Re: [PATCH][Arm] Enable CLI for Armv8.6-a: armv8.6-a, i8mm and bf16

[Dennis Zhang <Dennis.Zhang@arm.com>]

[-- Attachment #1: Type: text/plain, Size: 1691 bytes --]

Hi all,

On 22/11/2019 14:33, Dennis Zhang wrote:
> Hi all,
> 
> This patch is part of a series adding support for Armv8.6-A features.
> It enables options including -march=armv8.6-a, +i8mm and +bf16.
> The +i8mm and +bf16 features are optional for Armv8.2-a and onward.
> Documents are at https://developer.arm.com/docs/ddi0596/latest
> 
> Regtested for arm-none-linux-gnueabi-armv8-a.
> 

This is an update to rebase the patch to the top.
Some issues are fixed according to the recent CLI patch for AArch64.
ChangeLog is updated as following:

gcc/ChangeLog:

2019-12-12  Dennis Zhang  <dennis.zhang@arm.com>

	* config/arm/arm-c.c (arm_cpu_builtins): Define
	__ARM_FEATURE_MATMUL_INT8, __ARM_FEATURE_BF16_VECTOR_ARITHMETIC,
	__ARM_FEATURE_BF16_SCALAR_ARITHMETIC, and
	__ARM_BF16_FORMAT_ALTERNATIVE when enabled.
	* config/arm/arm-cpus.in (armv8_6, i8mm, bf16): New features.
	* config/arm/arm-tables.opt: Regenerated.
	* config/arm/arm.c (arm_option_reconfigure_globals): Initialize
	arm_arch_i8mm and arm_arch_bf16 when enabled.
	* config/arm/arm.h (TARGET_I8MM): New macro.
	(TARGET_BF16_FP, TARGET_BF16_SIMD): Likewise.
	* config/arm/t-aprofile: Add matching rules for -march=armv8.6-a.
	* config/arm/t-arm-elf (all_v8_archs): Add armv8.6-a.
	* config/arm/t-multilib: Add matching rules for -march=armv8.6-a.
	(v8_6_a_simd_variants): New.
	(v8_*_a_simd_variants): Add i8mm and bf16.
	* doc/invoke.texi (armv8.6-a, i8mm, bf16): Document new options.

gcc/testsuite/ChangeLog:

2019-12-12  Dennis Zhang  <dennis.zhang@arm.com>

	* gcc.target/arm/multilib.exp: Add combination tests for armv8.6-a.

Is it OK for trunk?

Many thanks!
Dennis

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: cli-arm-armv8.6-a+i8mm+bf16-20191211.patch --]
[-- Type: text/x-patch; name="cli-arm-armv8.6-a+i8mm+bf16-20191211.patch", Size: 14841 bytes --]

diff --git a/gcc/config/arm/arm-c.c b/gcc/config/arm/arm-c.c
index 546b35a5cbd..9cd1c5bdcba 100644
--- a/gcc/config/arm/arm-c.c
+++ b/gcc/config/arm/arm-c.c
@@ -226,6 +226,14 @@ arm_cpu_builtins (struct cpp_reader* pfile)
 
       builtin_define_with_int_value ("__ARM_FEATURE_COPROC", coproc_level);
     }
+
+  def_or_undef_macro (pfile, "__ARM_FEATURE_MATMUL_INT8", TARGET_I8MM);
+  def_or_undef_macro (pfile, "__ARM_FEATURE_BF16_SCALAR_ARITHMETIC",
+		      TARGET_BF16_FP);
+  def_or_undef_macro (pfile, "__ARM_FEATURE_BF16_VECTOR_ARITHMETIC",
+		      TARGET_BF16_SIMD);
+  def_or_undef_macro (pfile, "__ARM_BF16_FORMAT_ALTERNATIVE",
+		      TARGET_BF16_FP || TARGET_BF16_SIMD);
 }
 
 void
diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
index 7090775aa7e..a2f6ce00af4 100644
--- a/gcc/config/arm/arm-cpus.in
+++ b/gcc/config/arm/arm-cpus.in
@@ -123,6 +123,9 @@ define feature armv8_4
 # Architecture rel 8.5.
 define feature armv8_5
 
+# Architecture rel 8.6.
+define feature armv8_6
+
 # M-Profile security extensions.
 define feature cmse
 
@@ -191,6 +194,12 @@ define feature sb
 # v8-A architectures, added by default from v8.5-A
 define feature predres
 
+# 8-bit Integer Matrix Multiply extension. Optional from v8.2-A.
+define feature i8mm
+
+# Brain half-precision floating-point extension. Optional from v8.2-A.
+define feature bf16
+
 # Feature groups.  Conventionally all (or mostly) upper case.
 # ALL_FPU lists all the feature bits associated with the floating-point
 # unit; these will all be removed if the floating-point unit is disabled
@@ -213,7 +222,7 @@ define fgroup ALL_CRYPTO	crypto
 # strip off 32 D-registers, but does not remove support for
 # double-precision FP.
 define fgroup ALL_SIMD_INTERNAL	fp_d32 neon ALL_CRYPTO
-define fgroup ALL_SIMD_EXTERNAL dotprod fp16fml
+define fgroup ALL_SIMD_EXTERNAL dotprod fp16fml i8mm
 define fgroup ALL_SIMD	ALL_SIMD_INTERNAL ALL_SIMD_EXTERNAL
 
 # List of all FPU bits to strip out if -mfpu is used to override the
@@ -221,7 +230,7 @@ define fgroup ALL_SIMD	ALL_SIMD_INTERNAL ALL_SIMD_EXTERNAL
 define fgroup ALL_FPU_INTERNAL	vfpv2 vfpv3 vfpv4 fpv5 fp16conv fp_dbl ALL_SIMD_INTERNAL
 # Similarly, but including fp16 and other extensions that aren't part of
 # -mfpu support.
-define fgroup ALL_FPU_EXTERNAL fp16
+define fgroup ALL_FPU_EXTERNAL fp16 bf16
 
 # Everything related to the FPU extensions (FP or SIMD).
 define fgroup ALL_FP	ALL_FPU_EXTERNAL ALL_FPU_INTERNAL ALL_SIMD
@@ -256,6 +265,7 @@ define fgroup ARMv8_2a    ARMv8_1a armv8_2
 define fgroup ARMv8_3a    ARMv8_2a armv8_3
 define fgroup ARMv8_4a    ARMv8_3a armv8_4
 define fgroup ARMv8_5a    ARMv8_4a armv8_5 sb predres
+define fgroup ARMv8_6a    ARMv8_5a armv8_6
 define fgroup ARMv8m_base ARMv6m armv8 cmse tdiv
 define fgroup ARMv8m_main ARMv7m armv8 cmse
 define fgroup ARMv8r      ARMv8a
@@ -563,6 +573,8 @@ begin arch armv8.2-a
  option dotprod add FP_ARMv8 DOTPROD
  option sb add sb
  option predres add predres
+ option i8mm add i8mm FP_ARMv8 NEON
+ option bf16 add bf16 FP_ARMv8 NEON
 end arch armv8.2-a
 
 begin arch armv8.3-a
@@ -580,6 +592,8 @@ begin arch armv8.3-a
  option dotprod add FP_ARMv8 DOTPROD
  option sb add sb
  option predres add predres
+ option i8mm add i8mm FP_ARMv8 NEON
+ option bf16 add bf16 FP_ARMv8 NEON
 end arch armv8.3-a
 
 begin arch armv8.4-a
@@ -595,6 +609,8 @@ begin arch armv8.4-a
  option nofp remove ALL_FP
  option sb add sb
  option predres add predres
+ option i8mm add i8mm FP_ARMv8 DOTPROD
+ option bf16 add bf16 FP_ARMv8 DOTPROD
 end arch armv8.4-a
 
 begin arch armv8.5-a
@@ -608,8 +624,25 @@ begin arch armv8.5-a
  option crypto add FP_ARMv8 CRYPTO DOTPROD
  option nocrypto remove ALL_CRYPTO
  option nofp remove ALL_FP
+ option i8mm add i8mm FP_ARMv8 DOTPROD
+ option bf16 add bf16 FP_ARMv8 DOTPROD
 end arch armv8.5-a
 
+begin arch armv8.6-a
+ tune for cortex-a53
+ tune flags CO_PROC
+ base 8A
+ profile A
+ isa ARMv8_6a
+ option simd add FP_ARMv8 DOTPROD
+ option fp16 add fp16 fp16fml FP_ARMv8 DOTPROD
+ option crypto add FP_ARMv8 CRYPTO DOTPROD
+ option nocrypto remove ALL_CRYPTO
+ option nofp remove ALL_FP
+ option i8mm add i8mm FP_ARMv8 DOTPROD
+ option bf16 add bf16 FP_ARMv8 DOTPROD
+end arch armv8.6-a
+
 begin arch armv8-m.base
  tune for cortex-m23
  base 8M_BASE
diff --git a/gcc/config/arm/arm-tables.opt b/gcc/config/arm/arm-tables.opt
index aeb5b3fbf62..e509081678e 100644
--- a/gcc/config/arm/arm-tables.opt
+++ b/gcc/config/arm/arm-tables.opt
@@ -344,19 +344,22 @@ EnumValue
 Enum(arm_arch) String(armv8.5-a) Value(25)
 
 EnumValue
-Enum(arm_arch) String(armv8-m.base) Value(26)
+Enum(arm_arch) String(armv8.6-a) Value(26)
 
 EnumValue
-Enum(arm_arch) String(armv8-m.main) Value(27)
+Enum(arm_arch) String(armv8-m.base) Value(27)
 
 EnumValue
-Enum(arm_arch) String(armv8-r) Value(28)
+Enum(arm_arch) String(armv8-m.main) Value(28)
 
 EnumValue
-Enum(arm_arch) String(iwmmxt) Value(29)
+Enum(arm_arch) String(armv8-r) Value(29)
 
 EnumValue
-Enum(arm_arch) String(iwmmxt2) Value(30)
+Enum(arm_arch) String(iwmmxt) Value(30)
+
+EnumValue
+Enum(arm_arch) String(iwmmxt2) Value(31)
 
 Enum
 Name(arm_fpu) Type(enum fpu_type)
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 983852cc4e3..fc4ba2b1d1b 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -999,6 +999,12 @@ int arm_arch_cmse = 0;
 /* Nonzero if the core has a very small, high-latency, multiply unit.  */
 int arm_m_profile_small_mul = 0;
 
+/* Nonzero if chip supports the AdvSIMD I8MM instructions.  */
+int arm_arch_i8mm = 0;
+
+/* Nonzero if chip supports the BFloat16 instructions.  */
+int arm_arch_bf16 = 0;
+
 /* The condition codes of the ARM, and the inverse function.  */
 static const char * const arm_condition_codes[] =
 {
@@ -3672,8 +3678,11 @@ arm_option_reconfigure_globals (void)
   arm_arch_arm_hwdiv = bitmap_bit_p (arm_active_target.isa, isa_bit_adiv);
   arm_arch_crc = bitmap_bit_p (arm_active_target.isa, isa_bit_crc32);
   arm_arch_cmse = bitmap_bit_p (arm_active_target.isa, isa_bit_cmse);
-  arm_fp16_inst = bitmap_bit_p (arm_active_target.isa, isa_bit_fp16);
   arm_arch_lpae = bitmap_bit_p (arm_active_target.isa, isa_bit_lpae);
+  arm_arch_i8mm = bitmap_bit_p (arm_active_target.isa, isa_bit_i8mm);
+  arm_arch_bf16 = bitmap_bit_p (arm_active_target.isa, isa_bit_bf16);
+
+  arm_fp16_inst = bitmap_bit_p (arm_active_target.isa, isa_bit_fp16);
   if (arm_fp16_inst)
     {
       if (arm_fp16_format == ARM_FP16_FORMAT_ALTERNATIVE)
diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index 3a1ba8b9a57..23af941a4f6 100644
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -246,6 +246,15 @@ emission of floating point pcs attributes.  */
 /* FPU supports the AdvSIMD FP16 instructions for ARMv8.2 and later.  */
 #define TARGET_NEON_FP16INST (TARGET_VFP_FP16INST && TARGET_NEON_RDMA)
 
+/* FPU supports 8-bit Integer Matrix Multiply (I8MM) AdvSIMD extensions.  */
+#define TARGET_I8MM (TARGET_NEON && arm_arch8_2 && arm_arch_i8mm)
+
+/* FPU supports Brain half-precision floating-point (BFloat16) extension.  */
+#define TARGET_BF16_FP (TARGET_32BIT && TARGET_HARD_FLOAT && TARGET_VFP5 \
+			&& arm_arch8_2 && arm_arch_bf16)
+#define TARGET_BF16_SIMD (TARGET_NEON && TARGET_VFP5 \
+			  && arm_arch8_2 && arm_arch_bf16)
+
 /* Q-bit is present.  */
 #define TARGET_ARM_QBIT \
   (TARGET_32BIT && arm_arch5te && (arm_arch_notm || arm_arch7))
@@ -517,6 +526,12 @@ extern int arm_arch_crc;
 /* Nonzero if chip supports the ARMv8-M Security Extensions.  */
 extern int arm_arch_cmse;
 
+/* Nonzero if chip supports the I8MM instructions.  */
+extern int arm_arch_i8mm;
+
+/* Nonzero if chip supports the BFloat16 instructions.  */
+extern int arm_arch_bf16;
+
 #ifndef TARGET_DEFAULT
 #define TARGET_DEFAULT  (MASK_APCS_FRAME)
 #endif
diff --git a/gcc/config/arm/t-aprofile b/gcc/config/arm/t-aprofile
index 1556f1b23e3..e5f3c3b42d6 100644
--- a/gcc/config/arm/t-aprofile
+++ b/gcc/config/arm/t-aprofile
@@ -122,6 +122,13 @@ MULTILIB_MATCHES	+= march?armv8-a=march?armv8.5-a
 MULTILIB_MATCHES	+= $(foreach ARCH, $(v8_5_a_simd_variants), \
 			     march?armv8-a+simd=march?armv8.5-a$(ARCH))
 
+# Baseline v8.6-a: map down to baseline v8-a
+MULTILIB_MATCHES	+= march?armv8-a=march?armv8.6-a
+
+# Map all v8.6-a SIMD variants to v8-a+simd
+MULTILIB_MATCHES	+= $(foreach ARCH, $(v8_6_a_simd_variants), \
+			     march?armv8-a+simd=march?armv8.6-a$(ARCH))
+
 # Use Thumb libraries for everything.
 
 MULTILIB_REUSE		+= mthumb/march.armv7-a/mfloat-abi.soft=marm/march.armv7-a/mfloat-abi.soft
diff --git a/gcc/config/arm/t-arm-elf b/gcc/config/arm/t-arm-elf
index 8911d489f14..970cc43a9e4 100644
--- a/gcc/config/arm/t-arm-elf
+++ b/gcc/config/arm/t-arm-elf
@@ -47,7 +47,7 @@ all_early_arch	:= armv5tej armv6 armv6j armv6k armv6z armv6kz \
 all_v7_a_r	:= armv7-a armv7ve armv7-r
 
 all_v8_archs	:= armv8-a armv8-a+crc armv8.1-a armv8.2-a armv8.3-a armv8.4-a \
-		   armv8.5-a
+		   armv8.5-a armv8.6-a
 
 # No floating point variants, require thumb1 softfp
 all_nofp_t	:= armv6-m armv6s-m armv8-m.base
diff --git a/gcc/config/arm/t-multilib b/gcc/config/arm/t-multilib
index d5ee537193f..afe2e872d7d 100644
--- a/gcc/config/arm/t-multilib
+++ b/gcc/config/arm/t-multilib
@@ -73,9 +73,10 @@ v7ve_vfpv4_simd_variants := +simd
 v8_a_nosimd_variants	:= +crc
 v8_a_simd_variants	:= $(call all_feat_combs, simd crypto)
 v8_1_a_simd_variants	:= $(call all_feat_combs, simd crypto)
-v8_2_a_simd_variants	:= $(call all_feat_combs, simd fp16 fp16fml crypto dotprod)
-v8_4_a_simd_variants	:= $(call all_feat_combs, simd fp16 crypto)
-v8_5_a_simd_variants	:= $(call all_feat_combs, simd fp16 crypto)
+v8_2_a_simd_variants	:= $(call all_feat_combs, simd fp16 fp16fml crypto dotprod i8mm bf16)
+v8_4_a_simd_variants	:= $(call all_feat_combs, simd fp16 crypto i8mm bf16)
+v8_5_a_simd_variants	:= $(call all_feat_combs, simd fp16 crypto i8mm bf16)
+v8_6_a_simd_variants	:= $(call all_feat_combs, simd fp16 crypto i8mm bf16)
 v8_r_nosimd_variants	:= +crc
 
 ifneq (,$(HAS_APROFILE))
@@ -185,6 +186,13 @@ MULTILIB_MATCHES	+= march?armv7=march?armv8.5-a
 MULTILIB_MATCHES	+= $(foreach ARCH, $(v8_5_a_simd_variants), \
 			     march?armv7+fp=march?armv8.5-a$(ARCH))
 
+# Baseline v8.6-a: map down to baseline v8-a
+MULTILIB_MATCHES	+= march?armv7=march?armv8.6-a
+
+# Map all v8.6-a SIMD variants
+MULTILIB_MATCHES	+= $(foreach ARCH, $(v8_6_a_simd_variants), \
+			     march?armv7+fp=march?armv8.6-a$(ARCH))
+
 endif		# Not APROFILE.
 
 # Use Thumb libraries for everything.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 236bed92724..eb49f418741 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -17429,6 +17429,7 @@ Permissible names are:
 @samp{armv8-a}, @samp{armv8.1-a}, @samp{armv8.2-a}, @samp{armv8.3-a},
 @samp{armv8.4-a},
 @samp{armv8.5-a},
+@samp{armv8.6-a},
 @samp{armv7-r},
 @samp{armv8-r},
 @samp{armv6-m}, @samp{armv6s-m},
@@ -17672,6 +17673,14 @@ Speculation Barrier Instruction.
 
 @item +predres
 Execution and Data Prediction Restriction Instructions.
+
+@item +i8mm
+8-bit Integer Matrix Multiply instructions.
+This also enables Advanced SIMD and floating-point instructions.
+
+@item +bf16
+Brain half-precision floating-point instructions.
+This also enables Advanced SIMD and floating-point instructions.
 @end table
 
 @item armv8.4-a
@@ -17701,6 +17710,14 @@ Speculation Barrier Instruction.
 
 @item +predres
 Execution and Data Prediction Restriction Instructions.
+
+@item +i8mm
+8-bit Integer Matrix Multiply instructions.
+This also enables Advanced SIMD and floating-point instructions.
+
+@item +bf16
+Brain half-precision floating-point instructions.
+This also enables Advanced SIMD and floating-point instructions.
 @end table
 
 @item armv8.5-a
@@ -17724,6 +17741,45 @@ Disable the cryptographic extension.
 
 @item +nofp
 Disable the floating-point, Advanced SIMD and cryptographic instructions.
+
+@item +i8mm
+8-bit Integer Matrix Multiply instructions.
+This also enables Advanced SIMD and floating-point instructions.
+
+@item +bf16
+Brain half-precision floating-point instructions.
+This also enables Advanced SIMD and floating-point instructions.
+@end table
+
+@item armv8.6-a
+@table @samp
+@item +fp16
+The half-precision floating-point data processing instructions.
+This also enables the Advanced SIMD and floating-point instructions as well
+as the Dot Product extension and the half-precision floating-point fmla
+extension.
+
+@item +simd
+The ARMv8.3-A Advanced SIMD and floating-point instructions as well as the
+Dot Product extension.
+
+@item +crypto
+The cryptographic instructions.  This also enables the Advanced SIMD and
+floating-point instructions as well as the Dot Product extension.
+
+@item +nocrypto
+Disable the cryptographic extension.
+
+@item +nofp
+Disable the floating-point, Advanced SIMD and cryptographic instructions.
+
+@item +i8mm
+8-bit Integer Matrix Multiply instructions.
+This also enables Advanced SIMD and floating-point instructions.
+
+@item +bf16
+Brain half-precision floating-point instructions.
+This also enables Advanced SIMD and floating-point instructions.
 @end table
 
 @item armv7-r
diff --git a/gcc/testsuite/gcc.target/arm/multilib.exp b/gcc/testsuite/gcc.target/arm/multilib.exp
index dcea829965e..7807485352f 100644
--- a/gcc/testsuite/gcc.target/arm/multilib.exp
+++ b/gcc/testsuite/gcc.target/arm/multilib.exp
@@ -126,6 +126,14 @@ if {[multilib_config "aprofile"] } {
 	{-march=armv8.5-a+simd+fp16 -mfloat-abi=softfp} "thumb/v8-a+simd/softfp"
 	{-march=armv8.5-a+simd+fp16+nofp -mfloat-abi=softfp} "thumb/v8-a/nofp"
 	{-march=armv8.5-a+simd+nofp+fp16 -mfloat-abi=softfp} "thumb/v8-a+simd/softfp"
+	{-march=armv8.6-a+crypto -mfloat-abi=soft} "thumb/v8-a/nofp"
+	{-march=armv8.6-a+simd+crypto -mfloat-abi=softfp} "thumb/v8-a+simd/softfp"
+	{-march=armv8.6-a+simd+crypto+nofp -mfloat-abi=softfp} "thumb/v8-a/nofp"
+	{-march=armv8.6-a+simd+nofp+crypto -mfloat-abi=softfp} "thumb/v8-a+simd/softfp"
+	{-march=armv8.6-a+fp16 -mfloat-abi=soft} "thumb/v8-a/nofp"
+	{-march=armv8.6-a+simd+fp16 -mfloat-abi=softfp} "thumb/v8-a+simd/softfp"
+	{-march=armv8.6-a+simd+fp16+nofp -mfloat-abi=softfp} "thumb/v8-a/nofp"
+	{-march=armv8.6-a+simd+nofp+fp16 -mfloat-abi=softfp} "thumb/v8-a+simd/softfp"
 	{-mcpu=cortex-a53+crypto -mfloat-abi=hard} "thumb/v8-a+simd/hard"
 	{-mcpu=cortex-a53+nofp -mfloat-abi=softfp} "thumb/v8-a/nofp"
 	{-march=armv8-a+crc -mfloat-abi=hard -mfpu=vfp} "thumb/v8-a+simd/hard"