0 = float16_abs(a);
+    float16 f1 = float16_abs(b);
+    int compare = float16_compare(f0, f1, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater);
+}
diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h
index 5cbabcc27a..e701644ae7 100644
--- a/target/arm/helper-a64.h
+++ b/target/arm/helper-a64.h
@@ -57,3 +57,8 @@  DEF_HELPER_3(advsimd_maxh, f16, f16, f16, ptr)
 DEF_HELPER_3(advsimd_minh, f16, f16, f16, ptr)
 DEF_HELPER_3(advsimd_maxnumh, f16, f16, f16, ptr)
 DEF_HELPER_3(advsimd_minnumh, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_ceq_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_cge_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_cgt_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_acge_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_acgt_f16, i32, f16, f16, ptr)
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 93d71d8b2c..14572f26e1 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -9855,6 +9855,9 @@  static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
         case 0x2: /* FADD */
             gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst);
             break;
+        case 0x4: /* FCMEQ */
+            gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+            break;
         case 0x6: /* FMAX */
             gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst);
             break;
@@ -9870,6 +9873,12 @@  static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
         case 0x13: /* FMUL */
             gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst);
             break;
+        case 0x14: /* FCMGE */
+            gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+            break;
+        case 0x15: /* FACGE */
+            gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+            break;
         case 0x17: /* FDIV */
             gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst);
             break;
@@ -9877,6 +9886,12 @@  static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
             gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
             gen_helper_advsimd_absh(tcg_res, tcg_res);
             break;
+        case 0x1c: /* FCMGT */
+            gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+            break;
+        case 0x1d: /* FACGT */
+            gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+            break;
         default:
             fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
                     __func__, insn, fpopcode, s->pc);