[PATCH 2/6] Support Intel AMX-AVX512

Haochen Jiang haochen.jiang@intel.com
Wed Nov 13 08:44:31 GMT 2024


This patch will support AMX-AVX512. In disassmbler, we need to manually
change the operand3 names to r32 when it is register or it will print
out zmm instead.

gas/ChangeLog:

	* NEWS: Support Intel AMX-AVX512.
	* config/tc-i386.c: Add amx_avx512.
	* doc/c-i386.texi: Document .amx_avx512.
	* testsuite/gas/i386/i386.exp: Run AMX-AVX512 tests.
	* testsuite/gas/i386/x86-64.exp: Ditto.
	* testsuite/gas/i386/amx-avx512-inval.l: New test.
	* testsuite/gas/i386/amx-avx512-inval.s: Ditto.
	* testsuite/gas/i386/x86-64-amx-avx512-intel.d: Ditto.
	* testsuite/gas/i386/x86-64-amx-avx512.d: Ditto.
	* testsuite/gas/i386/x86-64-amx-avx512.s: Ditto.

opcodes/ChangeLog:

	* i386-dis-evex-len.h: Add EVEX_LEN_0F384A_X86_64_W_0,
	EVEX_LEN_0F386D_X86_64_W_0, EVEX_LEN_0F3A07_X86_64_W_0,
	EVEX_LEN_0F3A77_X86_64_W_0.
	* i386-dis-evex-prefix.h: Add PREFIX_EVEX_0F384A_W_0_L_2,
	PREFIX_EVEX_0F386D_W_0_L_2, PREFIX_EVEX_0F3A07_W_0_L_2,
	PREFIX_EVEX_0F3A77_W_0_L_2.
	* i386-dis-evex-w.h: Add EVEX_W_0F384A_X86_64, EVEX_W_0F386D_X86_64,
	EVEX_W_0F3A07_X86_64, EVEX_W_0F3A77_X86_64.
	* i386-dis-evex-x86-64.h: Add X86_64_EVEX_0F384A, X86_64_EVEX_0F386D,
	X86_64_EVEX_0F3A07, X86_64_EVEX_0F3A77.
	* i386-dis-evex.h: Ditto.
	* i386-dis.c (EVEX_LEN_0F384A_X86_64_W_0): New.
	(EVEX_LEN_0F386D_X86_64_W_0): Ditto.
	(EVEX_LEN_0F3A07_X86_64_W_0): Ditto.
	(EVEX_LEN_0F3A77_X86_64_W_0): Ditto.
	(MOD_EVEX_0F384A_X86_64_W_0): Ditto.
	(MOD_EVEX_0F386D_X86_64_W_0): Ditto.
	(MOD_EVEX_0F3A07_X86_64_W_0): Ditto.
	(MOD_EVEX_0F3A77_X86_64_W_0): Ditto.
	(PREFIX_EVEX_0F384A_W_0_L_2): Ditto.
	(PREFIX_EVEX_0F386D_W_0_L_2): Ditto.
	(PREFIX_EVEX_0F3A07_W_0_L_2): Ditto.
	(PREFIX_EVEX_0F3A77_W_0_L_2): Ditto.
	(EVEX_W_0F384A_X86_64): Ditto.
	(EVEX_W_0F386D_X86_64): Ditto.
	(EVEX_W_0F3A07_X86_64): Ditto.
	(EVEX_W_0F3A77_X86_64): Ditto.
	(X86_64_EVEX_0F384A): Ditto.
	(X86_64_EVEX_0F386D): Ditto.
	(X86_64_EVEX_0F3A07): Ditto.
	(X86_64_EVEX_0F3A77): Ditto.
	(OP_VEX): Add handler for dq_mode under EVEX512.
	* i386-gen.c (cpu_flag_init): Add CPU_AMX_AVX512_FLAGS and
	CPU_ANY_AMX_AVX512_FLAGS.
	* i386-init.h: Regenerated.
	* i386-mnem.h: Ditto.
	* i386-opc.h (CpuAMX_AVX512): New.
	(i386_cpu_flags): Add cpuamx_avx512.
	* i386-opc.tbl: Add AMX-AVX512 instructions.
	* i386-tbl.h: Regenerated.
---
 gas/NEWS                                      |    2 +
 gas/config/tc-i386.c                          |    1 +
 gas/doc/c-i386.texi                           |    4 +-
 gas/testsuite/gas/i386/amx-avx512-inval.l     |    7 +
 gas/testsuite/gas/i386/amx-avx512-inval.s     |   11 +
 gas/testsuite/gas/i386/i386.exp               |    1 +
 .../gas/i386/x86-64-amx-avx512-intel.d        |   35 +
 gas/testsuite/gas/i386/x86-64-amx-avx512.d    |   34 +
 gas/testsuite/gas/i386/x86-64-amx-avx512.s    |   55 +
 gas/testsuite/gas/i386/x86-64.exp             |    2 +
 opcodes/i386-dis-evex-len.h                   |   28 +
 opcodes/i386-dis-evex-prefix.h                |   27 +
 opcodes/i386-dis-evex-w.h                     |   16 +
 opcodes/i386-dis-evex-x86-64.h                |   20 +
 opcodes/i386-dis-evex.h                       |    8 +-
 opcodes/i386-dis.c                            |   22 +-
 opcodes/i386-gen.c                            |    3 +
 opcodes/i386-init.h                           |  766 ++---
 opcodes/i386-mnem.h                           | 2554 +++++++++--------
 opcodes/i386-opc.h                            |    3 +
 opcodes/i386-opc.tbl                          |   15 +
 opcodes/i386-tbl.h                            |  416 ++-
 22 files changed, 2244 insertions(+), 1786 deletions(-)
 create mode 100644 gas/testsuite/gas/i386/amx-avx512-inval.l
 create mode 100644 gas/testsuite/gas/i386/amx-avx512-inval.s
 create mode 100644 gas/testsuite/gas/i386/x86-64-amx-avx512-intel.d
 create mode 100644 gas/testsuite/gas/i386/x86-64-amx-avx512.d
 create mode 100644 gas/testsuite/gas/i386/x86-64-amx-avx512.s

diff --git a/gas/NEWS b/gas/NEWS
index 2a8f79b6360..9575dcdaaa1 100644
--- a/gas/NEWS
+++ b/gas/NEWS
@@ -1,5 +1,7 @@
 -*- text -*-
 
+* Add support for Intel AMX-AVX512 instructions.
+
 * Add support for Intel AMX-TRANSPOSE instructions.
 
 * Add support for Intel MSR_IMM instructions.
diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c
index c28d98109d3..9e54aae65fa 100644
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -1183,6 +1183,7 @@ static const arch_entry cpu_arch[] =
   SUBARCH (amx_fp16, AMX_FP16, ANY_AMX_FP16, false),
   SUBARCH (amx_complex, AMX_COMPLEX, ANY_AMX_COMPLEX, false),
   SUBARCH (amx_transpose, AMX_TRANSPOSE, ANY_AMX_TRANSPOSE, false),
+  SUBARCH (amx_avx512, AMX_AVX512, ANY_AMX_AVX512, false),
   SUBARCH (amx_tile, AMX_TILE, ANY_AMX_TILE, false),
   SUBARCH (movdiri, MOVDIRI, MOVDIRI, false),
   SUBARCH (movdir64b, MOVDIR64B, MOVDIR64B, false),
diff --git a/gas/doc/c-i386.texi b/gas/doc/c-i386.texi
index 84bb875791d..dd2e422e323 100644
--- a/gas/doc/c-i386.texi
+++ b/gas/doc/c-i386.texi
@@ -229,6 +229,7 @@ accept various extension mnemonics.  For example,
 @code{amx_fp16},
 @code{amx_complex},
 @code{amx_transpose},
+@code{amx_avx512},
 @code{amx_tile},
 @code{vmx},
 @code{vmfunc},
@@ -1701,7 +1702,8 @@ supported on the CPU specified.  The choices for @var{cpu_type} are:
 @item @samp{.shstk} @tab @samp{.gfni} @tab @samp{.vaes} @tab @samp{.vpclmulqdq}
 @item @samp{.movdiri} @tab @samp{.movdir64b} @tab @samp{.enqcmd} @tab @samp{.tsxldtrk}
 @item @samp{.amx_int8} @tab @samp{.amx_bf16} @tab @samp{.amx_fp16}
-@item @samp{.amx_complex} @tab @samp{.amx_transpose} @tab @samp{.amx_tile}
+@item @samp{.amx_complex} @tab @samp{.amx_transpose} @tab @samp{.amx_avx512}
+@item @samp{.amx_tile}
 @item @samp{.kl} @tab @samp{.widekl} @tab @samp{.uintr} @tab @samp{.hreset}
 @item @samp{.3dnow} @tab @samp{.3dnowa} @tab @samp{.sse4a} @tab @samp{.sse5}
 @item @samp{.syscall} @tab @samp{.rdtscp} @tab @samp{.svme}
diff --git a/gas/testsuite/gas/i386/amx-avx512-inval.l b/gas/testsuite/gas/i386/amx-avx512-inval.l
new file mode 100644
index 00000000000..0cfe3a7bf2f
--- /dev/null
+++ b/gas/testsuite/gas/i386/amx-avx512-inval.l
@@ -0,0 +1,7 @@
+.* Assembler messages:
+.*:6: Error: `tcvtrowd2ps' is only supported in 64-bit mode
+.*:7: Error: `tcvtrowps2pbf16h' is only supported in 64-bit mode
+.*:8: Error: `tcvtrowps2pbf16l' is only supported in 64-bit mode
+.*:9: Error: `tcvtrowps2phh' is only supported in 64-bit mode
+.*:10: Error: `tcvtrowps2phl' is only supported in 64-bit mode
+.*:11: Error: `tilemovrow' is only supported in 64-bit mode
diff --git a/gas/testsuite/gas/i386/amx-avx512-inval.s b/gas/testsuite/gas/i386/amx-avx512-inval.s
new file mode 100644
index 00000000000..2e7a6af2e60
--- /dev/null
+++ b/gas/testsuite/gas/i386/amx-avx512-inval.s
@@ -0,0 +1,11 @@
+# Check	Illegal AMX-AVX512 instructions
+
+	.allow_index_reg
+	.text
+_start:
+	tcvtrowd2ps	%edx, %tmm5, %zmm30
+	tcvtrowps2pbf16h	%edx, %tmm5, %zmm30
+	tcvtrowps2pbf16l	%edx, %tmm5, %zmm30
+	tcvtrowps2phh	%edx, %tmm5, %zmm30
+	tcvtrowps2phl	%edx, %tmm5, %zmm30
+	tilemovrow	%edx, %tmm5, %zmm30
diff --git a/gas/testsuite/gas/i386/i386.exp b/gas/testsuite/gas/i386/i386.exp
index 71abb0fc66c..acc1e2b9a63 100644
--- a/gas/testsuite/gas/i386/i386.exp
+++ b/gas/testsuite/gas/i386/i386.exp
@@ -547,6 +547,7 @@ if [gas_32_check] then {
     run_dump_test "avx10_2-256-miscs-intel"
     run_list_test "msr_imm-inval"
     run_list_test "amx-transpose-inval"
+    run_list_test "amx-avx512-inval"
     run_list_test "sg"
     run_dump_test "clzero"
     run_dump_test "invlpgb"
diff --git a/gas/testsuite/gas/i386/x86-64-amx-avx512-intel.d b/gas/testsuite/gas/i386/x86-64-amx-avx512-intel.d
new file mode 100644
index 00000000000..06ef2293bb9
--- /dev/null
+++ b/gas/testsuite/gas/i386/x86-64-amx-avx512-intel.d
@@ -0,0 +1,35 @@
+#objdump: -dw -Mintel
+#name: x86_64 AMX-AVX512 insns (Intel disassembly)
+#source: x86-64-amx-avx512.s
+
+.*: +file format .*
+
+Disassembly of section \.text:
+
+#...
+[a-f0-9]+ <_intel>:
+\s*[a-f0-9]+:\s*62 62 6e 48 4a f5\s+tcvtrowd2ps zmm30,tmm5,edx
+\s*[a-f0-9]+:\s*62 62 6e 48 4a f2\s+tcvtrowd2ps zmm30,tmm2,edx
+\s*[a-f0-9]+:\s*62 63 7e 48 07 f5 7b\s+tcvtrowd2ps zmm30,tmm5,0x7b
+\s*[a-f0-9]+:\s*62 63 7e 48 07 f2 7b\s+tcvtrowd2ps zmm30,tmm2,0x7b
+\s*[a-f0-9]+:\s*62 62 6f 48 6d f5\s+tcvtrowps2pbf16h zmm30,tmm5,edx
+\s*[a-f0-9]+:\s*62 62 6f 48 6d f2\s+tcvtrowps2pbf16h zmm30,tmm2,edx
+\s*[a-f0-9]+:\s*62 63 7f 48 07 f5 7b\s+tcvtrowps2pbf16h zmm30,tmm5,0x7b
+\s*[a-f0-9]+:\s*62 63 7f 48 07 f2 7b\s+tcvtrowps2pbf16h zmm30,tmm2,0x7b
+\s*[a-f0-9]+:\s*62 62 6e 48 6d f5\s+tcvtrowps2pbf16l zmm30,tmm5,edx
+\s*[a-f0-9]+:\s*62 62 6e 48 6d f2\s+tcvtrowps2pbf16l zmm30,tmm2,edx
+\s*[a-f0-9]+:\s*62 63 7e 48 77 f5 7b\s+tcvtrowps2pbf16l zmm30,tmm5,0x7b
+\s*[a-f0-9]+:\s*62 63 7e 48 77 f2 7b\s+tcvtrowps2pbf16l zmm30,tmm2,0x7b
+\s*[a-f0-9]+:\s*62 62 6c 48 6d f5\s+tcvtrowps2phh zmm30,tmm5,edx
+\s*[a-f0-9]+:\s*62 62 6c 48 6d f2\s+tcvtrowps2phh zmm30,tmm2,edx
+\s*[a-f0-9]+:\s*62 63 7c 48 07 f5 7b\s+tcvtrowps2phh zmm30,tmm5,0x7b
+\s*[a-f0-9]+:\s*62 63 7c 48 07 f2 7b\s+tcvtrowps2phh zmm30,tmm2,0x7b
+\s*[a-f0-9]+:\s*62 62 6d 48 6d f5\s+tcvtrowps2phl zmm30,tmm5,edx
+\s*[a-f0-9]+:\s*62 62 6d 48 6d f2\s+tcvtrowps2phl zmm30,tmm2,edx
+\s*[a-f0-9]+:\s*62 63 7f 48 77 f5 7b\s+tcvtrowps2phl zmm30,tmm5,0x7b
+\s*[a-f0-9]+:\s*62 63 7f 48 77 f2 7b\s+tcvtrowps2phl zmm30,tmm2,0x7b
+\s*[a-f0-9]+:\s*62 62 6d 48 4a f5\s+tilemovrow zmm30,tmm5,edx
+\s*[a-f0-9]+:\s*62 62 6d 48 4a f2\s+tilemovrow zmm30,tmm2,edx
+\s*[a-f0-9]+:\s*62 63 7d 48 07 f5 7b\s+tilemovrow zmm30,tmm5,0x7b
+\s*[a-f0-9]+:\s*62 63 7d 48 07 f2 7b\s+tilemovrow zmm30,tmm2,0x7b
+#pass
diff --git a/gas/testsuite/gas/i386/x86-64-amx-avx512.d b/gas/testsuite/gas/i386/x86-64-amx-avx512.d
new file mode 100644
index 00000000000..410588d494e
--- /dev/null
+++ b/gas/testsuite/gas/i386/x86-64-amx-avx512.d
@@ -0,0 +1,34 @@
+#objdump: -dw
+#name: x86_64 AMX-AVX512 insns
+#source: x86-64-amx-avx512.s
+
+.*: +file format .*
+
+Disassembly of section \.text:
+
+0+ <_start>:
+\s*[a-f0-9]+:\s*62 62 6e 48 4a f5\s+tcvtrowd2ps %edx,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 62 6e 48 4a f2\s+tcvtrowd2ps %edx,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 63 7e 48 07 f5 7b\s+tcvtrowd2ps \$0x7b,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 63 7e 48 07 f2 7b\s+tcvtrowd2ps \$0x7b,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 62 6f 48 6d f5\s+tcvtrowps2pbf16h %edx,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 62 6f 48 6d f2\s+tcvtrowps2pbf16h %edx,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 63 7f 48 07 f5 7b\s+tcvtrowps2pbf16h \$0x7b,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 63 7f 48 07 f2 7b\s+tcvtrowps2pbf16h \$0x7b,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 62 6e 48 6d f5\s+tcvtrowps2pbf16l %edx,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 62 6e 48 6d f2\s+tcvtrowps2pbf16l %edx,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 63 7e 48 77 f5 7b\s+tcvtrowps2pbf16l \$0x7b,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 63 7e 48 77 f2 7b\s+tcvtrowps2pbf16l \$0x7b,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 62 6c 48 6d f5\s+tcvtrowps2phh %edx,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 62 6c 48 6d f2\s+tcvtrowps2phh %edx,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 63 7c 48 07 f5 7b\s+tcvtrowps2phh \$0x7b,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 63 7c 48 07 f2 7b\s+tcvtrowps2phh \$0x7b,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 62 6d 48 6d f5\s+tcvtrowps2phl %edx,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 62 6d 48 6d f2\s+tcvtrowps2phl %edx,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 63 7f 48 77 f5 7b\s+tcvtrowps2phl \$0x7b,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 63 7f 48 77 f2 7b\s+tcvtrowps2phl \$0x7b,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 62 6d 48 4a f5\s+tilemovrow %edx,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 62 6d 48 4a f2\s+tilemovrow %edx,%tmm2,%zmm30
+\s*[a-f0-9]+:\s*62 63 7d 48 07 f5 7b\s+tilemovrow \$0x7b,%tmm5,%zmm30
+\s*[a-f0-9]+:\s*62 63 7d 48 07 f2 7b\s+tilemovrow \$0x7b,%tmm2,%zmm30
+#pass
diff --git a/gas/testsuite/gas/i386/x86-64-amx-avx512.s b/gas/testsuite/gas/i386/x86-64-amx-avx512.s
new file mode 100644
index 00000000000..0faecfde820
--- /dev/null
+++ b/gas/testsuite/gas/i386/x86-64-amx-avx512.s
@@ -0,0 +1,55 @@
+# Check 64bit AMX-AVX512 instructions
+
+	.text
+_start:
+	tcvtrowd2ps	%edx, %tmm5, %zmm30
+	tcvtrowd2ps	%edx, %tmm2, %zmm30
+	tcvtrowd2ps	$123, %tmm5, %zmm30
+	tcvtrowd2ps	$123, %tmm2, %zmm30
+	tcvtrowps2pbf16h	%edx, %tmm5, %zmm30
+	tcvtrowps2pbf16h	%edx, %tmm2, %zmm30
+	tcvtrowps2pbf16h	$123, %tmm5, %zmm30
+	tcvtrowps2pbf16h	$123, %tmm2, %zmm30
+	tcvtrowps2pbf16l	%edx, %tmm5, %zmm30
+	tcvtrowps2pbf16l	%edx, %tmm2, %zmm30
+	tcvtrowps2pbf16l	$123, %tmm5, %zmm30
+	tcvtrowps2pbf16l	$123, %tmm2, %zmm30
+	tcvtrowps2phh	%edx, %tmm5, %zmm30
+	tcvtrowps2phh	%edx, %tmm2, %zmm30
+	tcvtrowps2phh	$123, %tmm5, %zmm30
+	tcvtrowps2phh	$123, %tmm2, %zmm30
+	tcvtrowps2phl	%edx, %tmm5, %zmm30
+	tcvtrowps2phl	%edx, %tmm2, %zmm30
+	tcvtrowps2phl	$123, %tmm5, %zmm30
+	tcvtrowps2phl	$123, %tmm2, %zmm30
+	tilemovrow	%edx, %tmm5, %zmm30
+	tilemovrow	%edx, %tmm2, %zmm30
+	tilemovrow	$123, %tmm5, %zmm30
+	tilemovrow	$123, %tmm2, %zmm30
+
+_intel:
+	.intel_syntax noprefix
+	tcvtrowd2ps	zmm30, tmm5, edx
+	tcvtrowd2ps	zmm30, tmm2, edx
+	tcvtrowd2ps	zmm30, tmm5, 123
+	tcvtrowd2ps	zmm30, tmm2, 123
+	tcvtrowps2pbf16h	zmm30, tmm5, edx
+	tcvtrowps2pbf16h	zmm30, tmm2, edx
+	tcvtrowps2pbf16h	zmm30, tmm5, 123
+	tcvtrowps2pbf16h	zmm30, tmm2, 123
+	tcvtrowps2pbf16l	zmm30, tmm5, edx
+	tcvtrowps2pbf16l	zmm30, tmm2, edx
+	tcvtrowps2pbf16l	zmm30, tmm5, 123
+	tcvtrowps2pbf16l	zmm30, tmm2, 123
+	tcvtrowps2phh	zmm30, tmm5, edx
+	tcvtrowps2phh	zmm30, tmm2, edx
+	tcvtrowps2phh	zmm30, tmm5, 123
+	tcvtrowps2phh	zmm30, tmm2, 123
+	tcvtrowps2phl	zmm30, tmm5, edx
+	tcvtrowps2phl	zmm30, tmm2, edx
+	tcvtrowps2phl	zmm30, tmm5, 123
+	tcvtrowps2phl	zmm30, tmm2, 123
+	tilemovrow	zmm30, tmm5, edx
+	tilemovrow	zmm30, tmm2, edx
+	tilemovrow	zmm30, tmm5, 123
+	tilemovrow	zmm30, tmm2, 123
diff --git a/gas/testsuite/gas/i386/x86-64.exp b/gas/testsuite/gas/i386/x86-64.exp
index 1d54d7700e2..131e598e02a 100644
--- a/gas/testsuite/gas/i386/x86-64.exp
+++ b/gas/testsuite/gas/i386/x86-64.exp
@@ -527,6 +527,8 @@ run_list_test "x86-64-msr_imm-inval"
 run_dump_test "x86-64-amx-transpose"
 run_dump_test "x86-64-amx-transpose-intel"
 run_list_test "x86-64-amx-transpose-inval"
+run_dump_test "x86-64-amx-avx512"
+run_dump_test "x86-64-amx-avx512-intel"
 run_dump_test "x86-64-clzero"
 run_dump_test "x86-64-mwaitx-bdver4"
 run_list_test "x86-64-mwaitx-reg"
diff --git a/opcodes/i386-dis-evex-len.h b/opcodes/i386-dis-evex-len.h
index 24cc7b2e027..276749e1d54 100644
--- a/opcodes/i386-dis-evex-len.h
+++ b/opcodes/i386-dis-evex-len.h
@@ -44,6 +44,13 @@ static const struct dis386 evex_len_table[][3] = {
     { "vperm%DQ",	{ XM, Vex, EXx }, PREFIX_DATA },
   },
 
+  /* EVEX_LEN_0F384A_X86_64_W_0 */
+  {
+    { Bad_Opcode },
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_EVEX_0F384A_X86_64_W_0_L_2) },
+  },
+
   /* EVEX_LEN_0F385A */
   {
     { Bad_Opcode },
@@ -58,6 +65,13 @@ static const struct dis386 evex_len_table[][3] = {
     { VEX_W_TABLE (EVEX_W_0F385B_L_2) },
   },
 
+  /* EVEX_LEN_0F386D_X86_64_W_0_M_1 */
+  {
+    { Bad_Opcode },
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_EVEX_0F386D_X86_64_W_0_L_2) },
+  },
+
   /* EVEX_LEN_0F38C6 */
   {
     { Bad_Opcode },
@@ -86,6 +100,13 @@ static const struct dis386 evex_len_table[][3] = {
     { VEX_W_TABLE (VEX_W_0F3A01_L_1) },
   },
 
+  /* EVEX_LEN_0F3A07_X86_64_W_0 */
+  {
+    { Bad_Opcode },
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_EVEX_0F3A07_X86_64_W_0_L_2) },
+  },
+
   /* EVEX_LEN_0F3A18 */
   {
     { Bad_Opcode },
@@ -156,6 +177,13 @@ static const struct dis386 evex_len_table[][3] = {
     { VEX_W_TABLE (EVEX_W_0F3A43_L_n) },
   },
 
+  /* EVEX_LEN_0F3A77_X86_64_W_0 */
+  {
+    { Bad_Opcode },
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_EVEX_0F3A77_X86_64_W_0_L_2) },
+  },
+
   /* EVEX_LEN_MAP5_6E */
   {
     { PREFIX_TABLE (PREFIX_EVEX_MAP5_6E_L_0) },
diff --git a/opcodes/i386-dis-evex-prefix.h b/opcodes/i386-dis-evex-prefix.h
index 55d6d806ccb..a559b0b7c62 100644
--- a/opcodes/i386-dis-evex-prefix.h
+++ b/opcodes/i386-dis-evex-prefix.h
@@ -243,6 +243,12 @@
     { VEX_W_TABLE (EVEX_W_0F383A_P_1) },
     { "%XEvpminuw",	{ XM, Vex, EXx }, 0 },
   },
+  /* PREFIX_EVEX_0F384A_W_0_L_2 */
+  {
+    { Bad_Opcode },
+    { "tcvtrowd2ps",	{ XM, Rtmm, VexGd }, 0 },
+    { "tilemovrow",	{ XM, Rtmm, VexGd }, 0 },
+  },
   /* PREFIX_EVEX_0F3852 */
   {
     { "vdpphp%XS",	{ XM, Vex, EXx }, 0 },
@@ -264,6 +270,13 @@
     { Bad_Opcode },
     { "vp2intersectY%DQ", { MaskG, Vex, EXx, EXxEVexS }, 0 },
   },
+  /* PREFIX_EVEX_0F386D_W_0_L_2 */
+  {
+    { "tcvtrowps2phh",	{ XM, Rtmm, VexGd }, 0 },
+    { "tcvtrowps2pbf16l",	{ XM, Rtmm, VexGd }, 0 },
+    { "tcvtrowps2phl",	{ XM, Rtmm, VexGd }, 0 },
+    { "tcvtrowps2pbf16h",	{ XM, Rtmm, VexGd }, 0 },
+  },
   /* PREFIX_EVEX_0F3872 */
   {
     { Bad_Opcode },
@@ -306,6 +319,13 @@
     { "%XEvfmsub213s%XW",	{ XMScalar, VexScalar, EXdq, EXxEVexR }, 0 },
     { "v4fnmadds%XS",	{ XMScalar, VexScalar, Mxmm }, 0 },
   },
+  /* PREFIX_EVEX_0F3A07_W_0_L_2 */
+  {
+    { "tcvtrowps2phh",	{ XM, Rtmm, Ib }, 0 },
+    { "tcvtrowd2ps",	{ XM, Rtmm, Ib }, 0 },
+    { "tilemovrow",	{ XM, Rtmm, Ib }, 0 },
+    { "tcvtrowps2pbf16h",	{ XM, Rtmm, Ib }, 0 },
+  },
   /* PREFIX_EVEX_0F3A08 */
   {
     { "vrndscalep%XH",  { XM, EXxh, EXxEVexS, Ib }, 0 },
@@ -377,6 +397,13 @@
     { Bad_Opcode },
     { "vfpclasss%XW",	{ MaskG, EXdq, Ib }, 0 },
   },
+  /* PREFIX_EVEX_0F3A77_W_0_L_2 */
+  {
+    { Bad_Opcode },
+    { "tcvtrowps2pbf16l",	{ XM, Rtmm, Ib }, 0 },
+    { Bad_Opcode },
+    { "tcvtrowps2phl",	{ XM, Rtmm, Ib }, 0 },
+  },
   /* PREFIX_EVEX_0F3AC2 */
   {
     { "vcmpp%XH", { MaskG, Vex, EXxh, EXxEVexS, CMP }, 0 },
diff --git a/opcodes/i386-dis-evex-w.h b/opcodes/i386-dis-evex-w.h
index 36b8150cd2c..70f65dab96e 100644
--- a/opcodes/i386-dis-evex-w.h
+++ b/opcodes/i386-dis-evex-w.h
@@ -336,6 +336,10 @@
   {
     { "vpbroadcastmw2dY",	{ XM, MaskR }, 0 },
   },
+  /* EVEX_W_0F384A_X86_64 */
+  {
+    { EVEX_LEN_TABLE (EVEX_LEN_0F384A_X86_64_W_0) },
+  },
   /* EVEX_W_0F3859 */
   {
     { "vbroadcasti32x2",	{ XM, EXq }, PREFIX_DATA },
@@ -351,6 +355,10 @@
     { "vbroadcasti32x8",	{ XM, Mymm }, PREFIX_DATA },
     { "vbroadcasti64x4",	{ XM, Mymm }, PREFIX_DATA },
   },
+  /* EVEX_W_0F386D_X86_64 */
+  {
+    { EVEX_LEN_TABLE (EVEX_LEN_0F386D_X86_64_W_0) },
+  },
   /* EVEX_W_0F3870 */
   {
     { Bad_Opcode },
@@ -374,6 +382,10 @@
     { Bad_Opcode },
     { "vpmultishiftqb",	{ XM, Vex, EXx }, PREFIX_DATA },
   },
+  /* EVEX_W_0F3A07_X86_64 */
+  {
+    { EVEX_LEN_TABLE (EVEX_LEN_0F3A07_X86_64_W_0) },
+  },
   /* EVEX_W_0F3A18_L_n */
   {
     { "vinsertf32x4",	{ XM, Vex, EXxmm, Ib }, PREFIX_DATA },
@@ -442,6 +454,10 @@
     { Bad_Opcode },
     { "vpshrdw",   { XM, Vex, EXx, Ib }, 0 },
   },
+  /* EVEX_W_0F3A77_X86_64 */
+  {
+    { EVEX_LEN_TABLE (EVEX_LEN_0F3A77_X86_64_W_0) },
+  },
   /* EVEX_W_MAP4_8F_R_0 */
   {
     { "pop2", { { PUSH2_POP2_Fixup, q_mode}, Eq }, NO_PREFIX },
diff --git a/opcodes/i386-dis-evex-x86-64.h b/opcodes/i386-dis-evex-x86-64.h
index 4e52607d306..21bf3bf5e5d 100644
--- a/opcodes/i386-dis-evex-x86-64.h
+++ b/opcodes/i386-dis-evex-x86-64.h
@@ -1,3 +1,23 @@
+  /* X86_64_EVEX_0F384A */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (EVEX_W_0F384A_X86_64) },
+  },
+  /* X86_64_EVEX_0F386D */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (EVEX_W_0F386D_X86_64) },
+  },
+  /* X86_64_EVEX_0F3A07 */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (EVEX_W_0F3A07_X86_64) },
+  },
+  /* X86_64_EVEX_0F3A77 */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (EVEX_W_0F3A77_X86_64) },
+  },
   /* X86_64_EVEX_MAP5_6C_W_1_P_1 */
   {
     { Bad_Opcode },
diff --git a/opcodes/i386-dis-evex.h b/opcodes/i386-dis-evex.h
index d42b5af7b53..130b1da0272 100644
--- a/opcodes/i386-dis-evex.h
+++ b/opcodes/i386-dis-evex.h
@@ -376,7 +376,7 @@ static const struct dis386 evex_table[][256] = {
     /* 48 */
     { Bad_Opcode },
     { X86_64_EVEX_MEM_W_TABLE (VEX_W_0F3849_X86_64_L_0) },
-    { Bad_Opcode },
+    { X86_64_TABLE (X86_64_EVEX_0F384A) },
     { X86_64_EVEX_MEM_W_TABLE (VEX_W_0F384B_X86_64_L_0) },
     { "vrcp14p%XW",	{ XM, EXx }, PREFIX_DATA },
     { "vrcp14s%XW",	{ XMScalar, VexScalar, EXdq }, PREFIX_DATA },
@@ -415,7 +415,7 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_TABLE (X86_64_EVEX_0F386D) },
     { Bad_Opcode },
     { Bad_Opcode },
     /* 70 */
@@ -591,7 +591,7 @@ static const struct dis386 evex_table[][256] = {
     { VEX_W_TABLE (VEX_W_0F3A04) },
     { "%XEvpermilp%XD", { XM, EXx, Ib }, PREFIX_DATA },
     { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_TABLE (X86_64_EVEX_0F3A07) },
     /* 08 */
     { PREFIX_TABLE (PREFIX_EVEX_0F3A08) },
     { "vrndscalep%XD", { XM, EXx, EXxEVexS, Ib }, PREFIX_DATA },
@@ -717,7 +717,7 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_TABLE (X86_64_EVEX_0F3A77) },
     /* 78 */
     { Bad_Opcode },
     { Bad_Opcode },
diff --git a/opcodes/i386-dis.c b/opcodes/i386-dis.c
index 2095bb65196..8f651f7a06f 100644
--- a/opcodes/i386-dis.c
+++ b/opcodes/i386-dis.c
@@ -592,6 +592,7 @@ fetch_error (const instr_info *ins)
 #define VexGatherD { OP_VEX, vex_vsib_d_w_dq_mode }
 #define VexGatherQ { OP_VEX, vex_vsib_q_w_dq_mode }
 #define VexGdq { OP_VEX, dq_mode }
+#define VexGd { OP_VEX, d_mode }
 #define VexGb { OP_VEX, b_mode }
 #define VexGv { OP_VEX, v_mode }
 #define VexTmm { OP_VEX, tmm_mode }
@@ -1200,9 +1201,11 @@ enum
   PREFIX_EVEX_0F3838,
   PREFIX_EVEX_0F3839,
   PREFIX_EVEX_0F383A,
+  PREFIX_EVEX_0F384A_X86_64_W_0_L_2,
   PREFIX_EVEX_0F3852,
   PREFIX_EVEX_0F3853,
   PREFIX_EVEX_0F3868,
+  PREFIX_EVEX_0F386D_X86_64_W_0_L_2,
   PREFIX_EVEX_0F3872,
   PREFIX_EVEX_0F3874,
   PREFIX_EVEX_0F389A,
@@ -1210,6 +1213,7 @@ enum
   PREFIX_EVEX_0F38AA,
   PREFIX_EVEX_0F38AB,
 
+  PREFIX_EVEX_0F3A07_X86_64_W_0_L_2,
   PREFIX_EVEX_0F3A08,
   PREFIX_EVEX_0F3A0A,
   PREFIX_EVEX_0F3A26,
@@ -1221,6 +1225,7 @@ enum
   PREFIX_EVEX_0F3A57,
   PREFIX_EVEX_0F3A66,
   PREFIX_EVEX_0F3A67,
+  PREFIX_EVEX_0F3A77_X86_64_W_0_L_2,
   PREFIX_EVEX_0F3AC2,
 
   PREFIX_EVEX_MAP4_4x,
@@ -1362,7 +1367,12 @@ enum
 
   X86_64_VEX_MAP7_F6_L_0_W_0_R_0,
   X86_64_VEX_MAP7_F8_L_0_W_0_R_0,
-  
+
+  X86_64_EVEX_0F384A,
+  X86_64_EVEX_0F386D,
+  X86_64_EVEX_0F3A07,
+  X86_64_EVEX_0F3A77,
+
   X86_64_EVEX_MAP5_6C_W_1_P_1,
   X86_64_EVEX_MAP5_6C_W_1_P_3,
   X86_64_EVEX_MAP5_6D_W_1_P_1,
@@ -1555,12 +1565,15 @@ enum
   EVEX_LEN_0F381A,
   EVEX_LEN_0F381B,
   EVEX_LEN_0F3836,
+  EVEX_LEN_0F384A_X86_64_W_0,
   EVEX_LEN_0F385A,
   EVEX_LEN_0F385B,
+  EVEX_LEN_0F386D_X86_64_W_0,
   EVEX_LEN_0F38C6,
   EVEX_LEN_0F38C7,
   EVEX_LEN_0F3A00,
   EVEX_LEN_0F3A01,
+  EVEX_LEN_0F3A07_X86_64_W_0,
   EVEX_LEN_0F3A18,
   EVEX_LEN_0F3A19,
   EVEX_LEN_0F3A1A,
@@ -1571,6 +1584,7 @@ enum
   EVEX_LEN_0F3A3A,
   EVEX_LEN_0F3A3B,
   EVEX_LEN_0F3A43,
+  EVEX_LEN_0F3A77_X86_64_W_0,
 
   EVEX_LEN_MAP5_6E,
   EVEX_LEN_MAP5_7E,
@@ -1779,15 +1793,18 @@ enum
   EVEX_W_0F3835_P_2,
   EVEX_W_0F3837,
   EVEX_W_0F383A_P_1,
+  EVEX_W_0F384A_X86_64,
   EVEX_W_0F3859,
   EVEX_W_0F385A_L_n,
   EVEX_W_0F385B_L_2,
+  EVEX_W_0F386D_X86_64,
   EVEX_W_0F3870,
   EVEX_W_0F3872_P_2,
   EVEX_W_0F387A,
   EVEX_W_0F387B,
   EVEX_W_0F3883,
 
+  EVEX_W_0F3A07_X86_64,
   EVEX_W_0F3A18_L_n,
   EVEX_W_0F3A19_L_n,
   EVEX_W_0F3A1A_L_2,
@@ -1802,6 +1819,7 @@ enum
   EVEX_W_0F3A43_L_n,
   EVEX_W_0F3A70,
   EVEX_W_0F3A72,
+  EVEX_W_0F3A77_X86_64,
 
   EVEX_W_MAP4_8F_R_0,
   EVEX_W_MAP4_F8_P1_M_1,
@@ -13931,6 +13949,8 @@ OP_VEX (instr_info *ins, int bytemode, int sizeflag ATTRIBUTE_UNUSED)
     case 512:
       names = att_names_zmm;
       ins->evex_used |= EVEX_len_used;
+      if (bytemode == d_mode)
+	names = att_names32;
       break;
     default:
       abort ();
diff --git a/opcodes/i386-gen.c b/opcodes/i386-gen.c
index be05b1be817..168dc565a60 100644
--- a/opcodes/i386-gen.c
+++ b/opcodes/i386-gen.c
@@ -265,6 +265,8 @@ static const dependency isa_dependencies[] =
     "AMX_TILE" },
   { "AMX_TRANSPOSE",
     "AMX_TILE" },
+  { "AMX_AVX512",
+    "AMX_TILE|AVX10_2" },
   { "KL",
     "SSE2" },
   { "WIDEKL",
@@ -432,6 +434,7 @@ static bitfield cpu_flags[] =
   BITFIELD (AMX_FP16),
   BITFIELD (AMX_COMPLEX),
   BITFIELD (AMX_TRANSPOSE),
+  BITFIELD (AMX_AVX512),
   BITFIELD (AMX_TILE),
   BITFIELD (MOVDIRI),
   BITFIELD (MOVDIR64B),
diff --git a/opcodes/i386-opc.h b/opcodes/i386-opc.h
index fd11f9f0cd8..91972954966 100644
--- a/opcodes/i386-opc.h
+++ b/opcodes/i386-opc.h
@@ -252,6 +252,8 @@ enum i386_cpu
   CpuAMX_FP16,
   /* AMX-COMPLEX instructions required.  */
   CpuAMX_COMPLEX,
+  /* Intel AMX-AVX512 Instructions support required.  */
+  CpuAMX_AVX512,
   /* AMX-TILE instructions required */
   CpuAMX_TILE,
   /* GFNI instructions required */
@@ -500,6 +502,7 @@ typedef union i386_cpu_flags
       unsigned int cpuamx_bf16:1;
       unsigned int cpuamx_fp16:1;
       unsigned int cpuamx_complex:1;
+      unsigned int cpuamx_avx512:1;
       unsigned int cpuamx_tile:1;
       unsigned int cpugfni:1;
       unsigned int cpuvaes:1;
diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl
index d8f2a180ba7..d17765aa0af 100644
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -3204,6 +3204,19 @@ tconjtcmmimfp16ps, 0x6b, AMX_COMPLEX&AMX_TRANSPOSE, Modrm|Vex128|Space0F38|Src2V
 
 tconjtfp16, 0x666b, AMX_COMPLEX&AMX_TRANSPOSE, Modrm|Vex128|Space0F38|VexW0|NoSuf, { RegTMM, RegTMM }
 
+tcvtrowd2ps, 0xf34a, AMX_AVX512, Modrm|EVex512|Space0F38|Src2VVVV|VexW0|NoSuf, { Reg32, RegTMM, RegZMM }
+tcvtrowd2ps, 0xf307, AMX_AVX512, Modrm|EVex512|Space0F3A|VexW0|NoSuf, { Imm8, RegTMM, RegZMM }
+
+tcvtrowps2pbf16h, 0xf26d, AMX_AVX512, Modrm|EVex512|Space0F38|Src2VVVV|VexW0|NoSuf, { Reg32, RegTMM, RegZMM }
+tcvtrowps2pbf16h, 0xf207, AMX_AVX512, Modrm|EVex512|Space0F3A|VexW0|NoSuf, { Imm8, RegTMM, RegZMM }
+tcvtrowps2pbf16l, 0xf36d, AMX_AVX512, Modrm|EVex512|Space0F38|Src2VVVV|VexW0|NoSuf, { Reg32, RegTMM, RegZMM }
+tcvtrowps2pbf16l, 0xf377, AMX_AVX512, Modrm|EVex512|Space0F3A|VexW0|NoSuf, { Imm8, RegTMM, RegZMM }
+
+tcvtrowps2phh, 0x6d, AMX_AVX512, Modrm|EVex512|Space0F38|Src2VVVV|VexW0|NoSuf, { Reg32, RegTMM, RegZMM }
+tcvtrowps2phh, 0x07, AMX_AVX512, Modrm|EVex512|Space0F3A|VexW0|NoSuf, { Imm8, RegTMM, RegZMM }
+tcvtrowps2phl, 0x666d, AMX_AVX512, Modrm|EVex512|Space0F38|Src2VVVV|VexW0|NoSuf, { Reg32, RegTMM, RegZMM }
+tcvtrowps2phl, 0xf277, AMX_AVX512, Modrm|EVex512|Space0F3A|VexW0|NoSuf, { Imm8, RegTMM, RegZMM }
+
 tdpbf16ps, 0xf35c, AMX_BF16, Modrm|Vex128|Space0F38|Src2VVVV|VexW0|NoSuf, { RegTMM, RegTMM, RegTMM }
 tdpfp16ps, 0xf25c, AMX_FP16, Modrm|Vex128|Space0F38|Src2VVVV|VexW0|NoSuf, { RegTMM, RegTMM, RegTMM }
 tdpbssd, 0xf25e, AMX_INT8, Modrm|Vex128|Space0F38|Src2VVVV|VexW0|NoSuf, { RegTMM, RegTMM, RegTMM }
@@ -3213,6 +3226,8 @@ tdpbsud, 0xf35e, AMX_INT8, Modrm|Vex128|Space0F38|Src2VVVV|VexW0|NoSuf, { RegTMM
 
 tileloadd, 0xf24b, APX_F(AMX_TILE), Sibmem|Vex128|EVex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex, RegTMM }
 tileloaddt1, 0x664b, APX_F(AMX_TILE), Sibmem|Vex128|EVex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex, RegTMM }
+tilemovrow, 0x664a, AMX_AVX512, Modrm|EVex512|Space0F38|Src2VVVV|VexW0|NoSuf, { Reg32, RegTMM, RegZMM }
+tilemovrow, 0x6607, AMX_AVX512, Modrm|EVex512|Space0F3A|VexW0|NoSuf, { Imm8, RegTMM, RegZMM }
 tilestored, 0xf34b, APX_F(AMX_TILE), Sibmem|Vex128|EVex128|Space0F38|VexW0|NoSuf, { RegTMM, Unspecified|BaseIndex }
 
 tilerelease, 0x49c0, AMX_TILE, Vex128|Space0F38|VexW0|NoSuf, {}
-- 
2.31.1



More information about the Binutils mailing list