[RFC PATCH] x86/cpufeatures: Enumerate new AVX512 bfloat16 instructions
From: Fenghua Yu
Date: Mon Jun 10 2019 - 13:16:45 EST
AVX512 Vector Neural Network Instructions (VNNI) in Intel Deep Learning
Boost support bfloat16 format (BF16). BF16 is a short version of FP32 and
has several advantages over FP16. BF16 offers more than enough range for
deep learning training tasks and doesn't need to handle hardware exception
as this is a performance optimization. FP32 accumulation after the
multiply is essential to achieve sufficient numerical behavior on an
application level.
AVX512 bfloat16 instructions can be enumerated by:
CPUID.(EAX=7,ECX=1):EAX[bit 5] AVX512_BF16
Detailed information of the CPUID bit and AVX512 bfloat16 instructions
can be found in the latest Intel Architecture Instruction Set Extensions
and Future Features Programming Reference.
Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
---
Since split lock feature (to-be-upstreamed) occupies the last bit
of word 7, need to create a new word 19 to host AVX512_BF16 and other
future features.
arch/x86/include/asm/cpufeature.h | 7 +++++--
arch/x86/include/asm/cpufeatures.h | 8 +++++++-
arch/x86/include/asm/disabled-features.h | 3 ++-
arch/x86/include/asm/required-features.h | 3 ++-
arch/x86/kernel/cpu/cpuid-deps.c | 1 +
arch/x86/kernel/cpu/scattered.c | 1 +
6 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0e56ff7e4848..cfb7d765ed86 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -30,6 +30,7 @@ enum cpuid_leafs
CPUID_7_ECX,
CPUID_8000_0007_EBX,
CPUID_7_EDX,
+ CPUID_LNX_4,
};
#ifdef CONFIG_X86_FEATURE_NAMES
@@ -81,8 +82,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 19))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 20))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -104,8 +106,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 19))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 20))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 981ff9479648..7d76393ce916 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 19 /* N 32-bit words worth of info */
+#define NCAPINTS 20 /* N 32-bit words worth of info */
#define NBUGINTS 1 /* N 32-bit bug flags */
/*
@@ -352,6 +352,12 @@
#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
+/*
+ * Extended auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels and sub-leaves like CPUID level 7 and sub-leaf 1, etc, word 19.
+ */
+#define X86_FEATURE_AVX512_BF16 (19*32+ 0) /* BFLOAT16 instructions */
+
/*
* BUG word(s)
*/
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index a5ea841cc6d2..f0f935f8d917 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -84,6 +84,7 @@
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
+#define DISABLED_MASK19 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 6847d85400a8..fa5700097f64 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -101,6 +101,7 @@
#define REQUIRED_MASK16 0
#define REQUIRED_MASK17 0
#define REQUIRED_MASK18 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
+#define REQUIRED_MASK19 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 2c0bd38a44ab..65d3e0c47a25 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -59,6 +59,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
{}
};
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..59d7a85db621 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,7 @@ struct cpuid_bit {
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_AVX512_BF16, CPUID_EAX, 5, 0x00000007, 1 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
--
2.19.1