[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-stable] [PATCH v2 11/14] target/arm: Implement FCMP for fp16
From: |
Richard Henderson |
Subject: |
[Qemu-stable] [PATCH v2 11/14] target/arm: Implement FCMP for fp16 |
Date: |
Wed, 2 May 2018 15:15:49 -0700 |
From: Alex Bennée <address@hidden>
These where missed out from the rest of the half-precision work.
Cc: address@hidden
Signed-off-by: Alex Bennée <address@hidden>
[rth: Diagnose lack of FP16 before fp_access_check]
Signed-off-by: Richard Henderson <address@hidden>
---
target/arm/helper-a64.h | 2 ++
target/arm/helper-a64.c | 10 ++++++
target/arm/translate-a64.c | 88 +++++++++++++++++++++++++++++++++++++---------
3 files changed, 83 insertions(+), 17 deletions(-)
diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h
index ef4ddfe9d8..5c0b9bd799 100644
--- a/target/arm/helper-a64.h
+++ b/target/arm/helper-a64.h
@@ -19,6 +19,8 @@
DEF_HELPER_FLAGS_2(udiv64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
DEF_HELPER_FLAGS_2(sdiv64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
DEF_HELPER_FLAGS_1(rbit64, TCG_CALL_NO_RWG_SE, i64, i64)
+DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, ptr)
+DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, ptr)
DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr)
DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr)
DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr)
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index afb25ad20c..35df07adb9 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -85,6 +85,16 @@ static inline uint32_t float_rel_to_flags(int res)
return flags;
}
+uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status)
+{
+ return float_rel_to_flags(float16_compare_quiet(x, y, fp_status));
+}
+
+uint64_t HELPER(vfp_cmpeh_a64)(float16 x, float16 y, void *fp_status)
+{
+ return float_rel_to_flags(float16_compare(x, y, fp_status));
+}
+
uint64_t HELPER(vfp_cmps_a64)(float32 x, float32 y, void *fp_status)
{
return float_rel_to_flags(float32_compare_quiet(x, y, fp_status));
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 9322b0d896..f0aca20771 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -4475,14 +4475,14 @@ static void disas_data_proc_reg(DisasContext *s,
uint32_t insn)
}
}
-static void handle_fp_compare(DisasContext *s, bool is_double,
+static void handle_fp_compare(DisasContext *s, int size,
unsigned int rn, unsigned int rm,
bool cmp_with_zero, bool signal_all_nans)
{
TCGv_i64 tcg_flags = tcg_temp_new_i64();
- TCGv_ptr fpst = get_fpstatus_ptr(false);
+ TCGv_ptr fpst = get_fpstatus_ptr(size == MO_16);
- if (is_double) {
+ if (size == MO_64) {
TCGv_i64 tcg_vn, tcg_vm;
tcg_vn = read_fp_dreg(s, rn);
@@ -4499,19 +4499,35 @@ static void handle_fp_compare(DisasContext *s, bool
is_double,
tcg_temp_free_i64(tcg_vn);
tcg_temp_free_i64(tcg_vm);
} else {
- TCGv_i32 tcg_vn, tcg_vm;
+ TCGv_i32 tcg_vn = tcg_temp_new_i32();
+ TCGv_i32 tcg_vm = tcg_temp_new_i32();
- tcg_vn = read_fp_sreg(s, rn);
+ read_vec_element_i32(s, tcg_vn, rn, 0, size);
if (cmp_with_zero) {
- tcg_vm = tcg_const_i32(0);
+ tcg_gen_movi_i32(tcg_vm, 0);
} else {
- tcg_vm = read_fp_sreg(s, rm);
+ read_vec_element_i32(s, tcg_vm, rm, 0, size);
}
- if (signal_all_nans) {
- gen_helper_vfp_cmpes_a64(tcg_flags, tcg_vn, tcg_vm, fpst);
- } else {
- gen_helper_vfp_cmps_a64(tcg_flags, tcg_vn, tcg_vm, fpst);
+
+ switch (size) {
+ case MO_32:
+ if (signal_all_nans) {
+ gen_helper_vfp_cmpes_a64(tcg_flags, tcg_vn, tcg_vm, fpst);
+ } else {
+ gen_helper_vfp_cmps_a64(tcg_flags, tcg_vn, tcg_vm, fpst);
+ }
+ break;
+ case MO_16:
+ if (signal_all_nans) {
+ gen_helper_vfp_cmpeh_a64(tcg_flags, tcg_vn, tcg_vm, fpst);
+ } else {
+ gen_helper_vfp_cmph_a64(tcg_flags, tcg_vn, tcg_vm, fpst);
+ }
+ break;
+ default:
+ g_assert_not_reached();
}
+
tcg_temp_free_i32(tcg_vn);
tcg_temp_free_i32(tcg_vm);
}
@@ -4532,16 +4548,35 @@ static void handle_fp_compare(DisasContext *s, bool
is_double,
static void disas_fp_compare(DisasContext *s, uint32_t insn)
{
unsigned int mos, type, rm, op, rn, opc, op2r;
+ int size;
mos = extract32(insn, 29, 3);
- type = extract32(insn, 22, 2); /* 0 = single, 1 = double */
+ type = extract32(insn, 22, 2);
rm = extract32(insn, 16, 5);
op = extract32(insn, 14, 2);
rn = extract32(insn, 5, 5);
opc = extract32(insn, 3, 2);
op2r = extract32(insn, 0, 3);
- if (mos || op || op2r || type > 1) {
+ if (mos || op || op2r) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (type) {
+ case 0:
+ size = MO_32;
+ break;
+ case 1:
+ size = MO_64;
+ break;
+ case 3:
+ size = MO_16;
+ if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
+ break;
+ }
+ /* fallthru */
+ default:
unallocated_encoding(s);
return;
}
@@ -4550,7 +4585,7 @@ static void disas_fp_compare(DisasContext *s, uint32_t
insn)
return;
}
- handle_fp_compare(s, type, rn, rm, opc & 1, opc & 2);
+ handle_fp_compare(s, size, rn, rm, opc & 1, opc & 2);
}
/* Floating point conditional compare
@@ -4564,16 +4599,35 @@ static void disas_fp_ccomp(DisasContext *s, uint32_t
insn)
unsigned int mos, type, rm, cond, rn, op, nzcv;
TCGv_i64 tcg_flags;
TCGLabel *label_continue = NULL;
+ int size;
mos = extract32(insn, 29, 3);
- type = extract32(insn, 22, 2); /* 0 = single, 1 = double */
+ type = extract32(insn, 22, 2);
rm = extract32(insn, 16, 5);
cond = extract32(insn, 12, 4);
rn = extract32(insn, 5, 5);
op = extract32(insn, 4, 1);
nzcv = extract32(insn, 0, 4);
- if (mos || type > 1) {
+ if (mos) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (type) {
+ case 0:
+ size = MO_32;
+ break;
+ case 1:
+ size = MO_64;
+ break;
+ case 3:
+ size = MO_16;
+ if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
+ break;
+ }
+ /* fallthru */
+ default:
unallocated_encoding(s);
return;
}
@@ -4594,7 +4648,7 @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn)
gen_set_label(label_match);
}
- handle_fp_compare(s, type, rn, rm, false, op);
+ handle_fp_compare(s, size, rn, rm, false, op);
if (cond < 0x0e) {
gen_set_label(label_continue);
--
2.14.3
- [Qemu-stable] [PATCH v2 11/14] target/arm: Implement FCMP for fp16,
Richard Henderson <=