[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH v3 10/31] arm/translate-a64: add FP16 F[A]C[EQ/GE/GT
From: |
Alex Bennée |
Subject: |
[Qemu-devel] [PATCH v3 10/31] arm/translate-a64: add FP16 F[A]C[EQ/GE/GT] to simd_three_reg_same_fp16 |
Date: |
Fri, 23 Feb 2018 15:36:15 +0000 |
These use the generic float16_compare functionality which in turn uses
the common float_compare code from the softfloat re-factor.
Signed-off-by: Alex Bennée <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
---
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 931a6d3c34..d0b284fec4 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -594,3 +594,52 @@ 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 bac9469426..1cf40bda5e 100644
--- a/target/arm/helper-a64.h
+++ b/target/arm/helper-a64.h
@@ -56,3 +56,8 @@ DEF_HELPER_3(advsimd_addh, f16, f16, f16, ptr)
DEF_HELPER_3(advsimd_subh, f16, f16, f16, ptr)
DEF_HELPER_3(advsimd_mulh, f16, f16, f16, ptr)
DEF_HELPER_3(advsimd_divh, 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 f8770ee1e9..fb74dc1c45 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -10289,6 +10289,9 @@ 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;
@@ -10304,6 +10307,12 @@ 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;
@@ -10311,6 +10320,12 @@ static void
disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff);
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);
--
2.15.1
- [Qemu-devel] [PATCH v3 03/31] target/arm/cpu.h: update comment for half-precision values, (continued)
- [Qemu-devel] [PATCH v3 03/31] target/arm/cpu.h: update comment for half-precision values, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 02/31] target/arm/cpu64: introduce ARM_V8_FP16 feature bit, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 04/31] target/arm/cpu.h: add additional float_status flags, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 07/31] arm/translate-a64: handle_3same_64 comment fix, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 06/31] arm/translate-a64: implement half-precision F(MIN|MAX)(V|NMV), Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 05/31] target/arm/helper: pass explicit fpst to set_rmode, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 08/31] arm/translate-a64: initial decode for simd_three_reg_same_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 09/31] arm/translate-a64: add FP16 FADD/FABD/FSUB/FMUL/FDIV to simd_three_reg_same_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 10/31] arm/translate-a64: add FP16 F[A]C[EQ/GE/GT] to simd_three_reg_same_fp16,
Alex Bennée <=
- [Qemu-devel] [PATCH v3 16/31] arm/translate-a64: initial decode for simd_two_reg_misc_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 18/31] arm/translate-a64: add FCVTxx to simd_two_reg_misc_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 17/31] arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 13/31] arm/translate-a64: add FP16 pairwise ops simd_three_reg_same_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 30/31] arm/translate-a64: implement simd_scalar_three_reg_same_fp16, Alex Bennée, 2018/02/23
- [Qemu-devel] [PATCH v3 21/31] arm/translate-a64: add FP16 FNEG/FABS to simd_two_reg_misc_fp16, Alex Bennée, 2018/02/23