izzy/xemu
0
0
Fork 0
mirror of https://github.com/izzy2lost/xemu.git synced 2026-07-06 00:20:22 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200901' into staging

Browse Source 
target-arm queue:
 * Implement fp16 support for AArch32 VFP and Neon
 * hw/arm/sbsa-ref: add "reg" property to DT cpu nodes
 * hw/arm/sbsa-ref : Add embedded controller in secure memory

# gpg: Signature made Tue 01 Sep 2020 16:17:23 BST
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20200901: (47 commits)
  hw/arm/sbsa-ref : Add embedded controller in secure memory
  hw/misc/sbsa_ec : Add an embedded controller for sbsa-ref
  hw/arm/sbsa-ref: add "reg" property to DT cpu nodes
  target/arm: Enable FP16 in '-cpu max'
  target/arm: Implement fp16 for Neon VMUL, VMLA, VMLS
  target/arm/vec_helper: Add gvec fp indexed multiply-and-add operations
  target/arm/vec_helper: Handle oprsz less than 16 bytes in indexed operations
  target/arm: Implement fp16 for Neon VRINTX
  target/arm: Implement fp16 for Neon VRINT-with-specified-rounding-mode
  target/arm: Implement fp16 for Neon VCVT with rounding modes
  target/arm: Implement fp16 for Neon VCVT fixed-point
  target/arm: Convert Neon VCVT fixed-point to gvec
  target/arm: Implement fp16 for Neon float-integer VCVT
  target/arm: Implement fp16 for Neon pairwise fp ops
  target/arm: Implement fp16 for Neon VRSQRTS
  target/arm: Implement fp16 for Neon VRECPS
  target/arm: Implement fp16 for Neon fp compare-vs-0
  target/arm: Implement fp16 for Neon VFMA, VMFS
  target/arm: Implement fp16 for Neon VMLA, VMLS operations
  target/arm: Implement fp16 for Neon VMAXNM, VMINNM
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell
2020-09-01 16:51:37 +01:00
parent 071a6dba7d 3f462bf0f6
commit 8d90bfc5c3
16 changed files with 1819 additions and 801 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hw/arm/sbsa-ref.c
+37 -6
View File
@@ -62,6 +62,7 @@ enum {
SBSA_CPUPERIPHS,
SBSA_GIC_DIST,
SBSA_GIC_REDIST,
SBSA_SECURE_EC,
SBSA_SMMU,
SBSA_UART,
SBSA_RTC,
@@ -107,6 +108,7 @@ static const MemMapEntry sbsa_ref_memmap[] = {
[SBSA_CPUPERIPHS] = { 0x40000000, 0x00040000 },
[SBSA_GIC_DIST] = { 0x40060000, 0x00010000 },
[SBSA_GIC_REDIST] = { 0x40080000, 0x04000000 },
[SBSA_SECURE_EC] = { 0x50000000, 0x00001000 },
[SBSA_UART] = { 0x60000000, 0x00001000 },
[SBSA_RTC] = { 0x60010000, 0x00001000 },
[SBSA_GPIO] = { 0x60020000, 0x00001000 },
@@ -138,6 +140,12 @@ static const int sbsa_ref_irqmap[] = {
[SBSA_EHCI] = 11,
};
static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx)
{
uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER;
return arm_cpu_mp_affinity(idx, clustersz);
}
/*
* Firmware on this machine only uses ACPI table to load OS, these limited
* device tree nodes are just to let firmware know the info which varies from
@@ -183,14 +191,31 @@ static void create_fdt(SBSAMachineState *sms)
g_free(matrix);
}
/*
* From Documentation/devicetree/bindings/arm/cpus.yaml
* On ARM v8 64-bit systems this property is required
* and matches the MPIDR_EL1 register affinity bits.
*
* * If cpus node's #address-cells property is set to 2
*
* The first reg cell bits [7:0] must be set to
* bits [39:32] of MPIDR_EL1.
*
* The second reg cell bits [23:0] must be set to
* bits [23:0] of MPIDR_EL1.
*/
qemu_fdt_add_subnode(sms->fdt, "/cpus");
qemu_fdt_setprop_cell(sms->fdt, "/cpus", "#address-cells", 2);
qemu_fdt_setprop_cell(sms->fdt, "/cpus", "#size-cells", 0x0);
for (cpu = sms->smp_cpus - 1; cpu >= 0; cpu--) {
char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu);
ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu));
CPUState *cs = CPU(armcpu);
uint64_t mpidr = sbsa_ref_cpu_mp_affinity(sms, cpu);
qemu_fdt_add_subnode(sms->fdt, nodename);
qemu_fdt_setprop_u64(sms->fdt, nodename, "reg", mpidr);
if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) {
qemu_fdt_setprop_cell(sms->fdt, nodename, "numa-node-id",
@@ -585,6 +610,16 @@ static void *sbsa_ref_dtb(const struct arm_boot_info *binfo, int *fdt_size)
return board->fdt;
}
static void create_secure_ec(MemoryRegion *mem)
{
hwaddr base = sbsa_ref_memmap[SBSA_SECURE_EC].base;
DeviceState *dev = qdev_new("sbsa-ec");
SysBusDevice *s = SYS_BUS_DEVICE(dev);
memory_region_add_subregion(mem, base,
sysbus_mmio_get_region(s, 0));
}
static void sbsa_ref_init(MachineState *machine)
{
unsigned int smp_cpus = machine->smp.cpus;
@@ -708,6 +743,8 @@ static void sbsa_ref_init(MachineState *machine)
create_pcie(sms);
create_secure_ec(secure_sysmem);
sms->bootinfo.ram_size = machine->ram_size;
sms->bootinfo.nb_cpus = smp_cpus;
sms->bootinfo.board_id = -1;
@@ -717,12 +754,6 @@ static void sbsa_ref_init(MachineState *machine)
arm_load_kernel(ARM_CPU(first_cpu), machine, &sms->bootinfo);
}
static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx)
{
uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER;
return arm_cpu_mp_affinity(idx, clustersz);
}
static const CPUArchIdList *sbsa_ref_possible_cpu_arch_ids(MachineState *ms)
{
unsigned int max_cpus = ms->smp.max_cpus;
hw/misc/meson.build
+2
View File
@@ -97,3 +97,5 @@ specific_ss.add(when: 'CONFIG_MAC_VIA', if_true: files('mac_via.c'))
specific_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_cmgcr.c', 'mips_cpc.c'))
specific_ss.add(when: 'CONFIG_MIPS_ITU', if_true: files('mips_itu.c'))
specific_ss.add(when: 'CONFIG_SBSA_REF', if_true: files('sbsa_ec.c'))
hw/misc/sbsa_ec.c
+98
View File
@@ -0,0 +1,98 @@
/*
* ARM SBSA Reference Platform Embedded Controller
*
* A device to allow PSCI running in the secure side of sbsa-ref machine
* to communicate platform power states to qemu.
*
* Copyright (c) 2020 Nuvia Inc
* Written by Graeme Gregory <graeme@nuviainc.com>
*
* SPDX-License-Identifer: GPL-2.0-or-later
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/log.h"
#include "hw/sysbus.h"
#include "sysemu/runstate.h"
typedef struct {
SysBusDevice parent_obj;
MemoryRegion iomem;
} SECUREECState;
#define TYPE_SBSA_EC "sbsa-ec"
#define SECURE_EC(obj) OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_EC)
enum sbsa_ec_powerstates {
SBSA_EC_CMD_POWEROFF = 0x01,
SBSA_EC_CMD_REBOOT = 0x02,
};
static uint64_t sbsa_ec_read(void *opaque, hwaddr offset, unsigned size)
{
/* No use for this currently */
qemu_log_mask(LOG_GUEST_ERROR, "sbsa-ec: no readable registers");
return 0;
}
static void sbsa_ec_write(void *opaque, hwaddr offset,
uint64_t value, unsigned size)
{
if (offset == 0) { /* PSCI machine power command register */
switch (value) {
case SBSA_EC_CMD_POWEROFF:
qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
break;
case SBSA_EC_CMD_REBOOT:
qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
break;
default:
qemu_log_mask(LOG_GUEST_ERROR,
"sbsa-ec: unknown power command");
}
} else {
qemu_log_mask(LOG_GUEST_ERROR, "sbsa-ec: unknown EC register");
}
}
static const MemoryRegionOps sbsa_ec_ops = {
.read = sbsa_ec_read,
.write = sbsa_ec_write,
.endianness = DEVICE_NATIVE_ENDIAN,
.valid.min_access_size = 4,
.valid.max_access_size = 4,
};
static void sbsa_ec_init(Object *obj)
{
SECUREECState *s = SECURE_EC(obj);
SysBusDevice *dev = SYS_BUS_DEVICE(obj);
memory_region_init_io(&s->iomem, obj, &sbsa_ec_ops, s, "sbsa-ec",
0x1000);
sysbus_init_mmio(dev, &s->iomem);
}
static void sbsa_ec_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
/* No vmstate or reset required: device has no internal state */
dc->user_creatable = false;
}
static const TypeInfo sbsa_ec_info = {
.name = TYPE_SBSA_EC,
.parent = TYPE_SYS_BUS_DEVICE,
.instance_size = sizeof(SECUREECState),
.instance_init = sbsa_ec_init,
.class_init = sbsa_ec_class_init,
};
static void sbsa_ec_register_type(void)
{
type_register_static(&sbsa_ec_info);
}
type_init(sbsa_ec_register_type);
target/arm/cpu.c
+2 -1
View File
@@ -2143,7 +2143,8 @@ static void arm_max_initfn(Object *obj)
cpu->isar.id_isar6 = t;
t = cpu->isar.mvfr1;
t = FIELD_DP32(t, MVFR1, FPHP, 2); /* v8.0 FP support */
t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */
t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */
cpu->isar.mvfr1 = t;
t = cpu->isar.mvfr2;
target/arm/cpu.h
+1 -6
View File
@@ -3519,12 +3519,7 @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id)
static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id)
{
/*
* This is a placeholder for use by VCMA until the rest of
* the ARMv8.2-FP16 extension is implemented for aa32 mode.
* At which point we can properly set and check MVFR1.FPHP.
*/
return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1;
return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3;
}
static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id)
target/arm/cpu64.c
+4 -6
View File
@@ -704,12 +704,10 @@ static void aarch64_max_initfn(Object *obj)
u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */
cpu->isar.id_dfr0 = u;
/*
* FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet,
* so do not set MVFR1.FPHP. Strictly speaking this is not legal,
* but it is also not legal to enable SVE without support for FP16,
* and enabling SVE in system mode is more useful in the short term.
*/
u = cpu->isar.mvfr1;
u = FIELD_DP32(u, MVFR1, FPHP, 3); /* v8.2-FP16 */
u = FIELD_DP32(u, MVFR1, SIMDHP, 2); /* v8.2-FP16 */
cpu->isar.mvfr1 = u;
#ifdef CONFIG_USER_ONLY
/* For usermode -cpu max we can use a larger and more efficient DCZ
target/arm/helper-a64.c
-11
View File
@@ -234,17 +234,6 @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp)
* versions, these do a fully fused multiply-add or
* multiply-add-and-halve.
*/
#define float16_two make_float16(0x4000)
#define float16_three make_float16(0x4200)
#define float16_one_point_five make_float16(0x3e00)
#define float32_two make_float32(0x40000000)
#define float32_three make_float32(0x40400000)
#define float32_one_point_five make_float32(0x3fc00000)
#define float64_two make_float64(0x4000000000000000ULL)
#define float64_three make_float64(0x4008000000000000ULL)
#define float64_one_point_five make_float64(0x3FF8000000000000ULL)
uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp)
{
target/arm/helper.h
+130 -3
View File
@@ -101,30 +101,43 @@ DEF_HELPER_FLAGS_5(probe_access, TCG_CALL_NO_WG, void, env, tl, i32, i32, i32)
DEF_HELPER_1(vfp_get_fpscr, i32, env)
DEF_HELPER_2(vfp_set_fpscr, void, env, i32)
DEF_HELPER_3(vfp_addh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_adds, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_addd, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_subh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_subs, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_subd, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_mulh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_muls, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_muld, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_divh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_divs, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_divd, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_maxh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_maxs, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_maxd, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_minh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_mins, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_mind, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_maxnumh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_maxnums, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr)
DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr)
DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr)
DEF_HELPER_1(vfp_negh, f16, f16)
DEF_HELPER_1(vfp_negs, f32, f32)
DEF_HELPER_1(vfp_negd, f64, f64)
DEF_HELPER_1(vfp_absh, f16, f16)
DEF_HELPER_1(vfp_abss, f32, f32)
DEF_HELPER_1(vfp_absd, f64, f64)
DEF_HELPER_2(vfp_sqrth, f16, f16, env)
DEF_HELPER_2(vfp_sqrts, f32, f32, env)
DEF_HELPER_2(vfp_sqrtd, f64, f64, env)
DEF_HELPER_3(vfp_cmph, void, f16, f16, env)
DEF_HELPER_3(vfp_cmps, void, f32, f32, env)
DEF_HELPER_3(vfp_cmpd, void, f64, f64, env)
DEF_HELPER_3(vfp_cmpeh, void, f16, f16, env)
DEF_HELPER_3(vfp_cmpes, void, f32, f32, env)
DEF_HELPER_3(vfp_cmped, void, f64, f64, env)
@@ -151,6 +164,10 @@ DEF_HELPER_2(vfp_tosizh, s32, f16, ptr)
DEF_HELPER_2(vfp_tosizs, s32, f32, ptr)
DEF_HELPER_2(vfp_tosizd, s32, f64, ptr)
DEF_HELPER_3(vfp_toshh_round_to_zero, i32, f16, i32, ptr)
DEF_HELPER_3(vfp_toslh_round_to_zero, i32, f16, i32, ptr)
DEF_HELPER_3(vfp_touhh_round_to_zero, i32, f16, i32, ptr)
DEF_HELPER_3(vfp_toulh_round_to_zero, i32, f16, i32, ptr)
DEF_HELPER_3(vfp_toshs_round_to_zero, i32, f32, i32, ptr)
DEF_HELPER_3(vfp_tosls_round_to_zero, i32, f32, i32, ptr)
DEF_HELPER_3(vfp_touhs_round_to_zero, i32, f32, i32, ptr)
@@ -189,13 +206,14 @@ DEF_HELPER_3(vfp_sqtod, f64, i64, i32, ptr)
DEF_HELPER_3(vfp_uhtod, f64, i64, i32, ptr)
DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr)
DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr)
DEF_HELPER_3(vfp_shtoh, f16, i32, i32, ptr)
DEF_HELPER_3(vfp_uhtoh, f16, i32, i32, ptr)
DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr)
DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr)
DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr)
DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr)
DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr)
DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env)
DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f32, TCG_CALL_NO_RWG, f32, f16, ptr, i32)
DEF_HELPER_FLAGS_3(vfp_fcvt_f32_to_f16, TCG_CALL_NO_RWG, f16, f32, ptr, i32)
@@ -204,9 +222,8 @@ DEF_HELPER_FLAGS_3(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, ptr, i32)
DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr)
DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr)
DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr)
DEF_HELPER_3(recps_f32, f32, env, f32, f32)
DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32)
DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr)
DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
@@ -222,8 +239,10 @@ DEF_HELPER_3(shr_cc, i32, env, i32, i32)
DEF_HELPER_3(sar_cc, i32, env, i32, i32)
DEF_HELPER_3(ror_cc, i32, env, i32, i32)
DEF_HELPER_FLAGS_2(rinth_exact, TCG_CALL_NO_RWG, f16, f16, ptr)
DEF_HELPER_FLAGS_2(rints_exact, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, ptr)
DEF_HELPER_FLAGS_2(rinth, TCG_CALL_NO_RWG, f16, f16, ptr)
DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, ptr)
@@ -587,6 +606,43 @@ DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
@@ -595,6 +651,21 @@ DEF_HELPER_FLAGS_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
@@ -607,8 +678,54 @@ DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
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_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_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,
@@ -623,6 +740,16 @@ DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
target/arm/neon-dp.decode
+7 -1
View File
@@ -254,6 +254,8 @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
# We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings.
@2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5
@2reg_vcvt_f16 .... ... . . . 11 .... .... .... . q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s
@@ -370,7 +372,11 @@ VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h
VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b
# VCVT fixed<->float conversions
# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101
VCVT_SH_2sh 1111 001 0 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16
VCVT_UH_2sh 1111 001 1 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16
VCVT_HS_2sh 1111 001 0 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16
VCVT_HU_2sh 1111 001 1 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16
VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt
target/arm/translate-neon.c.inc
+250 -505
View File
File diff suppressed because it is too large Load Diff
target/arm/translate-sve.c
-4
View File
@@ -3803,10 +3803,6 @@ static bool trans_##NAME##_zpzi(DisasContext *s, arg_rpri_esz *a) \
return true; \
}
#define float16_two make_float16(0x4000)
#define float32_two make_float32(0x40000000)
#define float64_two make_float64(0x4000000000000000ULL)
DO_FP_IMM(FADD, fadds, half, one)
DO_FP_IMM(FSUB, fsubs, half, one)
DO_FP_IMM(FMUL, fmuls, half, two)
target/arm/translate-vfp.c.inc
+728 -82
View File
File diff suppressed because it is too large Load Diff
target/arm/vec_helper.c
+422 -9
View File
File diff suppressed because it is too large Load Diff
target/arm/vfp-uncond.decode
+21 -6
View File
@@ -44,10 +44,15 @@
@vfp_dnm_s ................................ vm=%vm_sp vn=%vn_sp vd=%vd_sp
@vfp_dnm_d ................................ vm=%vm_dp vn=%vn_dp vd=%vd_dp
VSEL 1111 1110 0. cc:2 .... .... 1001 .0.0 .... \
vm=%vm_sp vn=%vn_sp vd=%vd_sp sz=1
VSEL 1111 1110 0. cc:2 .... .... 1010 .0.0 .... \
vm=%vm_sp vn=%vn_sp vd=%vd_sp dp=0
vm=%vm_sp vn=%vn_sp vd=%vd_sp sz=2
VSEL 1111 1110 0. cc:2 .... .... 1011 .0.0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1
vm=%vm_dp vn=%vn_dp vd=%vd_dp sz=3
VMAXNM_hp 1111 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s
VMINNM_hp 1111 1110 1.00 .... .... 1001 .1.0 .... @vfp_dnm_s
VMAXNM_sp 1111 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s
VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @vfp_dnm_s
@@ -55,13 +60,23 @@ VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @vfp_dnm_s
VMAXNM_dp 1111 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d
VMINNM_dp 1111 1110 1.00 .... .... 1011 .1.0 .... @vfp_dnm_d
VRINT 1111 1110 1.11 10 rm:2 .... 1001 01.0 .... \
vm=%vm_sp vd=%vd_sp sz=1
VRINT 1111 1110 1.11 10 rm:2 .... 1010 01.0 .... \
vm=%vm_sp vd=%vd_sp dp=0
vm=%vm_sp vd=%vd_sp sz=2
VRINT 1111 1110 1.11 10 rm:2 .... 1011 01.0 .... \
vm=%vm_dp vd=%vd_dp dp=1
vm=%vm_dp vd=%vd_dp sz=3
# VCVT float to int with specified rounding mode; Vd is always single-precision
VCVT 1111 1110 1.11 11 rm:2 .... 1001 op:1 1.0 .... \
vm=%vm_sp vd=%vd_sp sz=1
VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \
vm=%vm_sp vd=%vd_sp dp=0
vm=%vm_sp vd=%vd_sp sz=2
VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \
vm=%vm_dp vd=%vd_sp dp=1
vm=%vm_dp vd=%vd_sp sz=3
VMOVX 1111 1110 1.11 0000 .... 1010 01 . 0 .... \
vd=%vd_sp vm=%vm_sp
VINS 1111 1110 1.11 0000 .... 1010 11 . 0 .... \
vd=%vd_sp vm=%vm_sp
target/arm/vfp.decode
+32 -2
View File
@@ -74,13 +74,13 @@ VDUP ---- 1110 1 b:1 q:1 0 .... rt:4 1011 . 0 e:1 1 0000 \
vn=%vn_dp
VMSR_VMRS ---- 1110 111 l:1 reg:4 rt:4 1010 0001 0000
VMOV_half ---- 1110 000 l:1 .... rt:4 1001 . 001 0000 vn=%vn_sp
VMOV_single ---- 1110 000 l:1 .... rt:4 1010 . 001 0000 vn=%vn_sp
VMOV_64_sp ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 .... vm=%vm_sp
VMOV_64_dp ---- 1100 010 op:1 rt2:4 rt:4 1011 00.1 .... vm=%vm_dp
# Note that the half-precision variants of VLDR and VSTR are
# not part of this decodetree at all because they have bits [9:8] == 0b01
VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8 vd=%vd_sp
VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8 vd=%vd_sp
VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8 vd=%vd_dp
@@ -103,33 +103,47 @@ VLDM_VSTM_dp ---- 1101 0.1 l:1 rn:4 .... 1011 imm:8 \
vd=%vd_dp p=1 u=0 w=1
# 3-register VFP data-processing; bits [23,21:20,6] identify the operation.
VMLA_hp ---- 1110 0.00 .... .... 1001 .0.0 .... @vfp_dnm_s
VMLA_sp ---- 1110 0.00 .... .... 1010 .0.0 .... @vfp_dnm_s
VMLA_dp ---- 1110 0.00 .... .... 1011 .0.0 .... @vfp_dnm_d
VMLS_hp ---- 1110 0.00 .... .... 1001 .1.0 .... @vfp_dnm_s
VMLS_sp ---- 1110 0.00 .... .... 1010 .1.0 .... @vfp_dnm_s
VMLS_dp ---- 1110 0.00 .... .... 1011 .1.0 .... @vfp_dnm_d
VNMLS_hp ---- 1110 0.01 .... .... 1001 .0.0 .... @vfp_dnm_s
VNMLS_sp ---- 1110 0.01 .... .... 1010 .0.0 .... @vfp_dnm_s
VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d
VNMLA_hp ---- 1110 0.01 .... .... 1001 .1.0 .... @vfp_dnm_s
VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s
VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d
VMUL_hp ---- 1110 0.10 .... .... 1001 .0.0 .... @vfp_dnm_s
VMUL_sp ---- 1110 0.10 .... .... 1010 .0.0 .... @vfp_dnm_s
VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... @vfp_dnm_d
VNMUL_hp ---- 1110 0.10 .... .... 1001 .1.0 .... @vfp_dnm_s
VNMUL_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s
VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d
VADD_hp ---- 1110 0.11 .... .... 1001 .0.0 .... @vfp_dnm_s
VADD_sp ---- 1110 0.11 .... .... 1010 .0.0 .... @vfp_dnm_s
VADD_dp ---- 1110 0.11 .... .... 1011 .0.0 .... @vfp_dnm_d
VSUB_hp ---- 1110 0.11 .... .... 1001 .1.0 .... @vfp_dnm_s
VSUB_sp ---- 1110 0.11 .... .... 1010 .1.0 .... @vfp_dnm_s
VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... @vfp_dnm_d
VDIV_hp ---- 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s
VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s
VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d
VFMA_hp ---- 1110 1.10 .... .... 1001 .0. 0 .... @vfp_dnm_s
VFMS_hp ---- 1110 1.10 .... .... 1001 .1. 0 .... @vfp_dnm_s
VFNMA_hp ---- 1110 1.01 .... .... 1001 .0. 0 .... @vfp_dnm_s
VFNMS_hp ---- 1110 1.01 .... .... 1001 .1. 0 .... @vfp_dnm_s
VFMA_sp ---- 1110 1.10 .... .... 1010 .0. 0 .... @vfp_dnm_s
VFMS_sp ---- 1110 1.10 .... .... 1010 .1. 0 .... @vfp_dnm_s
VFNMA_sp ---- 1110 1.01 .... .... 1010 .0. 0 .... @vfp_dnm_s
@@ -140,6 +154,8 @@ VFMS_dp ---- 1110 1.10 .... .... 1011 .1.0 .... @vfp_dnm_d
VFNMA_dp ---- 1110 1.01 .... .... 1011 .0.0 .... @vfp_dnm_d
VFNMS_dp ---- 1110 1.01 .... .... 1011 .1.0 .... @vfp_dnm_d
VMOV_imm_hp ---- 1110 1.11 .... .... 1001 0000 .... \
vd=%vd_sp imm=%vmov_imm
VMOV_imm_sp ---- 1110 1.11 .... .... 1010 0000 .... \
vd=%vd_sp imm=%vmov_imm
VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \
@@ -148,15 +164,20 @@ VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \
VMOV_reg_sp ---- 1110 1.11 0000 .... 1010 01.0 .... @vfp_dm_ss
VMOV_reg_dp ---- 1110 1.11 0000 .... 1011 01.0 .... @vfp_dm_dd
VABS_hp ---- 1110 1.11 0000 .... 1001 11.0 .... @vfp_dm_ss
VABS_sp ---- 1110 1.11 0000 .... 1010 11.0 .... @vfp_dm_ss
VABS_dp ---- 1110 1.11 0000 .... 1011 11.0 .... @vfp_dm_dd
VNEG_hp ---- 1110 1.11 0001 .... 1001 01.0 .... @vfp_dm_ss
VNEG_sp ---- 1110 1.11 0001 .... 1010 01.0 .... @vfp_dm_ss
VNEG_dp ---- 1110 1.11 0001 .... 1011 01.0 .... @vfp_dm_dd
VSQRT_hp ---- 1110 1.11 0001 .... 1001 11.0 .... @vfp_dm_ss
VSQRT_sp ---- 1110 1.11 0001 .... 1010 11.0 .... @vfp_dm_ss
VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... @vfp_dm_dd
VCMP_hp ---- 1110 1.11 010 z:1 .... 1001 e:1 1.0 .... \
vd=%vd_sp vm=%vm_sp
VCMP_sp ---- 1110 1.11 010 z:1 .... 1010 e:1 1.0 .... \
vd=%vd_sp vm=%vm_sp
VCMP_dp ---- 1110 1.11 010 z:1 .... 1011 e:1 1.0 .... \
@@ -175,12 +196,15 @@ VCVT_f16_f32 ---- 1110 1.11 0011 .... 1010 t:1 1.0 .... \
VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \
vd=%vd_sp vm=%vm_dp
VRINTR_hp ---- 1110 1.11 0110 .... 1001 01.0 .... @vfp_dm_ss
VRINTR_sp ---- 1110 1.11 0110 .... 1010 01.0 .... @vfp_dm_ss
VRINTR_dp ---- 1110 1.11 0110 .... 1011 01.0 .... @vfp_dm_dd
VRINTZ_hp ---- 1110 1.11 0110 .... 1001 11.0 .... @vfp_dm_ss
VRINTZ_sp ---- 1110 1.11 0110 .... 1010 11.0 .... @vfp_dm_ss
VRINTZ_dp ---- 1110 1.11 0110 .... 1011 11.0 .... @vfp_dm_dd
VRINTX_hp ---- 1110 1.11 0111 .... 1001 01.0 .... @vfp_dm_ss
VRINTX_sp ---- 1110 1.11 0111 .... 1010 01.0 .... @vfp_dm_ss
VRINTX_dp ---- 1110 1.11 0111 .... 1011 01.0 .... @vfp_dm_dd
@@ -190,6 +214,8 @@ VCVT_sp ---- 1110 1.11 0111 .... 1010 11.0 .... @vfp_dm_ds
VCVT_dp ---- 1110 1.11 0111 .... 1011 11.0 .... @vfp_dm_sd
# VCVT from integer to floating point: Vm always single; Vd depends on size
VCVT_int_hp ---- 1110 1.11 1000 .... 1001 s:1 1.0 .... \
vd=%vd_sp vm=%vm_sp
VCVT_int_sp ---- 1110 1.11 1000 .... 1010 s:1 1.0 .... \
vd=%vd_sp vm=%vm_sp
VCVT_int_dp ---- 1110 1.11 1000 .... 1011 s:1 1.0 .... \
@@ -203,12 +229,16 @@ VJCVT ---- 1110 1.11 1001 .... 1011 11.0 .... @vfp_dm_sd
# We assemble bits 18 (op), 16 (u) and 7 (sx) into a single opc field
# for the convenience of the trans_VCVT_fix functions.
%vcvt_fix_op 18:1 16:1 7:1
VCVT_fix_hp ---- 1110 1.11 1.1. .... 1001 .1.0 .... \
vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op
VCVT_fix_sp ---- 1110 1.11 1.1. .... 1010 .1.0 .... \
vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op
VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \
vd=%vd_dp imm=%vm_sp opc=%vcvt_fix_op
# VCVT float to integer (VCVT and VCVTR): Vd always single; Vd depends on size
VCVT_hp_int ---- 1110 1.11 110 s:1 .... 1001 rz:1 1.0 .... \
vd=%vd_sp vm=%vm_sp
VCVT_sp_int ---- 1110 1.11 110 s:1 .... 1010 rz:1 1.0 .... \
vd=%vd_sp vm=%vm_sp
VCVT_dp_int ---- 1110 1.11 110 s:1 .... 1011 rz:1 1.0 .... \
target/arm/vfp_helper.c
+85 -159
View File
@@ -236,6 +236,11 @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val)
#define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p))
#define VFP_BINOP(name) \
dh_ctype_f16 VFP_HELPER(name, h)(dh_ctype_f16 a, dh_ctype_f16 b, void *fpstp) \
{ \
float_status *fpst = fpstp; \
return float16_ ## name(a, b, fpst); \
} \
float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \
{ \
float_status *fpst = fpstp; \
@@ -256,6 +261,11 @@ VFP_BINOP(minnum)
VFP_BINOP(maxnum)
#undef VFP_BINOP
dh_ctype_f16 VFP_HELPER(neg, h)(dh_ctype_f16 a)
{
return float16_chs(a);
}
float32 VFP_HELPER(neg, s)(float32 a)
{
return float32_chs(a);
@@ -266,6 +276,11 @@ float64 VFP_HELPER(neg, d)(float64 a)
return float64_chs(a);
}
dh_ctype_f16 VFP_HELPER(abs, h)(dh_ctype_f16 a)
{
return float16_abs(a);
}
float32 VFP_HELPER(abs, s)(float32 a)
{
return float32_abs(a);
@@ -276,6 +291,11 @@ float64 VFP_HELPER(abs, d)(float64 a)
return float64_abs(a);
}
dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, CPUARMState *env)
{
return float16_sqrt(a, &env->vfp.fp_status_f16);
}
float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env)
{
return float32_sqrt(a, &env->vfp.fp_status);
@@ -310,19 +330,20 @@ static void softfloat_to_vfp_compare(CPUARMState *env, FloatRelation cmp)
}
/* XXX: check quiet/signaling case */
#define DO_VFP_cmp(p, type) \
void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \
#define DO_VFP_cmp(P, FLOATTYPE, ARGTYPE, FPST) \
void VFP_HELPER(cmp, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \
{ \
softfloat_to_vfp_compare(env, \
type ## _compare_quiet(a, b, &env->vfp.fp_status)); \
FLOATTYPE ## _compare_quiet(a, b, &env->vfp.FPST)); \
} \
void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \
void VFP_HELPER(cmpe, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \
{ \
softfloat_to_vfp_compare(env, \
type ## _compare(a, b, &env->vfp.fp_status)); \
FLOATTYPE ## _compare(a, b, &env->vfp.FPST)); \
}
DO_VFP_cmp(s, float32)
DO_VFP_cmp(d, float64)
DO_VFP_cmp(h, float16, dh_ctype_f16, fp_status_f16)
DO_VFP_cmp(s, float32, float32, fp_status)
DO_VFP_cmp(d, float64, float64, fp_status)
#undef DO_VFP_cmp
/* Integer to float and float to integer conversions */
@@ -373,13 +394,13 @@ float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env)
}
/* VFP3 fixed point conversion. */
#define VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \
float##fsz HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \
#define VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \
ftype HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \
void *fpstp) \
{ return itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); }
#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, ROUND, suff) \
uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \
#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, ROUND, suff) \
uint##isz##_t HELPER(vfp_to##name##p##suff)(ftype x, uint32_t shift, \
void *fpst) \
{ \
if (unlikely(float##fsz##_is_any_nan(x))) { \
@@ -389,116 +410,42 @@ uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \
return float##fsz##_to_##itype##_scalbn(x, ROUND, shift, fpst); \
}
#define VFP_CONV_FIX(name, p, fsz, isz, itype) \
VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \
#define VFP_CONV_FIX(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \
float_round_to_zero, _round_to_zero) \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \
get_float_rounding_mode(fpst), )
#define VFP_CONV_FIX_A64(name, p, fsz, isz, itype) \
VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \
#define VFP_CONV_FIX_A64(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \
get_float_rounding_mode(fpst), )
VFP_CONV_FIX(sh, d, 64, 64, int16)
VFP_CONV_FIX(sl, d, 64, 64, int32)
VFP_CONV_FIX_A64(sq, d, 64, 64, int64)
VFP_CONV_FIX(uh, d, 64, 64, uint16)
VFP_CONV_FIX(ul, d, 64, 64, uint32)
VFP_CONV_FIX_A64(uq, d, 64, 64, uint64)
VFP_CONV_FIX(sh, s, 32, 32, int16)
VFP_CONV_FIX(sl, s, 32, 32, int32)
VFP_CONV_FIX_A64(sq, s, 32, 64, int64)
VFP_CONV_FIX(uh, s, 32, 32, uint16)
VFP_CONV_FIX(ul, s, 32, 32, uint32)
VFP_CONV_FIX_A64(uq, s, 32, 64, uint64)
VFP_CONV_FIX(sh, d, 64, float64, 64, int16)
VFP_CONV_FIX(sl, d, 64, float64, 64, int32)
VFP_CONV_FIX_A64(sq, d, 64, float64, 64, int64)
VFP_CONV_FIX(uh, d, 64, float64, 64, uint16)
VFP_CONV_FIX(ul, d, 64, float64, 64, uint32)
VFP_CONV_FIX_A64(uq, d, 64, float64, 64, uint64)
VFP_CONV_FIX(sh, s, 32, float32, 32, int16)
VFP_CONV_FIX(sl, s, 32, float32, 32, int32)
VFP_CONV_FIX_A64(sq, s, 32, float32, 64, int64)
VFP_CONV_FIX(uh, s, 32, float32, 32, uint16)
VFP_CONV_FIX(ul, s, 32, float32, 32, uint32)
VFP_CONV_FIX_A64(uq, s, 32, float32, 64, uint64)
VFP_CONV_FIX(sh, h, 16, dh_ctype_f16, 32, int16)
VFP_CONV_FIX(sl, h, 16, dh_ctype_f16, 32, int32)
VFP_CONV_FIX_A64(sq, h, 16, dh_ctype_f16, 64, int64)
VFP_CONV_FIX(uh, h, 16, dh_ctype_f16, 32, uint16)
VFP_CONV_FIX(ul, h, 16, dh_ctype_f16, 32, uint32)
VFP_CONV_FIX_A64(uq, h, 16, dh_ctype_f16, 64, uint64)
#undef VFP_CONV_FIX
#undef VFP_CONV_FIX_FLOAT
#undef VFP_CONV_FLOAT_FIX_ROUND
#undef VFP_CONV_FIX_A64
uint32_t HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst)
{
return int32_to_float16_scalbn(x, -shift, fpst);
}
uint32_t HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst)
{
return uint32_to_float16_scalbn(x, -shift, fpst);
}
uint32_t HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst)
{
return int64_to_float16_scalbn(x, -shift, fpst);
}
uint32_t HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst)
{
return uint64_to_float16_scalbn(x, -shift, fpst);
}
uint32_t HELPER(vfp_toshh)(uint32_t x, uint32_t shift, void *fpst)
{
if (unlikely(float16_is_any_nan(x))) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_int16_scalbn(x, get_float_rounding_mode(fpst),
shift, fpst);
}
uint32_t HELPER(vfp_touhh)(uint32_t x, uint32_t shift, void *fpst)
{
if (unlikely(float16_is_any_nan(x))) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_uint16_scalbn(x, get_float_rounding_mode(fpst),
shift, fpst);
}
uint32_t HELPER(vfp_toslh)(uint32_t x, uint32_t shift, void *fpst)
{
if (unlikely(float16_is_any_nan(x))) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_int32_scalbn(x, get_float_rounding_mode(fpst),
shift, fpst);
}
uint32_t HELPER(vfp_toulh)(uint32_t x, uint32_t shift, void *fpst)
{
if (unlikely(float16_is_any_nan(x))) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_uint32_scalbn(x, get_float_rounding_mode(fpst),
shift, fpst);
}
uint64_t HELPER(vfp_tosqh)(uint32_t x, uint32_t shift, void *fpst)
{
if (unlikely(float16_is_any_nan(x))) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_int64_scalbn(x, get_float_rounding_mode(fpst),
shift, fpst);
}
uint64_t HELPER(vfp_touqh)(uint32_t x, uint32_t shift, void *fpst)
{
if (unlikely(float16_is_any_nan(x))) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_uint64_scalbn(x, get_float_rounding_mode(fpst),
shift, fpst);
}
/* Set the current fp rounding mode and return the old one.
* The argument is a softfloat float_round_ value.
*/
@@ -512,23 +459,6 @@ uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp)
return prev_rmode;
}
/* Set the current fp rounding mode in the standard fp status and return
* the old one. This is for NEON instructions that need to change the
* rounding mode but wish to use the standard FPSCR values for everything
* else. Always set the rounding mode back to the correct value after
* modifying it.
* The argument is a softfloat float_round_ value.
*/
uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env)
{
float_status *fp_status = &env->vfp.standard_fp_status;
uint32_t prev_rmode = get_float_rounding_mode(fp_status);
set_float_rounding_mode(rmode, fp_status);
return prev_rmode;
}
/* Half precision conversions. */
float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode)
{
@@ -582,38 +512,6 @@ uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode)
return r;
}
#define float32_two make_float32(0x40000000)
#define float32_three make_float32(0x40400000)
#define float32_one_point_five make_float32(0x3fc00000)
float32 HELPER(recps_f32)(CPUARMState *env, float32 a, float32 b)
{
float_status *s = &env->vfp.standard_fp_status;
if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) ||
(float32_is_infinity(b) && float32_is_zero_or_denormal(a))) {
if (!(float32_is_zero(a) || float32_is_zero(b))) {
float_raise(float_flag_input_denormal, s);
}
return float32_two;
}
return float32_sub(float32_two, float32_mul(a, b, s), s);
}
float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b)
{
float_status *s = &env->vfp.standard_fp_status;
float32 product;
if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) ||
(float32_is_infinity(b) && float32_is_zero_or_denormal(a))) {
if (!(float32_is_zero(a) || float32_is_zero(b))) {
float_raise(float_flag_input_denormal, s);
}
return float32_one_point_five;
}
product = float32_mul(a, b, s);
return float32_div(float32_sub(float32_three, product, s), float32_two, s);
}
/* NEON helpers. */
/* Constants 256 and 512 are used in some helpers; we avoid relying on
@@ -1056,6 +954,13 @@ uint32_t HELPER(rsqrte_u32)(uint32_t a)
}
/* VFPv4 fused multiply-accumulate */
dh_ctype_f16 VFP_HELPER(muladd, h)(dh_ctype_f16 a, dh_ctype_f16 b,
dh_ctype_f16 c, void *fpstp)
{
float_status *fpst = fpstp;
return float16_muladd(a, b, c, 0, fpst);
}
float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp)
{
float_status *fpst = fpstp;
@@ -1069,6 +974,11 @@ float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp)
}
/* ARMv8 round to integral */
dh_ctype_f16 HELPER(rinth_exact)(dh_ctype_f16 x, void *fp_status)
{
return float16_round_to_int(x, fp_status);
}
float32 HELPER(rints_exact)(float32 x, void *fp_status)
{
return float32_round_to_int(x, fp_status);
@@ -1079,6 +989,22 @@ float64 HELPER(rintd_exact)(float64 x, void *fp_status)
return float64_round_to_int(x, fp_status);
}
dh_ctype_f16 HELPER(rinth)(dh_ctype_f16 x, void *fp_status)
{
int old_flags = get_float_exception_flags(fp_status), new_flags;
float16 ret;
ret = float16_round_to_int(x, fp_status);
/* Suppress any inexact exceptions the conversion produced */
if (!(old_flags & float_flag_inexact)) {
new_flags = get_float_exception_flags(fp_status);
set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status);
}
return ret;
}
float32 HELPER(rints)(float32 x, void *fp_status)
{
int old_flags = get_float_exception_flags(fp_status), new_flags;