diff options
| author | Dongjiu Geng <gengdongjiu@huawei.com> | 2017-12-13 13:13:56 +0300 |
|---|---|---|
| committer | Catalin Marinas <catalin.marinas@arm.com> | 2018-01-05 14:29:48 +0300 |
| commit | 3b3b681097fae73b7f5dcdd42db6cfdf32943d4c (patch) | |
| tree | 514122d4fd4358c7dfda62c2294ad31215e0aed6 /arch/arm64 | |
| parent | a8ffaaa060b8d4da6138e0958cb0f45b73e1cb78 (diff) | |
| download | linux-3b3b681097fae73b7f5dcdd42db6cfdf32943d4c.tar.xz | |
arm64: v8.4: Support for new floating point multiplication instructions
ARM v8.4 extensions add new neon instructions for performing a
multiplication of each FP16 element of one vector with the corresponding
FP16 element of a second vector, and to add or subtract this without an
intermediate rounding to the corresponding FP32 element in a third vector.
This patch detects this feature and let the userspace know about it via a
HWCAP bit and MRS emulation.
Cc: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com>
Reviewed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Diffstat (limited to 'arch/arm64')
| -rw-r--r-- | arch/arm64/include/asm/sysreg.h | 1 | ||||
| -rw-r--r-- | arch/arm64/include/uapi/asm/hwcap.h | 1 | ||||
| -rw-r--r-- | arch/arm64/kernel/cpufeature.c | 2 | ||||
| -rw-r--r-- | arch/arm64/kernel/cpuinfo.c | 1 |
4 files changed, 5 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index ec144f480b39..ab637886a6f9 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -419,6 +419,7 @@ #define SCTLR_EL1_CP15BEN (1 << 5) /* id_aa64isar0 */ +#define ID_AA64ISAR0_FHM_SHIFT 48 #define ID_AA64ISAR0_DP_SHIFT 44 #define ID_AA64ISAR0_SM4_SHIFT 40 #define ID_AA64ISAR0_SM3_SHIFT 36 diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index cda76fa8b9b2..f018c3deea3b 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -43,5 +43,6 @@ #define HWCAP_ASIMDDP (1 << 20) #define HWCAP_SHA512 (1 << 21) #define HWCAP_SVE (1 << 22) +#define HWCAP_ASIMDFHM (1 << 23) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 9f0545dfe497..1f024049eb30 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -123,6 +123,7 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0), @@ -1032,6 +1033,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD), diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 1e2554543506..7f94623df8a5 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -76,6 +76,7 @@ static const char *const hwcap_str[] = { "asimddp", "sha512", "sve", + "asimdfhm", NULL }; |