openkylin
/
qemu
mirror of https://gitee.com/openkylin/qemu.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

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
 -----BEGIN PGP SIGNATURE-----
 
 iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAl9OZgMZHHBldGVyLm1h
 eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3uRfD/4kjn9wRlcHJkFYajL6nk1f
 6CI8CAeb6Fv2+snzcDfbutqC1jdL2V9qeojsq6K1L/k59rQgOlBJNJCWNB06KLWq
 /kbmK6Wa0jTscMTf2Kzo5USUFK9TckrHcpAzAYzPTtJdIVDZOJ01npmaxwRvoQ5V
 D84VVfKs73Pkpn1PwBVAVpOjn3VeE01vK+A+71kj0Jo9cPoyzqL/ObmJmjVI1MjP
 aEMRHDvQLl+Co59jjWYOWKyAEPhofo9mDVmCjDapHGppeAWH6E81AJYF6sG8K08Y
 VJutzsJbe9o9limkVzAGj2Z/i5lFCyX49NL0YBUO2iwDpNd2ijxDUUy+s4rLGyMK
 ehkgFjXp7qm91R5RAf/xkBtvTbEbQm/tbyYxGdnjN/Vpknpl1hk9O0QW6ItOqZUC
 FGZbvzn1fdT4xG7bWsaFmy1fwX8nwLPmCeKclQlnpGaBoai9b1Xu/au8QUku82Kb
 lNfhJeJLe8UiQvNHXmMZvDYGHIICAQApmuPEPjspsAmHYIJWWVPtq18A3Ac8jZ3a
 D1dq7sZqPD/7Lwl9Bci0froAioUhgaJgT4WCv4irhzpRjvz5ftN4D+iq41edoTQb
 XGLabaj9cXQqYD87uSB42+aHlCq3a+i+FOrh/NDKZb/tn8eaT/IKjSkl1LF6lbu/
 8yyMd3mncxFtRxtN9t1AXw==
 =NZ+q
 -----END PGP SIGNATURE-----

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

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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
hw/arm/sbsa-ref.c
View File

@ -62,6 +62,7 @@ enum {
SBSA_CPUPERIPHS, SBSA_CPUPERIPHS,
SBSA_GIC_DIST, SBSA_GIC_DIST,
SBSA_GIC_REDIST, SBSA_GIC_REDIST,
SBSA_SECURE_EC,
SBSA_SMMU, SBSA_SMMU,
SBSA_UART, SBSA_UART,
SBSA_RTC, SBSA_RTC,
@ -107,6 +108,7 @@ static const MemMapEntry sbsa_ref_memmap[] = {
[SBSA_CPUPERIPHS] = { 0x40000000, 0x00040000 }, [SBSA_CPUPERIPHS] = { 0x40000000, 0x00040000 },
[SBSA_GIC_DIST] = { 0x40060000, 0x00010000 }, [SBSA_GIC_DIST] = { 0x40060000, 0x00010000 },
[SBSA_GIC_REDIST] = { 0x40080000, 0x04000000 }, [SBSA_GIC_REDIST] = { 0x40080000, 0x04000000 },
[SBSA_SECURE_EC] = { 0x50000000, 0x00001000 },
[SBSA_UART] = { 0x60000000, 0x00001000 }, [SBSA_UART] = { 0x60000000, 0x00001000 },
[SBSA_RTC] = { 0x60010000, 0x00001000 }, [SBSA_RTC] = { 0x60010000, 0x00001000 },
[SBSA_GPIO] = { 0x60020000, 0x00001000 }, [SBSA_GPIO] = { 0x60020000, 0x00001000 },
@ -138,6 +140,12 @@ static const int sbsa_ref_irqmap[] = {
[SBSA_EHCI] = 11, [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 * 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 * 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); 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_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--) { for (cpu = sms->smp_cpus - 1; cpu >= 0; cpu--) {
char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu); char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu);
ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu));
CPUState *cs = CPU(armcpu); CPUState *cs = CPU(armcpu);
uint64_t mpidr = sbsa_ref_cpu_mp_affinity(sms, cpu);
qemu_fdt_add_subnode(sms->fdt, nodename); 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) { if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) {
qemu_fdt_setprop_cell(sms->fdt, nodename, "numa-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; 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) static void sbsa_ref_init(MachineState *machine)
{ {
unsigned int smp_cpus = machine->smp.cpus; unsigned int smp_cpus = machine->smp.cpus;
@ -708,6 +743,8 @@ static void sbsa_ref_init(MachineState *machine)
create_pcie(sms); create_pcie(sms);
create_secure_ec(secure_sysmem);
sms->bootinfo.ram_size = machine->ram_size; sms->bootinfo.ram_size = machine->ram_size;
sms->bootinfo.nb_cpus = smp_cpus; sms->bootinfo.nb_cpus = smp_cpus;
sms->bootinfo.board_id = -1; 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); 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) static const CPUArchIdList *sbsa_ref_possible_cpu_arch_ids(MachineState *ms)
{ {
unsigned int max_cpus = ms->smp.max_cpus; unsigned int max_cpus = ms->smp.max_cpus;

2
hw/misc/meson.build
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_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_MIPS_ITU', if_true: files('mips_itu.c'))
specific_ss.add(when: 'CONFIG_SBSA_REF', if_true: files('sbsa_ec.c'))

98
hw/misc/sbsa_ec.c Normal file
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);

3
target/arm/cpu.c
View File

@ -2143,7 +2143,8 @@ static void arm_max_initfn(Object *obj)
cpu->isar.id_isar6 = t; cpu->isar.id_isar6 = t;
t = cpu->isar.mvfr1; 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; cpu->isar.mvfr1 = t;
t = cpu->isar.mvfr2; t = cpu->isar.mvfr2;

7
target/arm/cpu.h
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) static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id)
{ {
/* return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3;
* 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;
} }
static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id)

10
target/arm/cpu64.c
View File

@ -704,12 +704,10 @@ static void aarch64_max_initfn(Object *obj)
u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */
cpu->isar.id_dfr0 = u; cpu->isar.id_dfr0 = u;
/* u = cpu->isar.mvfr1;
* FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet, u = FIELD_DP32(u, MVFR1, FPHP, 3); /* v8.2-FP16 */
* so do not set MVFR1.FPHP. Strictly speaking this is not legal, u = FIELD_DP32(u, MVFR1, SIMDHP, 2); /* v8.2-FP16 */
* but it is also not legal to enable SVE without support for FP16, cpu->isar.mvfr1 = u;
* and enabling SVE in system mode is more useful in the short term.
*/
#ifdef CONFIG_USER_ONLY #ifdef CONFIG_USER_ONLY
/* For usermode -cpu max we can use a larger and more efficient DCZ /* For usermode -cpu max we can use a larger and more efficient DCZ

11
target/arm/helper-a64.c
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 * versions, these do a fully fused multiply-add or
* multiply-add-and-halve. * 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) uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp)
{ {

133
target/arm/helper.h
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_1(vfp_get_fpscr, i32, env)
DEF_HELPER_2(vfp_set_fpscr, void, env, i32) 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_adds, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_addd, f64, f64, f64, 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_subs, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_subd, f64, f64, f64, 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_muls, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_muld, f64, f64, f64, 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_divs, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_divd, f64, f64, f64, 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_maxs, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_maxd, f64, f64, f64, 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_mins, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_mind, f64, f64, f64, 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_maxnums, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, 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_minnums, f32, f32, f32, ptr)
DEF_HELPER_3(vfp_minnumd, f64, f64, f64, 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_negs, f32, f32)
DEF_HELPER_1(vfp_negd, f64, f64) 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_abss, f32, f32)
DEF_HELPER_1(vfp_absd, f64, f64) 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_sqrts, f32, f32, env)
DEF_HELPER_2(vfp_sqrtd, f64, f64, 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_cmps, void, f32, f32, env)
DEF_HELPER_3(vfp_cmpd, void, f64, f64, 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_cmpes, void, f32, f32, env)
DEF_HELPER_3(vfp_cmped, void, f64, f64, 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_tosizs, s32, f32, ptr)
DEF_HELPER_2(vfp_tosizd, s32, f64, 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_toshs_round_to_zero, i32, f32, i32, ptr)
DEF_HELPER_3(vfp_tosls_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) 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_uhtod, f64, i64, i32, ptr)
DEF_HELPER_3(vfp_ultod, 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_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_sltoh, f16, i32, i32, ptr)
DEF_HELPER_3(vfp_ultoh, 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_sqtoh, f16, i64, i32, ptr)
DEF_HELPER_3(vfp_uqtoh, 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_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_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) 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_muladdd, f64, f64, f64, f64, ptr)
DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, 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_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_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, 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(sar_cc, i32, env, i32, i32)
DEF_HELPER_3(ror_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(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(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(rints, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, 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, DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32) 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_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_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) 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_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_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_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_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) 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_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_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_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, DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32) void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, 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, DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32) 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, DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32) void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,

8
target/arm/neon-dp.decode
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. # We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings.
@2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \ @2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5 &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_d
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s 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 VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b
# VCVT fixed<->float conversions # 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_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
VCVT_UF_2sh 1111 001 1 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 VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt

755
target/arm/translate-neon.c.inc
View File

@ -1033,122 +1033,54 @@ DO_3SAME_PAIR(VPADD, padd_u)
DO_3SAME_VQDMULH(VQDMULH, qdmulh) DO_3SAME_VQDMULH(VQDMULH, qdmulh)
DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) DO_3SAME_VQDMULH(VQRDMULH, qrdmulh)
static bool do_3same_fp(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn, #define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \
bool reads_vd) static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
{ uint32_t rn_ofs, uint32_t rm_ofs, \
/* uint32_t oprsz, uint32_t maxsz) \
* FP operations handled elementwise 32 bits at a time.
* If reads_vd is true then the old value of Vd will be
* loaded before calling the callback function. This is
* used for multiply-accumulate type operations.
*/
TCGv_i32 tmp, tmp2;
int pass;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
}
/* UNDEF accesses to D16-D31 if they don't exist. */
if (!dc_isar_feature(aa32_simd_r32, s) &&
((a->vd | a->vn | a->vm) & 0x10)) {
return false;
}
if ((a->vn | a->vm | a->vd) & a->q) {
return false;
}
if (!vfp_access_check(s)) {
return true;
}
TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD);
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
tmp = neon_load_reg(a->vn, pass);
tmp2 = neon_load_reg(a->vm, pass);
if (reads_vd) {
TCGv_i32 tmp_rd = neon_load_reg(a->vd, pass);
fn(tmp_rd, tmp, tmp2, fpstatus);
neon_store_reg(a->vd, pass, tmp_rd);
tcg_temp_free_i32(tmp);
} else {
fn(tmp, tmp, tmp2, fpstatus);
neon_store_reg(a->vd, pass, tmp);
}
tcg_temp_free_i32(tmp2);
}
tcg_temp_free_ptr(fpstatus);
return true;
}
/*
* For all the functions using this macro, size == 1 means fp16,
* which is an architecture extension we don't implement yet.
*/
#define DO_3S_FP_GVEC(INSN,FUNC) \
static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
uint32_t rn_ofs, uint32_t rm_ofs, \
uint32_t oprsz, uint32_t maxsz) \
{ \ { \
TCGv_ptr fpst = fpstatus_ptr(FPST_STD); \ TCGv_ptr fpst = fpstatus_ptr(FPST); \
tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpst, \ tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpst, \
oprsz, maxsz, 0, FUNC); \ oprsz, maxsz, 0, FUNC); \
tcg_temp_free_ptr(fpst); \ tcg_temp_free_ptr(fpst); \
} \ }
#define DO_3S_FP_GVEC(INSN,SFUNC,HFUNC) \
WRAP_FP_GVEC(gen_##INSN##_fp32_3s, FPST_STD, SFUNC) \
WRAP_FP_GVEC(gen_##INSN##_fp16_3s, FPST_STD_F16, HFUNC) \
static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \
{ \ { \
if (a->size != 0) { \ if (a->size != 0) { \
/* TODO fp16 support */ \ if (!dc_isar_feature(aa32_fp16_arith, s)) { \
return false; \ return false; \
} \
return do_3same(s, a, gen_##INSN##_fp16_3s); \
} \ } \
return do_3same(s, a, gen_##INSN##_3s); \ return do_3same(s, a, gen_##INSN##_fp32_3s); \
} }
DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s) DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s, gen_helper_gvec_fadd_h)
DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s) DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_h)
DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s) DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_h)
DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s) DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h)
DO_3S_FP_GVEC(VCEQ, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_h)
DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h)
DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h)
DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h)
DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h)
DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h)
DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h)
DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h)
DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h)
DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h)
DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h)
DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h)
DO_3S_FP_GVEC(VRSQRTS, gen_helper_gvec_rsqrts_nf_s, gen_helper_gvec_rsqrts_nf_h)
/* WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s)
* For all the functions using this macro, size == 1 means fp16, WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h)
* which is an architecture extension we don't implement yet. WRAP_FP_GVEC(gen_VMINNM_fp32_3s, FPST_STD, gen_helper_gvec_fminnum_s)
*/ WRAP_FP_GVEC(gen_VMINNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fminnum_h)
#define DO_3S_FP(INSN,FUNC,READS_VD) \
static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \
{ \
if (a->size != 0) { \
/* TODO fp16 support */ \
return false; \
} \
return do_3same_fp(s, a, FUNC, READS_VD); \
}
DO_3S_FP(VCEQ, gen_helper_neon_ceq_f32, false)
DO_3S_FP(VCGE, gen_helper_neon_cge_f32, false)
DO_3S_FP(VCGT, gen_helper_neon_cgt_f32, false)
DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false)
DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false)
DO_3S_FP(VMAX, gen_helper_vfp_maxs, false)
DO_3S_FP(VMIN, gen_helper_vfp_mins, false)
static void gen_VMLA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
TCGv_ptr fpstatus)
{
gen_helper_vfp_muls(vn, vn, vm, fpstatus);
gen_helper_vfp_adds(vd, vd, vn, fpstatus);
}
static void gen_VMLS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
TCGv_ptr fpstatus)
{
gen_helper_vfp_muls(vn, vn, vm, fpstatus);
gen_helper_vfp_subs(vd, vd, vn, fpstatus);
}
DO_3S_FP(VMLA, gen_VMLA_fp_3s, true)
DO_3S_FP(VMLS, gen_VMLS_fp_3s, true)
static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a)
{ {
@ -1157,11 +1089,12 @@ static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a)
} }
if (a->size != 0) { if (a->size != 0) {
/* TODO fp16 support */ if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false; return false;
}
return do_3same(s, a, gen_VMAXNM_fp16_3s);
} }
return do_3same(s, a, gen_VMAXNM_fp32_3s);
return do_3same_fp(s, a, gen_helper_vfp_maxnums, false);
} }
static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a)
@ -1171,98 +1104,18 @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a)
} }
if (a->size != 0) { if (a->size != 0) {
/* TODO fp16 support */ if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false; return false;
}
return do_3same(s, a, gen_VMINNM_fp16_3s);
} }
return do_3same(s, a, gen_VMINNM_fp32_3s);
return do_3same_fp(s, a, gen_helper_vfp_minnums, false);
} }
WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32) static bool do_3same_fp_pair(DisasContext *s, arg_3same *a,
gen_helper_gvec_3_ptr *fn)
static void gen_VRECPS_fp_3s(unsigned vece, uint32_t rd_ofs,
uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{ {
static const GVecGen3 ops = { .fni4 = gen_VRECPS_tramp }; /* FP pairwise operations */
tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops);
}
static bool trans_VRECPS_fp_3s(DisasContext *s, arg_3same *a)
{
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same(s, a, gen_VRECPS_fp_3s);
}
WRAP_ENV_FN(gen_VRSQRTS_tramp, gen_helper_rsqrts_f32)
static void gen_VRSQRTS_fp_3s(unsigned vece, uint32_t rd_ofs,
uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{
static const GVecGen3 ops = { .fni4 = gen_VRSQRTS_tramp };
tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops);
}
static bool trans_VRSQRTS_fp_3s(DisasContext *s, arg_3same *a)
{
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same(s, a, gen_VRSQRTS_fp_3s);
}
static void gen_VFMA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
TCGv_ptr fpstatus)
{
gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus);
}
static bool trans_VFMA_fp_3s(DisasContext *s, arg_3same *a)
{
if (!dc_isar_feature(aa32_simdfmac, s)) {
return false;
}
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same_fp(s, a, gen_VFMA_fp_3s, true);
}
static void gen_VFMS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
TCGv_ptr fpstatus)
{
gen_helper_vfp_negs(vn, vn);
gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus);
}
static bool trans_VFMS_fp_3s(DisasContext *s, arg_3same *a)
{
if (!dc_isar_feature(aa32_simdfmac, s)) {
return false;
}
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same_fp(s, a, gen_VFMS_fp_3s, true);
}
static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn)
{
/* FP operations handled pairwise 32 bits at a time */
TCGv_i32 tmp, tmp2, tmp3;
TCGv_ptr fpstatus; TCGv_ptr fpstatus;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@ -1281,26 +1134,14 @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn)
assert(a->q == 0); /* enforced by decode patterns */ assert(a->q == 0); /* enforced by decode patterns */
/*
* Note that we have to be careful not to clobber the source operands
* in the "vm == vd" case by storing the result of the first pass too
* early. Since Q is 0 there are always just two passes, so instead
* of a complicated loop over each pass we just unroll.
*/
fpstatus = fpstatus_ptr(FPST_STD);
tmp = neon_load_reg(a->vn, 0);
tmp2 = neon_load_reg(a->vn, 1);
fn(tmp, tmp, tmp2, fpstatus);
tcg_temp_free_i32(tmp2);
tmp3 = neon_load_reg(a->vm, 0); fpstatus = fpstatus_ptr(a->size != 0 ? FPST_STD_F16 : FPST_STD);
tmp2 = neon_load_reg(a->vm, 1); tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
fn(tmp3, tmp3, tmp2, fpstatus); vfp_reg_offset(1, a->vn),
tcg_temp_free_i32(tmp2); vfp_reg_offset(1, a->vm),
fpstatus, 8, 8, 0, fn);
tcg_temp_free_ptr(fpstatus); tcg_temp_free_ptr(fpstatus);
neon_store_reg(a->vd, 0, tmp);
neon_store_reg(a->vd, 1, tmp3);
return true; return true;
} }
@ -1312,15 +1153,17 @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn)
static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \
{ \ { \
if (a->size != 0) { \ if (a->size != 0) { \
/* TODO fp16 support */ \ if (!dc_isar_feature(aa32_fp16_arith, s)) { \
return false; \ return false; \
} \
return do_3same_fp_pair(s, a, FUNC##h); \
} \ } \
return do_3same_fp_pair(s, a, FUNC); \ return do_3same_fp_pair(s, a, FUNC##s); \
} }
DO_3S_FP_PAIR(VPADD, gen_helper_vfp_adds) DO_3S_FP_PAIR(VPADD, gen_helper_neon_padd)
DO_3S_FP_PAIR(VPMAX, gen_helper_vfp_maxs) DO_3S_FP_PAIR(VPMAX, gen_helper_neon_pmax)
DO_3S_FP_PAIR(VPMIN, gen_helper_vfp_mins) DO_3S_FP_PAIR(VPMIN, gen_helper_neon_pmin)
static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn)
{ {
@ -1765,17 +1608,24 @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a)
} }
static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
NeonGenTwoSingleOpFn *fn) gen_helper_gvec_2_ptr *fn)
{ {
/* FP operations in 2-reg-and-shift group */ /* FP operations in 2-reg-and-shift group */
TCGv_i32 tmp, shiftv; int vec_size = a->q ? 16 : 8;
TCGv_ptr fpstatus; int rd_ofs = neon_reg_offset(a->vd, 0);
int pass; int rm_ofs = neon_reg_offset(a->vm, 0);
TCGv_ptr fpst;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false; return false;
} }
if (a->size != 0) {
if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false;
}
}
/* UNDEF accesses to D16-D31 if they don't exist. */ /* UNDEF accesses to D16-D31 if they don't exist. */
if (!dc_isar_feature(aa32_simd_r32, s) && if (!dc_isar_feature(aa32_simd_r32, s) &&
((a->vd | a->vm) & 0x10)) { ((a->vd | a->vm) & 0x10)) {
@ -1790,15 +1640,9 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
return true; return true;
} }
fpstatus = fpstatus_ptr(FPST_STD); fpst = fpstatus_ptr(a->size ? FPST_STD_F16 : FPST_STD);
shiftv = tcg_const_i32(a->shift); tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, vec_size, vec_size, a->shift, fn);
for (pass = 0; pass < (a->q ? 4 : 2); pass++) { tcg_temp_free_ptr(fpst);
tmp = neon_load_reg(a->vm, pass);
fn(tmp, tmp, shiftv, fpstatus);
neon_store_reg(a->vd, pass, tmp);
}
tcg_temp_free_ptr(fpstatus);
tcg_temp_free_i32(shiftv);
return true; return true;
} }
@ -1808,10 +1652,15 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
return do_fp_2sh(s, a, FUNC); \ return do_fp_2sh(s, a, FUNC); \
} }
DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos) DO_FP_2SH(VCVT_SF, gen_helper_gvec_vcvt_sf)
DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos) DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf)
DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero) DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs)
DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero) DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu)
DO_FP_2SH(VCVT_SH, gen_helper_gvec_vcvt_sh)
DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh)
DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs)
DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu)
static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
{ {
@ -2583,70 +2432,70 @@ static bool trans_VMLS_2sc(DisasContext *s, arg_2scalar *a)
return do_2scalar(s, a, opfn[a->size], accfn[a->size]); return do_2scalar(s, a, opfn[a->size], accfn[a->size]);
} }
/* static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a,
* Rather than have a float-specific version of do_2scalar just for gen_helper_gvec_3_ptr *fn)
* three insns, we wrap a NeonGenTwoSingleOpFn to turn it into {
* a NeonGenTwoOpFn. /* Two registers and a scalar, using gvec */
*/ int vec_size = a->q ? 16 : 8;
#define WRAP_FP_FN(WRAPNAME, FUNC) \ int rd_ofs = neon_reg_offset(a->vd, 0);
static void WRAPNAME(TCGv_i32 rd, TCGv_i32 rn, TCGv_i32 rm) \ int rn_ofs = neon_reg_offset(a->vn, 0);
{ \ int rm_ofs;
TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD); \ int idx;
FUNC(rd, rn, rm, fpstatus); \ TCGv_ptr fpstatus;
tcg_temp_free_ptr(fpstatus); \
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
} }
WRAP_FP_FN(gen_VMUL_F_mul, gen_helper_vfp_muls) /* UNDEF accesses to D16-D31 if they don't exist. */
WRAP_FP_FN(gen_VMUL_F_add, gen_helper_vfp_adds) if (!dc_isar_feature(aa32_simd_r32, s) &&
WRAP_FP_FN(gen_VMUL_F_sub, gen_helper_vfp_subs) ((a->vd | a->vn | a->vm) & 0x10)) {
return false;
}
static bool trans_VMUL_F_2sc(DisasContext *s, arg_2scalar *a) if (!fn) {
{ /* Bad size (including size == 3, which is a different insn group) */
static NeonGenTwoOpFn * const opfn[] = { return false;
NULL, }
NULL, /* TODO: fp16 support */
gen_VMUL_F_mul,
NULL,
};
return do_2scalar(s, a, opfn[a->size], NULL); if (a->q && ((a->vd | a->vn) & 1)) {
return false;
}
if (!vfp_access_check(s)) {
return true;
}
/* a->vm is M:Vm, which encodes both register and index */
idx = extract32(a->vm, a->size + 2, 2);
a->vm = extract32(a->vm, 0, a->size + 2);
rm_ofs = neon_reg_offset(a->vm, 0);
fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD);
tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus,
vec_size, vec_size, idx, fn);
tcg_temp_free_ptr(fpstatus);
return true;
} }
static bool trans_VMLA_F_2sc(DisasContext *s, arg_2scalar *a) #define DO_VMUL_F_2sc(NAME, FUNC) \
{ static bool trans_##NAME##_F_2sc(DisasContext *s, arg_2scalar *a) \
static NeonGenTwoOpFn * const opfn[] = { { \
NULL, static gen_helper_gvec_3_ptr * const opfn[] = { \
NULL, /* TODO: fp16 support */ NULL, \
gen_VMUL_F_mul, gen_helper_##FUNC##_h, \
NULL, gen_helper_##FUNC##_s, \
}; NULL, \
static NeonGenTwoOpFn * const accfn[] = { }; \
NULL, if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { \
NULL, /* TODO: fp16 support */ return false; \
gen_VMUL_F_add, } \
NULL, return do_2scalar_fp_vec(s, a, opfn[a->size]); \
}; }
return do_2scalar(s, a, opfn[a->size], accfn[a->size]); DO_VMUL_F_2sc(VMUL, gvec_fmul_idx)
} DO_VMUL_F_2sc(VMLA, gvec_fmla_nf_idx)
DO_VMUL_F_2sc(VMLS, gvec_fmls_nf_idx)
static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a)
{
static NeonGenTwoOpFn * const opfn[] = {
NULL,
NULL, /* TODO: fp16 support */
gen_VMUL_F_mul,
NULL,
};
static NeonGenTwoOpFn * const accfn[] = {
NULL,
NULL, /* TODO: fp16 support */
gen_VMUL_F_sub,
NULL,
};
return do_2scalar(s, a, opfn[a->size], accfn[a->size]);
}
WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16) WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16)
WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32) WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32)
@ -3739,22 +3588,44 @@ static bool trans_VCNT(DisasContext *s, arg_2misc *a)
return do_2misc(s, a, gen_helper_neon_cnt_u8); return do_2misc(s, a, gen_helper_neon_cnt_u8);
} }
static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{
tcg_gen_gvec_andi(vece, rd_ofs, rm_ofs,
vece == MO_16 ? 0x7fff : 0x7fffffff,
oprsz, maxsz);
}
static bool trans_VABS_F(DisasContext *s, arg_2misc *a) static bool trans_VABS_F(DisasContext *s, arg_2misc *a)
{ {
if (a->size != 2) { if (a->size == MO_16) {
if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false;
}
} else if (a->size != MO_32) {
return false; return false;
} }
/* TODO: FP16 : size == 1 */ return do_2misc_vec(s, a, gen_VABS_F);
return do_2misc(s, a, gen_helper_vfp_abss); }
static void gen_VNEG_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{
tcg_gen_gvec_xori(vece, rd_ofs, rm_ofs,
vece == MO_16 ? 0x8000 : 0x80000000,
oprsz, maxsz);
} }
static bool trans_VNEG_F(DisasContext *s, arg_2misc *a) static bool trans_VNEG_F(DisasContext *s, arg_2misc *a)
{ {
if (a->size != 2) { if (a->size == MO_16) {
if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false;
}
} else if (a->size != MO_32) {
return false; return false;
} }
/* TODO: FP16 : size == 1 */ return do_2misc_vec(s, a, gen_VNEG_F);
return do_2misc(s, a, gen_helper_vfp_negs);
} }
static bool trans_VRECPE(DisasContext *s, arg_2misc *a) static bool trans_VRECPE(DisasContext *s, arg_2misc *a)
@ -3808,226 +3679,100 @@ static bool trans_VQNEG(DisasContext *s, arg_2misc *a)
return do_2misc(s, a, fn[a->size]); return do_2misc(s, a, fn[a->size]);
} }
static bool do_2misc_fp(DisasContext *s, arg_2misc *a, #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \
NeonGenOneSingleOpFn *fn) static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \
{ uint32_t rm_ofs, \
int pass; uint32_t oprsz, uint32_t maxsz) \
TCGv_ptr fpst; { \
static gen_helper_gvec_2_ptr * const fns[4] = { \
/* Handle a 2-reg-misc operation by iterating 32 bits at a time */ NULL, HFUNC, SFUNC, NULL, \
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { }; \
return false; TCGv_ptr fpst; \
fpst = fpstatus_ptr(vece == MO_16 ? FPST_STD_F16 : FPST_STD); \
tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, oprsz, maxsz, 0, \
fns[vece]); \
tcg_temp_free_ptr(fpst); \
} \
static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
{ \
if (a->size == MO_16) { \
if (!dc_isar_feature(aa32_fp16_arith, s)) { \
return false; \
} \
} else if (a->size != MO_32) { \
return false; \
} \
return do_2misc_vec(s, a, gen_##INSN); \
} }
/* UNDEF accesses to D16-D31 if they don't exist. */ DO_2MISC_FP_VEC(VRECPE_F, gen_helper_gvec_frecpe_h, gen_helper_gvec_frecpe_s)
if (!dc_isar_feature(aa32_simd_r32, s) && DO_2MISC_FP_VEC(VRSQRTE_F, gen_helper_gvec_frsqrte_h, gen_helper_gvec_frsqrte_s)
((a->vd | a->vm) & 0x10)) { DO_2MISC_FP_VEC(VCGT0_F, gen_helper_gvec_fcgt0_h, gen_helper_gvec_fcgt0_s)
return false; DO_2MISC_FP_VEC(VCGE0_F, gen_helper_gvec_fcge0_h, gen_helper_gvec_fcge0_s)
} DO_2MISC_FP_VEC(VCEQ0_F, gen_helper_gvec_fceq0_h, gen_helper_gvec_fceq0_s)
DO_2MISC_FP_VEC(VCLT0_F, gen_helper_gvec_fclt0_h, gen_helper_gvec_fclt0_s)
DO_2MISC_FP_VEC(VCLE0_F, gen_helper_gvec_fcle0_h, gen_helper_gvec_fcle0_s)
DO_2MISC_FP_VEC(VCVT_FS, gen_helper_gvec_sstoh, gen_helper_gvec_sitos)
DO_2MISC_FP_VEC(VCVT_FU, gen_helper_gvec_ustoh, gen_helper_gvec_uitos)
DO_2MISC_FP_VEC(VCVT_SF, gen_helper_gvec_tosszh, gen_helper_gvec_tosizs)
DO_2MISC_FP_VEC(VCVT_UF, gen_helper_gvec_touszh, gen_helper_gvec_touizs)
if (a->size != 2) { DO_2MISC_FP_VEC(VRINTX_impl, gen_helper_gvec_vrintx_h, gen_helper_gvec_vrintx_s)
/* TODO: FP16 will be the size == 1 case */
return false;
}
if ((a->vd | a->vm) & a->q) {
return false;
}
if (!vfp_access_check(s)) {
return true;
}
fpst = fpstatus_ptr(FPST_STD);
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 tmp = neon_load_reg(a->vm, pass);
fn(tmp, tmp, fpst);
neon_store_reg(a->vd, pass, tmp);
}
tcg_temp_free_ptr(fpst);
return true;
}
#define DO_2MISC_FP(INSN, FUNC) \
static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
{ \
return do_2misc_fp(s, a, FUNC); \
}
DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32)
DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32)
DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos)
DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos)
DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs)
DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs)
static bool trans_VRINTX(DisasContext *s, arg_2misc *a) static bool trans_VRINTX(DisasContext *s, arg_2misc *a)
{ {
if (!arm_dc_feature(s, ARM_FEATURE_V8)) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
return false; return false;
} }
return do_2misc_fp(s, a, gen_helper_rints_exact); return trans_VRINTX_impl(s, a);
} }
#define WRAP_FP_CMP0_FWD(WRAPNAME, FUNC) \ #define DO_VEC_RMODE(INSN, RMODE, OP) \
static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \
{ \ uint32_t rm_ofs, \
TCGv_i32 zero = tcg_const_i32(0); \ uint32_t oprsz, uint32_t maxsz) \
FUNC(d, m, zero, fpst); \ { \
tcg_temp_free_i32(zero); \ static gen_helper_gvec_2_ptr * const fns[4] = { \
} NULL, \
#define WRAP_FP_CMP0_REV(WRAPNAME, FUNC) \ gen_helper_gvec_##OP##h, \
static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ gen_helper_gvec_##OP##s, \
{ \ NULL, \
TCGv_i32 zero = tcg_const_i32(0); \ }; \
FUNC(d, zero, m, fpst); \ TCGv_ptr fpst; \
tcg_temp_free_i32(zero); \ fpst = fpstatus_ptr(vece == 1 ? FPST_STD_F16 : FPST_STD); \
tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, oprsz, maxsz, \
arm_rmode_to_sf(RMODE), fns[vece]); \
tcg_temp_free_ptr(fpst); \
} \
static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
{ \
if (!arm_dc_feature(s, ARM_FEATURE_V8)) { \
return false; \
} \
if (a->size == MO_16) { \
if (!dc_isar_feature(aa32_fp16_arith, s)) { \
return false; \
} \
} else if (a->size != MO_32) { \
return false; \
} \
return do_2misc_vec(s, a, gen_##INSN); \
} }
#define DO_FP_CMP0(INSN, FUNC, REV) \ DO_VEC_RMODE(VCVTAU, FPROUNDING_TIEAWAY, vcvt_rm_u)
WRAP_FP_CMP0_##REV(gen_##INSN, FUNC) \ DO_VEC_RMODE(VCVTAS, FPROUNDING_TIEAWAY, vcvt_rm_s)
static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ DO_VEC_RMODE(VCVTNU, FPROUNDING_TIEEVEN, vcvt_rm_u)
{ \ DO_VEC_RMODE(VCVTNS, FPROUNDING_TIEEVEN, vcvt_rm_s)
return do_2misc_fp(s, a, gen_##INSN); \ DO_VEC_RMODE(VCVTPU, FPROUNDING_POSINF, vcvt_rm_u)
} DO_VEC_RMODE(VCVTPS, FPROUNDING_POSINF, vcvt_rm_s)
DO_VEC_RMODE(VCVTMU, FPROUNDING_NEGINF, vcvt_rm_u)
DO_VEC_RMODE(VCVTMS, FPROUNDING_NEGINF, vcvt_rm_s)
DO_FP_CMP0(VCGT0_F, gen_helper_neon_cgt_f32, FWD) DO_VEC_RMODE(VRINTN, FPROUNDING_TIEEVEN, vrint_rm_)
DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD) DO_VEC_RMODE(VRINTA, FPROUNDING_TIEAWAY, vrint_rm_)
DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD) DO_VEC_RMODE(VRINTZ, FPROUNDING_ZERO, vrint_rm_)
DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV) DO_VEC_RMODE(VRINTM, FPROUNDING_NEGINF, vrint_rm_)
DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV) DO_VEC_RMODE(VRINTP, FPROUNDING_POSINF, vrint_rm_)
static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode)
{
/*
* Handle a VRINT* operation by iterating 32 bits at a time,
* with a specified rounding mode in operation.
*/
int pass;
TCGv_ptr fpst;
TCGv_i32 tcg_rmode;
if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
!arm_dc_feature(s, ARM_FEATURE_V8)) {
return false;
}
/* UNDEF accesses to D16-D31 if they don't exist. */
if (!dc_isar_feature(aa32_simd_r32, s) &&
((a->vd | a->vm) & 0x10)) {
return false;
}
if (a->size != 2) {
/* TODO: FP16 will be the size == 1 case */
return false;
}
if ((a->vd | a->vm) & a->q) {
return false;
}
if (!vfp_access_check(s)) {
return true;
}
fpst = fpstatus_ptr(FPST_STD);
tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 tmp = neon_load_reg(a->vm, pass);
gen_helper_rints(tmp, tmp, fpst);
neon_store_reg(a->vd, pass, tmp);
}
gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
tcg_temp_free_i32(tcg_rmode);
tcg_temp_free_ptr(fpst);
return true;
}
#define DO_VRINT(INSN, RMODE) \
static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
{ \
return do_vrint(s, a, RMODE); \
}
DO_VRINT(VRINTN, FPROUNDING_TIEEVEN)
DO_VRINT(VRINTA, FPROUNDING_TIEAWAY)
DO_VRINT(VRINTZ, FPROUNDING_ZERO)
DO_VRINT(VRINTM, FPROUNDING_NEGINF)
DO_VRINT(VRINTP, FPROUNDING_POSINF)
static bool do_vcvt(DisasContext *s, arg_2misc *a, int rmode, bool is_signed)
{
/*
* Handle a VCVT* operation by iterating 32 bits at a time,
* with a specified rounding mode in operation.
*/
int pass;
TCGv_ptr fpst;
TCGv_i32 tcg_rmode, tcg_shift;
if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
!arm_dc_feature(s, ARM_FEATURE_V8)) {
return false;
}
/* UNDEF accesses to D16-D31 if they don't exist. */
if (!dc_isar_feature(aa32_simd_r32, s) &&
((a->vd | a->vm) & 0x10)) {
return false;
}
if (a->size != 2) {
/* TODO: FP16 will be the size == 1 case */
return false;
}
if ((a->vd | a->vm) & a->q) {
return false;
}
if (!vfp_access_check(s)) {
return true;
}
fpst = fpstatus_ptr(FPST_STD);
tcg_shift = tcg_const_i32(0);
tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 tmp = neon_load_reg(a->vm, pass);
if (is_signed) {
gen_helper_vfp_tosls(tmp, tmp, tcg_shift, fpst);
} else {
gen_helper_vfp_touls(tmp, tmp, tcg_shift, fpst);
}
neon_store_reg(a->vd, pass, tmp);
}
gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
tcg_temp_free_i32(tcg_rmode);
tcg_temp_free_i32(tcg_shift);
tcg_temp_free_ptr(fpst);
return true;
}
#define DO_VCVT(INSN, RMODE, SIGNED) \
static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
{ \
return do_vcvt(s, a, RMODE, SIGNED); \
}
DO_VCVT(VCVTAU, FPROUNDING_TIEAWAY, false)
DO_VCVT(VCVTAS, FPROUNDING_TIEAWAY, true)
DO_VCVT(VCVTNU, FPROUNDING_TIEEVEN, false)
DO_VCVT(VCVTNS, FPROUNDING_TIEEVEN, true)
DO_VCVT(VCVTPU, FPROUNDING_POSINF, false)
DO_VCVT(VCVTPS, FPROUNDING_POSINF, true)
DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false)
DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true)
static bool trans_VSWP(DisasContext *s, arg_2misc *a) static bool trans_VSWP(DisasContext *s, arg_2misc *a)
{ {

4
target/arm/translate-sve.c
View File

@ -3803,10 +3803,6 @@ static bool trans_##NAME##_zpzi(DisasContext *s, arg_rpri_esz *a) \
return true; \ 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(FADD, fadds, half, one)
DO_FP_IMM(FSUB, fsubs, half, one) DO_FP_IMM(FSUB, fsubs, half, one)
DO_FP_IMM(FMUL, fmuls, half, two) DO_FP_IMM(FMUL, fmuls, half, two)

810
target/arm/translate-vfp.c.inc
View File

File diff suppressed because it is too large Load Diff

431
target/arm/vec_helper.c
View File

@ -656,6 +656,81 @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
clear_tail(d, opr_sz, simd_maxsz(desc)); clear_tail(d, opr_sz, simd_maxsz(desc));
} }
/*
* Floating point comparisons producing an integer result (all 1s or all 0s).
* Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do.
* Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires.
*/
static uint16_t float16_ceq(float16 op1, float16 op2, float_status *stat)
{
return -float16_eq_quiet(op1, op2, stat);
}
static uint32_t float32_ceq(float32 op1, float32 op2, float_status *stat)
{
return -float32_eq_quiet(op1, op2, stat);
}
static uint16_t float16_cge(float16 op1, float16 op2, float_status *stat)
{
return -float16_le(op2, op1, stat);
}
static uint32_t float32_cge(float32 op1, float32 op2, float_status *stat)
{
return -float32_le(op2, op1, stat);
}
static uint16_t float16_cgt(float16 op1, float16 op2, float_status *stat)
{
return -float16_lt(op2, op1, stat);
}
static uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat)
{
return -float32_lt(op2, op1, stat);
}
static uint16_t float16_acge(float16 op1, float16 op2, float_status *stat)
{
return -float16_le(float16_abs(op2), float16_abs(op1), stat);
}
static uint32_t float32_acge(float32 op1, float32 op2, float_status *stat)
{
return -float32_le(float32_abs(op2), float32_abs(op1), stat);
}
static uint16_t float16_acgt(float16 op1, float16 op2, float_status *stat)
{
return -float16_lt(float16_abs(op2), float16_abs(op1), stat);
}
static uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat)
{
return -float32_lt(float32_abs(op2), float32_abs(op1), stat);
}
static int16_t vfp_tosszh(float16 x, void *fpstp)
{
float_status *fpst = fpstp;
if (float16_is_any_nan(x)) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_int16_round_to_zero(x, fpst);
}
static uint16_t vfp_touszh(float16 x, void *fpstp)
{
float_status *fpst = fpstp;
if (float16_is_any_nan(x)) {
float_raise(float_flag_invalid, fpst);
return 0;
}
return float16_to_uint16_round_to_zero(x, fpst);
}
#define DO_2OP(NAME, FUNC, TYPE) \ #define DO_2OP(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \
{ \ { \
@ -675,7 +750,44 @@ DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16)
DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32)
DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64)
DO_2OP(gvec_vrintx_h, float16_round_to_int, float16)
DO_2OP(gvec_vrintx_s, float32_round_to_int, float32)
DO_2OP(gvec_sitos, helper_vfp_sitos, int32_t)
DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t)
DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32)
DO_2OP(gvec_touizs, helper_vfp_touizs, float32)
DO_2OP(gvec_sstoh, int16_to_float16, int16_t)
DO_2OP(gvec_ustoh, uint16_to_float16, uint16_t)
DO_2OP(gvec_tosszh, vfp_tosszh, float16)
DO_2OP(gvec_touszh, vfp_touszh, float16)
#define WRAP_CMP0_FWD(FN, CMPOP, TYPE) \
static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \
{ \
return TYPE##_##CMPOP(op, TYPE##_zero, stat); \
}
#define WRAP_CMP0_REV(FN, CMPOP, TYPE) \
static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \
{ \
return TYPE##_##CMPOP(TYPE##_zero, op, stat); \
}
#define DO_2OP_CMP0(FN, CMPOP, DIRN) \
WRAP_CMP0_##DIRN(FN, CMPOP, float16) \
WRAP_CMP0_##DIRN(FN, CMPOP, float32) \
DO_2OP(gvec_f##FN##0_h, float16_##FN##0, float16) \
DO_2OP(gvec_f##FN##0_s, float32_##FN##0, float32)
DO_2OP_CMP0(cgt, cgt, FWD)
DO_2OP_CMP0(cge, cge, FWD)
DO_2OP_CMP0(ceq, ceq, FWD)
DO_2OP_CMP0(clt, cgt, REV)
DO_2OP_CMP0(cle, cge, REV)
#undef DO_2OP #undef DO_2OP
#undef DO_2OP_CMP0
/* Floating-point trigonometric starting value. /* Floating-point trigonometric starting value.
* See the ARM ARM pseudocode function FPTrigSMul. * See the ARM ARM pseudocode function FPTrigSMul.
@ -707,11 +819,71 @@ static float64 float64_ftsmul(float64 op1, uint64_t op2, float_status *stat)
return result; return result;
} }
static float16 float16_abd(float16 op1, float16 op2, float_status *stat)
{
return float16_abs(float16_sub(op1, op2, stat));
}
static float32 float32_abd(float32 op1, float32 op2, float_status *stat) static float32 float32_abd(float32 op1, float32 op2, float_status *stat)
{ {
return float32_abs(float32_sub(op1, op2, stat)); return float32_abs(float32_sub(op1, op2, stat));
} }
/*
* Reciprocal step. These are the AArch32 version which uses a
* non-fused multiply-and-subtract.
*/
static float16 float16_recps_nf(float16 op1, float16 op2, float_status *stat)
{
op1 = float16_squash_input_denormal(op1, stat);
op2 = float16_squash_input_denormal(op2, stat);
if ((float16_is_infinity(op1) && float16_is_zero(op2)) ||
(float16_is_infinity(op2) && float16_is_zero(op1))) {
return float16_two;
}
return float16_sub(float16_two, float16_mul(op1, op2, stat), stat);
}
static float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat)
{
op1 = float32_squash_input_denormal(op1, stat);
op2 = float32_squash_input_denormal(op2, stat);
if ((float32_is_infinity(op1) && float32_is_zero(op2)) ||
(float32_is_infinity(op2) && float32_is_zero(op1))) {
return float32_two;
}
return float32_sub(float32_two, float32_mul(op1, op2, stat), stat);
}
/* Reciprocal square-root step. AArch32 non-fused semantics. */
static float16 float16_rsqrts_nf(float16 op1, float16 op2, float_status *stat)
{
op1 = float16_squash_input_denormal(op1, stat);
op2 = float16_squash_input_denormal(op2, stat);
if ((float16_is_infinity(op1) && float16_is_zero(op2)) ||
(float16_is_infinity(op2) && float16_is_zero(op1))) {
return float16_one_point_five;
}
op1 = float16_sub(float16_three, float16_mul(op1, op2, stat), stat);
return float16_div(op1, float16_two, stat);
}
static float32 float32_rsqrts_nf(float32 op1, float32 op2, float_status *stat)
{
op1 = float32_squash_input_denormal(op1, stat);
op2 = float32_squash_input_denormal(op2, stat);
if ((float32_is_infinity(op1) && float32_is_zero(op2)) ||
(float32_is_infinity(op2) && float32_is_zero(op1))) {
return float32_one_point_five;
}
op1 = float32_sub(float32_three, float32_mul(op1, op2, stat), stat);
return float32_div(op1, float32_two, stat);
}
#define DO_3OP(NAME, FUNC, TYPE) \ #define DO_3OP(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
{ \ { \
@ -739,8 +911,42 @@ DO_3OP(gvec_ftsmul_h, float16_ftsmul, float16)
DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32) DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32)
DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64)
DO_3OP(gvec_fabd_h, float16_abd, float16)
DO_3OP(gvec_fabd_s, float32_abd, float32) DO_3OP(gvec_fabd_s, float32_abd, float32)
DO_3OP(gvec_fceq_h, float16_ceq, float16)
DO_3OP(gvec_fceq_s, float32_ceq, float32)
DO_3OP(gvec_fcge_h, float16_cge, float16)
DO_3OP(gvec_fcge_s, float32_cge, float32)
DO_3OP(gvec_fcgt_h, float16_cgt, float16)
DO_3OP(gvec_fcgt_s, float32_cgt, float32)
DO_3OP(gvec_facge_h, float16_acge, float16)
DO_3OP(gvec_facge_s, float32_acge, float32)
DO_3OP(gvec_facgt_h, float16_acgt, float16)
DO_3OP(gvec_facgt_s, float32_acgt, float32)
DO_3OP(gvec_fmax_h, float16_max, float16)
DO_3OP(gvec_fmax_s, float32_max, float32)
DO_3OP(gvec_fmin_h, float16_min, float16)
DO_3OP(gvec_fmin_s, float32_min, float32)
DO_3OP(gvec_fmaxnum_h, float16_maxnum, float16)
DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32)
DO_3OP(gvec_fminnum_h, float16_minnum, float16)
DO_3OP(gvec_fminnum_s, float32_minnum, float32)
DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16)
DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32)
DO_3OP(gvec_rsqrts_nf_h, float16_rsqrts_nf, float16)
DO_3OP(gvec_rsqrts_nf_s, float32_rsqrts_nf, float32)
#ifdef TARGET_AARCH64 #ifdef TARGET_AARCH64
DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) DO_3OP(gvec_recps_h, helper_recpsf_f16, float16)
@ -754,6 +960,79 @@ DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64)
#endif #endif
#undef DO_3OP #undef DO_3OP
/* Non-fused multiply-add (unlike float16_muladd etc, which are fused) */
static float16 float16_muladd_nf(float16 dest, float16 op1, float16 op2,
float_status *stat)
{
return float16_add(dest, float16_mul(op1, op2, stat), stat);
}
static float32 float32_muladd_nf(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
return float32_add(dest, float32_mul(op1, op2, stat), stat);
}
static float16 float16_mulsub_nf(float16 dest, float16 op1, float16 op2,
float_status *stat)
{
return float16_sub(dest, float16_mul(op1, op2, stat), stat);
}
static float32 float32_mulsub_nf(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
return float32_sub(dest, float32_mul(op1, op2, stat), stat);
}
/* Fused versions; these have the semantics Neon VFMA/VFMS want */
static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2,
float_status *stat)
{
return float16_muladd(op1, op2, dest, 0, stat);
}
static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
return float32_muladd(op1, op2, dest, 0, stat);
}
static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2,
float_status *stat)
{
return float16_muladd(float16_chs(op1), op2, dest, 0, stat);
}
static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
return float32_muladd(float32_chs(op1), op2, dest, 0, stat);
}
#define DO_MULADD(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
{ \
intptr_t i, oprsz = simd_oprsz(desc); \
TYPE *d = vd, *n = vn, *m = vm; \
for (i = 0; i < oprsz / sizeof(TYPE); i++) { \
d[i] = FUNC(d[i], n[i], m[i], stat); \
} \
clear_tail(d, oprsz, simd_maxsz(desc)); \
}
DO_MULADD(gvec_fmla_h, float16_muladd_nf, float16)
DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32)
DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16)
DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32)
DO_MULADD(gvec_vfma_h, float16_muladd_f, float16)
DO_MULADD(gvec_vfma_s, float32_muladd_f, float32)
DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
/* For the indexed ops, SVE applies the index per 128-bit vector segment. /* For the indexed ops, SVE applies the index per 128-bit vector segment.
* For AdvSIMD, there is of course only one such vector segment. * For AdvSIMD, there is of course only one such vector segment.
*/ */
@ -761,7 +1040,8 @@ DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64)
#define DO_MUL_IDX(NAME, TYPE, H) \ #define DO_MUL_IDX(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \ { \
intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ intptr_t i, j, oprsz = simd_oprsz(desc); \
intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \
intptr_t idx = simd_data(desc); \ intptr_t idx = simd_data(desc); \
TYPE *d = vd, *n = vn, *m = vm; \ TYPE *d = vd, *n = vn, *m = vm; \
for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \
@ -782,7 +1062,8 @@ DO_MUL_IDX(gvec_mul_idx_d, uint64_t, )
#define DO_MLA_IDX(NAME, TYPE, OP, H) \ #define DO_MLA_IDX(NAME, TYPE, OP, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
{ \ { \
intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ intptr_t i, j, oprsz = simd_oprsz(desc); \
intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \
intptr_t idx = simd_data(desc); \ intptr_t idx = simd_data(desc); \
TYPE *d = vd, *n = vn, *m = vm, *a = va; \ TYPE *d = vd, *n = vn, *m = vm, *a = va; \
for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \
@ -804,32 +1085,51 @@ DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, )
#undef DO_MLA_IDX #undef DO_MLA_IDX
#define DO_FMUL_IDX(NAME, TYPE, H) \ #define DO_FMUL_IDX(NAME, ADD, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
{ \ { \
intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ intptr_t i, j, oprsz = simd_oprsz(desc); \
intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \
intptr_t idx = simd_data(desc); \ intptr_t idx = simd_data(desc); \
TYPE *d = vd, *n = vn, *m = vm; \ TYPE *d = vd, *n = vn, *m = vm; \
for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \
TYPE mm = m[H(i + idx)]; \ TYPE mm = m[H(i + idx)]; \
for (j = 0; j < segment; j++) { \ for (j = 0; j < segment; j++) { \
d[i + j] = TYPE##_mul(n[i + j], mm, stat); \ d[i + j] = TYPE##_##ADD(d[i + j], \
TYPE##_mul(n[i + j], mm, stat), stat); \
} \ } \
} \ } \
clear_tail(d, oprsz, simd_maxsz(desc)); \ clear_tail(d, oprsz, simd_maxsz(desc)); \
} }
DO_FMUL_IDX(gvec_fmul_idx_h, float16, H2) #define float16_nop(N, M, S) (M)
DO_FMUL_IDX(gvec_fmul_idx_s, float32, H4) #define float32_nop(N, M, S) (M)
DO_FMUL_IDX(gvec_fmul_idx_d, float64, ) #define float64_nop(N, M, S) (M)
DO_FMUL_IDX(gvec_fmul_idx_h, nop, float16, H2)
DO_FMUL_IDX(gvec_fmul_idx_s, nop, float32, H4)
DO_FMUL_IDX(gvec_fmul_idx_d, nop, float64, )
/*
* Non-fused multiply-accumulate operations, for Neon. NB that unlike
* the fused ops below they assume accumulate both from and into Vd.
*/
DO_FMUL_IDX(gvec_fmla_nf_idx_h, add, float16, H2)
DO_FMUL_IDX(gvec_fmla_nf_idx_s, add, float32, H4)
DO_FMUL_IDX(gvec_fmls_nf_idx_h, sub, float16, H2)
DO_FMUL_IDX(gvec_fmls_nf_idx_s, sub, float32, H4)
#undef float16_nop
#undef float32_nop
#undef float64_nop
#undef DO_FMUL_IDX #undef DO_FMUL_IDX
#define DO_FMLA_IDX(NAME, TYPE, H) \ #define DO_FMLA_IDX(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \
void *stat, uint32_t desc) \ void *stat, uint32_t desc) \
{ \ { \
intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ intptr_t i, j, oprsz = simd_oprsz(desc); \
intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \
TYPE op1_neg = extract32(desc, SIMD_DATA_SHIFT, 1); \ TYPE op1_neg = extract32(desc, SIMD_DATA_SHIFT, 1); \
intptr_t idx = desc >> (SIMD_DATA_SHIFT + 1); \ intptr_t idx = desc >> (SIMD_DATA_SHIFT + 1); \
TYPE *d = vd, *n = vn, *m = vm, *a = va; \ TYPE *d = vd, *n = vn, *m = vm, *a = va; \
@ -1524,3 +1824,116 @@ DO_ABA(gvec_uaba_s, uint32_t)
DO_ABA(gvec_uaba_d, uint64_t) DO_ABA(gvec_uaba_d, uint64_t)
#undef DO_ABA #undef DO_ABA
#define DO_NEON_PAIRWISE(NAME, OP) \
void HELPER(NAME##s)(void *vd, void *vn, void *vm, \
void *stat, uint32_t oprsz) \
{ \
float_status *fpst = stat; \
float32 *d = vd; \
float32 *n = vn; \
float32 *m = vm; \
float32 r0, r1; \
\
/* Read all inputs before writing outputs in case vm == vd */ \
r0 = float32_##OP(n[H4(0)], n[H4(1)], fpst); \
r1 = float32_##OP(m[H4(0)], m[H4(1)], fpst); \
\
d[H4(0)] = r0; \
d[H4(1)] = r1; \
} \
\
void HELPER(NAME##h)(void *vd, void *vn, void *vm, \
void *stat, uint32_t oprsz) \
{ \
float_status *fpst = stat; \
float16 *d = vd; \
float16 *n = vn; \
float16 *m = vm; \
float16 r0, r1, r2, r3; \
\
/* Read all inputs before writing outputs in case vm == vd */ \
r0 = float16_##OP(n[H2(0)], n[H2(1)], fpst); \
r1 = float16_##OP(n[H2(2)], n[H2(3)], fpst); \
r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \
r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \
\
d[H4(0)] = r0; \
d[H4(1)] = r1; \
d[H4(2)] = r2; \
d[H4(3)] = r3; \
}
DO_NEON_PAIRWISE(neon_padd, add)
DO_NEON_PAIRWISE(neon_pmax, max)
DO_NEON_PAIRWISE(neon_pmin, min)
#undef DO_NEON_PAIRWISE
#define DO_VCVT_FIXED(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \
{ \
intptr_t i, oprsz = simd_oprsz(desc); \
int shift = simd_data(desc); \
TYPE *d = vd, *n = vn; \
float_status *fpst = stat; \
for (i = 0; i < oprsz / sizeof(TYPE); i++) { \
d[i] = FUNC(n[i], shift, fpst); \
} \
clear_tail(d, oprsz, simd_maxsz(desc)); \
}
DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t)
DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t)
DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t)
DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t)
DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t)
DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t)
DO_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t)
DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t)
#undef DO_VCVT_FIXED
#define DO_VCVT_RMODE(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \
{ \
float_status *fpst = stat; \
intptr_t i, oprsz = simd_oprsz(desc); \
uint32_t rmode = simd_data(desc); \
uint32_t prev_rmode = get_float_rounding_mode(fpst); \
TYPE *d = vd, *n = vn; \
set_float_rounding_mode(rmode, fpst); \
for (i = 0; i < oprsz / sizeof(TYPE); i++) { \
d[i] = FUNC(n[i], 0, fpst); \
} \
set_float_rounding_mode(prev_rmode, fpst); \
clear_tail(d, oprsz, simd_maxsz(desc)); \
}
DO_VCVT_RMODE(gvec_vcvt_rm_ss, helper_vfp_tosls, uint32_t)
DO_VCVT_RMODE(gvec_vcvt_rm_us, helper_vfp_touls, uint32_t)
DO_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t)
DO_VCVT_RMODE(gvec_vcvt_rm_uh, helper_vfp_touhh, uint16_t)
#undef DO_VCVT_RMODE
#define DO_VRINT_RMODE(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \
{ \
float_status *fpst = stat; \
intptr_t i, oprsz = simd_oprsz(desc); \
uint32_t rmode = simd_data(desc); \
uint32_t prev_rmode = get_float_rounding_mode(fpst); \
TYPE *d = vd, *n = vn; \
set_float_rounding_mode(rmode, fpst); \
for (i = 0; i < oprsz / sizeof(TYPE); i++) { \
d[i] = FUNC(n[i], fpst); \
} \
set_float_rounding_mode(prev_rmode, fpst); \
clear_tail(d, oprsz, simd_maxsz(desc)); \
}
DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t)
DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t)
#undef DO_VRINT_RMODE

27
target/arm/vfp-uncond.decode
View File

@ -44,10 +44,15 @@
@vfp_dnm_s ................................ vm=%vm_sp vn=%vn_sp vd=%vd_sp @vfp_dnm_s ................................ vm=%vm_sp vn=%vn_sp vd=%vd_sp
@vfp_dnm_d ................................ vm=%vm_dp vn=%vn_dp vd=%vd_dp @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 .... \ 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 .... \ 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 VMAXNM_sp 1111 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s
VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @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 VMAXNM_dp 1111 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d
VMINNM_dp 1111 1110 1.00 .... .... 1011 .1.0 .... @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 .... \ 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 .... \ 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 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 .... \ 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 .... \ 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

34
target/arm/vfp.decode
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 vn=%vn_dp
VMSR_VMRS ---- 1110 111 l:1 reg:4 rt:4 1010 0001 0000 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_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_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 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 VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8 vd=%vd_sp
# not part of this decodetree at all because they have bits [9:8] == 0b01
VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 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 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 vd=%vd_dp p=1 u=0 w=1
# 3-register VFP data-processing; bits [23,21:20,6] identify the operation. # 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_sp ---- 1110 0.00 .... .... 1010 .0.0 .... @vfp_dnm_s
VMLA_dp ---- 1110 0.00 .... .... 1011 .0.0 .... @vfp_dnm_d 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_sp ---- 1110 0.00 .... .... 1010 .1.0 .... @vfp_dnm_s
VMLS_dp ---- 1110 0.00 .... .... 1011 .1.0 .... @vfp_dnm_d 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_sp ---- 1110 0.01 .... .... 1010 .0.0 .... @vfp_dnm_s
VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d 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_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s
VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d 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_sp ---- 1110 0.10 .... .... 1010 .0.0 .... @vfp_dnm_s
VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... @vfp_dnm_d 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_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s
VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d 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_sp ---- 1110 0.11 .... .... 1010 .0.0 .... @vfp_dnm_s
VADD_dp ---- 1110 0.11 .... .... 1011 .0.0 .... @vfp_dnm_d 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_sp ---- 1110 0.11 .... .... 1010 .1.0 .... @vfp_dnm_s
VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... @vfp_dnm_d 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_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s
VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d 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 VFMA_sp ---- 1110 1.10 .... .... 1010 .0. 0 .... @vfp_dnm_s
VFMS_sp ---- 1110 1.10 .... .... 1010 .1. 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 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 VFNMA_dp ---- 1110 1.01 .... .... 1011 .0.0 .... @vfp_dnm_d
VFNMS_dp ---- 1110 1.01 .... .... 1011 .1.0 .... @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 .... \ VMOV_imm_sp ---- 1110 1.11 .... .... 1010 0000 .... \
vd=%vd_sp imm=%vmov_imm vd=%vd_sp imm=%vmov_imm
VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ 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_sp ---- 1110 1.11 0000 .... 1010 01.0 .... @vfp_dm_ss
VMOV_reg_dp ---- 1110 1.11 0000 .... 1011 01.0 .... @vfp_dm_dd 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_sp ---- 1110 1.11 0000 .... 1010 11.0 .... @vfp_dm_ss
VABS_dp ---- 1110 1.11 0000 .... 1011 11.0 .... @vfp_dm_dd 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_sp ---- 1110 1.11 0001 .... 1010 01.0 .... @vfp_dm_ss
VNEG_dp ---- 1110 1.11 0001 .... 1011 01.0 .... @vfp_dm_dd 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_sp ---- 1110 1.11 0001 .... 1010 11.0 .... @vfp_dm_ss
VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... @vfp_dm_dd 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 .... \ VCMP_sp ---- 1110 1.11 010 z:1 .... 1010 e:1 1.0 .... \
vd=%vd_sp vm=%vm_sp vd=%vd_sp vm=%vm_sp
VCMP_dp ---- 1110 1.11 010 z:1 .... 1011 e:1 1.0 .... \ 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 .... \ VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \
vd=%vd_sp vm=%vm_dp 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_sp ---- 1110 1.11 0110 .... 1010 01.0 .... @vfp_dm_ss
VRINTR_dp ---- 1110 1.11 0110 .... 1011 01.0 .... @vfp_dm_dd 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_sp ---- 1110 1.11 0110 .... 1010 11.0 .... @vfp_dm_ss
VRINTZ_dp ---- 1110 1.11 0110 .... 1011 11.0 .... @vfp_dm_dd 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_sp ---- 1110 1.11 0111 .... 1010 01.0 .... @vfp_dm_ss
VRINTX_dp ---- 1110 1.11 0111 .... 1011 01.0 .... @vfp_dm_dd 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_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 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 .... \ VCVT_int_sp ---- 1110 1.11 1000 .... 1010 s:1 1.0 .... \
vd=%vd_sp vm=%vm_sp vd=%vd_sp vm=%vm_sp
VCVT_int_dp ---- 1110 1.11 1000 .... 1011 s:1 1.0 .... \ 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 # We assemble bits 18 (op), 16 (u) and 7 (sx) into a single opc field
# for the convenience of the trans_VCVT_fix functions. # for the convenience of the trans_VCVT_fix functions.
%vcvt_fix_op 18:1 16:1 7:1 %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 .... \ VCVT_fix_sp ---- 1110 1.11 1.1. .... 1010 .1.0 .... \
vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op
VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \ VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \
vd=%vd_dp imm=%vm_sp opc=%vcvt_fix_op 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 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 .... \ VCVT_sp_int ---- 1110 1.11 110 s:1 .... 1010 rz:1 1.0 .... \
vd=%vd_sp vm=%vm_sp vd=%vd_sp vm=%vm_sp
VCVT_dp_int ---- 1110 1.11 110 s:1 .... 1011 rz:1 1.0 .... \ VCVT_dp_int ---- 1110 1.11 110 s:1 .... 1011 rz:1 1.0 .... \

244
target/arm/vfp_helper.c
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_HELPER(name, p) HELPER(glue(glue(vfp_,name),p))
#define VFP_BINOP(name) \ #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) \ float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \
{ \ { \
float_status *fpst = fpstp; \ float_status *fpst = fpstp; \
@ -256,6 +261,11 @@ VFP_BINOP(minnum)
VFP_BINOP(maxnum) VFP_BINOP(maxnum)
#undef VFP_BINOP #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) float32 VFP_HELPER(neg, s)(float32 a)
{ {
return float32_chs(a); return float32_chs(a);
@ -266,6 +276,11 @@ float64 VFP_HELPER(neg, d)(float64 a)
return float64_chs(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) float32 VFP_HELPER(abs, s)(float32 a)
{ {
return float32_abs(a); return float32_abs(a);
@ -276,6 +291,11 @@ float64 VFP_HELPER(abs, d)(float64 a)
return float64_abs(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) float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env)
{ {
return float32_sqrt(a, &env->vfp.fp_status); 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 */ /* XXX: check quiet/signaling case */
#define DO_VFP_cmp(p, type) \ #define DO_VFP_cmp(P, FLOATTYPE, ARGTYPE, FPST) \
void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \ void VFP_HELPER(cmp, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \
{ \ { \
softfloat_to_vfp_compare(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, \ 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(h, float16, dh_ctype_f16, fp_status_f16)
DO_VFP_cmp(d, float64) DO_VFP_cmp(s, float32, float32, fp_status)
DO_VFP_cmp(d, float64, float64, fp_status)
#undef DO_VFP_cmp #undef DO_VFP_cmp
/* Integer to float and float to integer conversions */ /* 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. */ /* VFP3 fixed point conversion. */
#define VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ #define VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \
float##fsz HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \ ftype HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \
void *fpstp) \ void *fpstp) \
{ return itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); } { return itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); }
#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, ROUND, suff) \ #define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, ROUND, suff) \
uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \ uint##isz##_t HELPER(vfp_to##name##p##suff)(ftype x, uint32_t shift, \
void *fpst) \ void *fpst) \
{ \ { \
if (unlikely(float##fsz##_is_any_nan(x))) { \ 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); \ return float##fsz##_to_##itype##_scalbn(x, ROUND, shift, fpst); \
} }
#define VFP_CONV_FIX(name, p, fsz, isz, itype) \ #define VFP_CONV_FIX(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \
float_round_to_zero, _round_to_zero) \ 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), ) get_float_rounding_mode(fpst), )
#define VFP_CONV_FIX_A64(name, p, fsz, isz, itype) \ #define VFP_CONV_FIX_A64(name, p, fsz, ftype, isz, itype) \
VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \
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), ) get_float_rounding_mode(fpst), )
VFP_CONV_FIX(sh, d, 64, 64, int16) VFP_CONV_FIX(sh, d, 64, float64, 64, int16)
VFP_CONV_FIX(sl, d, 64, 64, int32) VFP_CONV_FIX(sl, d, 64, float64, 64, int32)
VFP_CONV_FIX_A64(sq, d, 64, 64, int64) VFP_CONV_FIX_A64(sq, d, 64, float64, 64, int64)
VFP_CONV_FIX(uh, d, 64, 64, uint16) VFP_CONV_FIX(uh, d, 64, float64, 64, uint16)
VFP_CONV_FIX(ul, d, 64, 64, uint32) VFP_CONV_FIX(ul, d, 64, float64, 64, uint32)
VFP_CONV_FIX_A64(uq, d, 64, 64, uint64) VFP_CONV_FIX_A64(uq, d, 64, float64, 64, uint64)
VFP_CONV_FIX(sh, s, 32, 32, int16) VFP_CONV_FIX(sh, s, 32, float32, 32, int16)
VFP_CONV_FIX(sl, s, 32, 32, int32) VFP_CONV_FIX(sl, s, 32, float32, 32, int32)
VFP_CONV_FIX_A64(sq, s, 32, 64, int64) VFP_CONV_FIX_A64(sq, s, 32, float32, 64, int64)
VFP_CONV_FIX(uh, s, 32, 32, uint16) VFP_CONV_FIX(uh, s, 32, float32, 32, uint16)
VFP_CONV_FIX(ul, s, 32, 32, uint32) VFP_CONV_FIX(ul, s, 32, float32, 32, uint32)
VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) 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
#undef VFP_CONV_FIX_FLOAT #undef VFP_CONV_FIX_FLOAT
#undef VFP_CONV_FLOAT_FIX_ROUND #undef VFP_CONV_FLOAT_FIX_ROUND
#undef VFP_CONV_FIX_A64 #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. /* Set the current fp rounding mode and return the old one.
* The argument is a softfloat float_round_ value. * 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; 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. */ /* Half precision conversions. */
float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) 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; 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. */ /* NEON helpers. */
/* Constants 256 and 512 are used in some helpers; we avoid relying on /* 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 */ /* 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) float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp)
{ {
float_status *fpst = 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 */ /* 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) float32 HELPER(rints_exact)(float32 x, void *fp_status)
{ {
return float32_round_to_int(x, 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); 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) float32 HELPER(rints)(float32 x, void *fp_status)
{ {
int old_flags = get_float_exception_flags(fp_status), new_flags; int old_flags = get_float_exception_flags(fp_status), new_flags;