Enable Intel GFNI instructions.

Intel has disclosed a set of new instructions. The spec is
https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf

gas/

	* config/tc-i386.c (cpu_arch): Add .gfni.
	* doc/c-i386.texi: Document .gfni.
	* testsuite/gas/i386/i386.exp: Add GFNI tests.
	* testsuite/gas/i386/avx.s: New GFNI test.
	* testsuite/gas/i386/x86-64-avx.s: Likewise.
	* testsuite/gas/i386/avx.d: Adjust.
	* testsuite/gas/i386/avx-intel.d: Likewise
	* testsuite/gas/i386/ilp32/x86-64-avx-intel.d: Likewise.
	* testsuite/gas/i386/ilp32/x86-64-avx.d: Likewise.
	* testsuite/gas/i386/avx512f_gfni-intel.d: New test.
	* testsuite/gas/i386/avx512f_gfni.d: Likewise.
	* testsuite/gas/i386/avx512f_gfni.s: Likewise.
	* testsuite/gas/i386/avx512vl_gfni-intel.d: Likewise.
	* testsuite/gas/i386/avx512vl_gfni.d: Likewise.
	* testsuite/gas/i386/avx512vl_gfni.s: Likewise.
	* testsuite/gas/i386/gfni-intel.d: Likewise.
	* testsuite/gas/i386/gfni.d: Likewise.
	* testsuite/gas/i386/gfni.s: Likewise.
	* testsuite/gas/i386/x86-64-avx512f_gfni-intel.d: Likewise.
	* testsuite/gas/i386/x86-64-avx512f_gfni.d: Likewise.
	* testsuite/gas/i386/x86-64-avx512f_gfni.s: Likewise.
	* testsuite/gas/i386/x86-64-avx512vl_gfni-intel.d: Likewise.
	* testsuite/gas/i386/x86-64-avx512vl_gfni.d: Likewise.
	* testsuite/gas/i386/x86-64-avx512vl_gfni.s: Likewise.
	* testsuite/gas/i386/x86-64-avx_gfni-intel.d: Likewise.
	* testsuite/gas/i386/x86-64-avx_gfni.d: Likewise.
	* testsuite/gas/i386/x86-64-avx_gfni.s: Likewise.
	* testsuite/gas/i386/x86-64-gfni-intel.d: Likewise.
	* testsuite/gas/i386/x86-64-gfni.d: Likewise.
	* testsuite/gas/i386/x86-64-gfni.s: Likewise.

opcodes/

	* i386-dis.c (enum): Add PREFIX_0F38CF, PREFIX_0F3ACE, PREFIX_0F3ACF,
	PREFIX_VEX_0F38CF, PREFIX_VEX_0F3ACE, PREFIX_VEX_0F3ACF,
	PREFIX_EVEX_0F38CF, PREFIX_EVEX_0F3ACE, PREFIX_EVEX_0F3ACF.
	(enum): Add VEX_W_0F38CF_P_2, VEX_W_0F3ACE_P_2, VEX_W_0F3ACF_P_2,
	EVEX_W_0F3ACE_P_2, EVEX_W_0F3ACF_P_2.
	(prefix_table): Updated (see prefixes above).
	(three_byte_table): Likewise.
	(vex_w_table): Likewise.
	* i386-dis-evex.h: Likewise.
	* i386-gen.c (cpu_flag_init): Add CPU_GFNI_FLAGS, CpuGFNI.
	(cpu_flags): Add CpuGFNI.
	* i386-opc.h (enum): Add CpuGFNI.
	(i386_cpu_flags): Add cpugfni.
	* i386-opc.tbl: Add Intel GFNI instructions.
	* i386-init.h: Regenerate.
	* i386-tbl.h: Likewise.

1 files changed, 36 insertions, 0 deletions

diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl
index 2c6a425..a5617e5 100644
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -1806,6 +1806,15 @@ pclmullqhqdq, 2, 0x660f3a44, 0x10, 3, CpuPCLMUL, Modrm|IgnoreSize|No_bSuf|No_wSu
 pclmulhqhqdq, 2, 0x6644, 0x11, 1, CpuAVX|CpuPCLMUL, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt|SSE2AVX, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
 pclmulhqhqdq, 2, 0x660f3a44, 0x11, 3, CpuPCLMUL, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
 
+// GFNI
+
+gf2p8affineqb, 3, 0x66ce, None, 1, CpuAVX|CpuGFNI, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { Imm8, Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
+gf2p8affineqb, 3, 0x660f3ace, None, 3, CpuGFNI, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
+gf2p8affineinvqb, 3, 0x66cf, None, 1, CpuAVX|CpuGFNI, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { Imm8, Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
+gf2p8affineinvqb, 3, 0x660f3acf, None, 3, CpuGFNI, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
+gf2p8mulb, 2, 0x66cf, None, 1, CpuAVX|CpuGFNI, Modrm|Vex|VexOpcode=1|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
+gf2p8mulb, 2, 0x660f38cf, None, 3, CpuGFNI, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM }
+
 // AVX instructions.
 
 vaddpd, 3, 0x6658, None, 1, CpuAVX, Modrm|Vex|VexOpcode=0|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM, RegXMM }
@@ -2591,6 +2600,17 @@ vpclmulhqlqdq, 3, 0x6644, 0x1, 1, CpuAVX|CpuPCLMUL, Modrm|Vex|VexOpcode=2|VexVVV
 vpclmullqhqdq, 3, 0x6644, 0x10, 1, CpuAVX|CpuPCLMUL, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM, RegXMM }
 vpclmulhqhqdq, 3, 0x6644, 0x11, 1, CpuAVX|CpuPCLMUL, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt, { Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM, RegXMM }
 
+// GFNI + AVX
+
+vgf2p8affineinvqb, 4, 0x66cf, None, 1, CpuAVX|CpuGFNI, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM, RegXMM }
+vgf2p8affineinvqb, 4, 0x66cf, None, 1, CpuAVX|CpuGFNI, Modrm|Vex=2|VexOpcode=2|VexVVVV=1|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Ymmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegYMM, RegYMM, RegYMM }
+
+vgf2p8affineqb, 4, 0x66ce, None, 1, CpuAVX|CpuGFNI, Modrm|Vex|VexOpcode=2|VexVVVV=1|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Xmmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegXMM, RegXMM, RegXMM }
+vgf2p8affineqb, 4, 0x66ce, None, 1, CpuAVX|CpuGFNI, Modrm|Vex=2|VexOpcode=2|VexVVVV=1|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Ymmword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|RegYMM, RegYMM, RegYMM }
+
+vgf2p8mulb, 3, 0x66cf, None, 1, CpuAVX|CpuGFNI, Modrm|Vex|VexOpcode=1|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|XMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegXMM, RegXMM }
+vgf2p8mulb, 3, 0x66cf, None, 1, CpuAVX|CpuGFNI, Modrm|Vex=2|VexOpcode=1|VexVVVV=1|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegYMM|YMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegYMM, RegYMM }
+
 // FSGSBASE, RDRND and F16C
 
 rdfsbase, 1, 0xf30fae, 0x0, 2, CpuFSGSBase, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg32|Reg64 }
@@ -6042,6 +6062,22 @@ vpshrdw, 4, 0x6672, None, 1, CpuAVX512_VBMI2|CpuAVX512VL, Modrm|EVex=3|Masking=3
 
 // AVX512_VBMI2 instructions end
 
+// AVX512 + GFNI instructions
+
+vgf2p8affineinvqb, 4, 0x66cf, None, 1, CpuAVX512F|CpuGFNI, Modrm|EVex=1|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|VecESize=1|Broadcast=2|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Qword|ZMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegZMM, RegZMM }
+vgf2p8affineinvqb, 4, 0x66cf, None, 1, CpuGFNI|CpuAVX512VL, Modrm|EVex=2|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|VecESize=1|Broadcast=4|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Qword|XMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegXMM, RegXMM }
+vgf2p8affineinvqb, 4, 0x66cf, None, 1, CpuGFNI|CpuAVX512VL, Modrm|EVex=3|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|VecESize=1|Broadcast=3|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Qword|YMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegYMM, RegYMM }
+
+vgf2p8affineqb, 4, 0x66ce, None, 1, CpuAVX512F|CpuGFNI, Modrm|EVex=1|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|VecESize=1|Broadcast=2|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Qword|ZMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegZMM, RegZMM }
+vgf2p8affineqb, 4, 0x66ce, None, 1, CpuGFNI|CpuAVX512VL, Modrm|EVex=2|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|VecESize=1|Broadcast=4|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Qword|XMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegXMM, RegXMM }
+vgf2p8affineqb, 4, 0x66ce, None, 1, CpuGFNI|CpuAVX512VL, Modrm|EVex=3|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|VecESize=1|Broadcast=3|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Qword|YMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegYMM, RegYMM }
+
+vgf2p8mulb, 3, 0x66cf, None, 1, CpuAVX512F|CpuGFNI, Modrm|EVex=1|Masking=3|VexOpcode=1|VexVVVV=1|VexW=1|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegZMM|ZMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegZMM, RegZMM }
+vgf2p8mulb, 3, 0x66cf, None, 1, CpuGFNI|CpuAVX512VL, Modrm|EVex=2|Masking=3|VexOpcode=1|VexVVVV=1|VexW=1|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|XMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegXMM, RegXMM }
+vgf2p8mulb, 3, 0x66cf, None, 1, CpuGFNI|CpuAVX512VL, Modrm|EVex=3|Masking=3|VexOpcode=1|VexVVVV=1|VexW=1|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegYMM|YMMword|Unspecified|BaseIndex|Disp8|Disp16|Disp32|Disp32S|Vec_Disp8, RegYMM, RegYMM }
+
+// AVX512 + GFNI instructions end
+
 // CLZERO instructions
 
 clzero, 0, 0xf01fc, None, 3, CpuCLZERO, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }