Support Intel SHA512

gas/ChangeLog:

	* NEWS: Support Intel SHA512.
	* config/tc-i386.c: Add sha512.
	* doc/c-i386.texi: Document .sha512.
	* testsuite/gas/i386/disassem.d: Add SHA512 tests.
	* testsuite/gas/i386/disassem.s: Ditto.
	* testsuite/gas/i386/i386.exp: Run SHA512 tests.
	* testsuite/gas/i386/x86-64.exp: Ditto.
	* testsuite/gas/i386/sha512-intel.d: New test.
	* testsuite/gas/i386/sha512-inval.l: Ditto.
	* testsuite/gas/i386/sha512-inval.s: Ditto.
	* testsuite/gas/i386/sha512.d: Ditto.
	* testsuite/gas/i386/sha512.s: Ditto.
	* testsuite/gas/i386/x86-64-sha512-intel.d: Ditto.
	* testsuite/gas/i386/x86-64-sha512-inval.l: Ditto.
	* testsuite/gas/i386/x86-64-sha512-inval.s: Ditto.
	* testsuite/gas/i386/x86-64-sha512.d: Ditto.
	* testsuite/gas/i386/x86-64-sha512.s: Ditto.

opcodes/ChangeLog:

	* i386-dis.c (Rxmmq): New.
	(Rymm): Ditto.
	(PREFIX_VEX_0F38CB): Ditto.
	(PREFIX_VEX_0F38CC): Ditto.
	(PREFIX_VEX_0F38CD): Ditto.
	(VEX_LEN_0F38CB_P_3_W_0): Ditto.
	(VEX_LEN_0F38CC_P_3_W_0): Ditto.
	(VEX_LEN_0F38CD_P_3_W_0): Ditto.
	(VEX_W_0F38CB_P_3): Ditto.
	(VEX_W_0F38CC_P_3): Ditto.
	(VEX_W_0F38CD_P_3): Ditto.
	(prefix_table): Add PREFIX_VEX_0F38CB, PREFIX_VEX_0F38CC,
	PREFIX_VEX_0F38CD.
	(vex_len_table): Add VEX_LEN_0F38CB_P_3_W_0,
	VEX_LEN_0F38CC_P_3_W_0, VEX_LEN_0F38CD_P_3_W_0.
	(vex_w_table): Add VEX_W_0F38CB_P_3, VEX_W_0F38CC_P_3, VEX_W_0F38CD_P_3.
	* i386-gen.c (isa_dependencies): Add SHA512.
	(cpu_flags): Ditto.
	* i386-init.h: Regenerated.
	* i386-mnem.h: Ditto.
	* i386-opc.h (CpuSHA512): New.
	(i386_cpu_flags): Add cpusha512.
	* i386-opc.tbl: Add SHA512 instructions.
	* i386-tbl.h: Regenerated.
This commit is contained in:
Haochen Jiang
2023-07-24 11:09:43 +08:00
parent 3fde5f6e7d
commit 3ac2eb9481
24 changed files with 7411 additions and 7131 deletions
+2
View File
@@ -1,5 +1,7 @@
-*- text -*-
* Add support for Intel SHA512 instructions.
* Add support for Intel AVX-VNNI-INT16 instructions.
Changes in 2.41:
+1
View File
@@ -1152,6 +1152,7 @@ static const arch_entry cpu_arch[] =
SUBARCH (fred, FRED, ANY_FRED, false),
SUBARCH (lkgs, LKGS, ANY_LKGS, false),
SUBARCH (avx_vnni_int16, AVX_VNNI_INT16, ANY_AVX_VNNI_INT16, false),
SUBARCH (sha512, SHA512, ANY_SHA512, false),
};
#undef SUBARCH
+2 -1
View File
@@ -208,6 +208,7 @@ accept various extension mnemonics. For example,
@code{fred},
@code{lkgs},
@code{avx_vnni_int16},
@code{sha512},
@code{amx_int8},
@code{amx_bf16},
@code{amx_fp16},
@@ -1637,7 +1638,7 @@ supported on the CPU specified. The choices for @var{cpu_type} are:
@item @samp{.prefetchi} @tab @samp{.avx_ifma} @tab @samp{.avx_vnni_int8}
@item @samp{.cmpccxadd} @tab @samp{.wrmsrns} @tab @samp{.msrlist}
@item @samp{.avx_ne_convert} @tab @samp{.rao_int} @tab @samp{.fred} @tab @samp{.lkgs}
@item @samp{.avx_vnni_int16}
@item @samp{.avx_vnni_int16} @tab @samp{.sha512}
@item @samp{.wbnoinvd} @tab @samp{.pconfig} @tab @samp{.waitpkg} @tab @samp{.cldemote}
@item @samp{.shstk} @tab @samp{.gfni} @tab @samp{.vaes} @tab @samp{.vpclmulqdq}
@item @samp{.movdiri} @tab @samp{.movdir64b} @tab @samp{.enqcmd} @tab @samp{.tsxldtrk}
+6
View File
@@ -345,6 +345,12 @@ Disassembly of section \.text:
[ ]*[a-f0-9]+:[ ]*c4 e2 01 1c[ ]*\(bad\)
[ ]*[a-f0-9]+:[ ]*41[ ]*inc[ ]*%ecx
[ ]*[a-f0-9]+:[ ]*37[ ]*aaa
[ ]*[a-f0-9]+:[ ]*c4 e2 7f cc[ ]+vsha512msg1[ ]*\(bad\),.*
[ ]*[a-f0-9]+:[ ]*71 20[ ]+jno.*
[ ]*[a-f0-9]+:[ ]*c4 e2 7f cd[ ]+vsha512msg2[ ]*\(bad\),.*
[ ]*[a-f0-9]+:[ ]*71 20[ ]+jno.*
[ ]*[a-f0-9]+:[ ]*c4 e2 6f cb[ ]+vsha512rnds2[ ]*\(bad\),.*
[ ]*[a-f0-9]+:[ ]*71 20[ ]+jno.*
[ ]*[a-f0-9]+:[ ]*62 f2 ad 08 1c[ ]*\(bad\)
[ ]*[a-f0-9]+:[ ]*01 01[ ]*add[ ]*%eax,\(%ecx\)
[ ]*[a-f0-9]+:[ ]*62 f3 7d 28 1b[ ]*\(bad\)
+3
View File
@@ -168,6 +168,9 @@
.byte 0xC4, 0xE1, 0xF9, 0x93, 0x6F
.insn VEX.L0.66.0f.W1 0x93, (%edi), %k7
.byte 0xc4, 0xe2, 0x1, 0x1c, 0x41, 0x37
.insn VEX.L1.F2.0f38.W0 0xCC, 32(%ecx), %ymm6
.insn VEX.L1.F2.0f38.W0 0xCD, 32(%ecx), %ymm6
.insn VEX.L1.F2.0f38.W0 0xCB, 32(%ecx), %ymm2, %ymm6
.byte 0x62, 0xf2, 0xad, 0x08, 0x1c, 0x01
.byte 0x1
.insn EVEX.66.0f3a.W0 0x1b, $0x25, %ymm0, %xmm1
+3
View File
@@ -498,6 +498,9 @@ if [gas_32_check] then {
run_list_test "amx-complex-inval"
run_dump_test "avx-vnni-int16"
run_dump_test "avx-vnni-int16-intel"
run_dump_test "sha512"
run_dump_test "sha512-intel"
run_list_test "sha512-inval"
run_list_test "sg"
run_dump_test "clzero"
run_dump_test "invlpgb"
+15
View File
@@ -0,0 +1,15 @@
#objdump: -dw -Mintel
#name: i386 SHA512 insns (Intel disassembly)
#source: sha512.s
.*: +file format .*
Disassembly of section \.text:
0+ <_start>:
\s*[a-f0-9]+:\s*c4 e2 7f cc f5\s+vsha512msg1 ymm6,xmm5
\s*[a-f0-9]+:\s*c4 e2 7f cd f5\s+vsha512msg2 ymm6,ymm5
\s*[a-f0-9]+:\s*c4 e2 57 cb f4\s+vsha512rnds2 ymm6,ymm5,xmm4
\s*[a-f0-9]+:\s*c4 e2 7f cc f5\s+vsha512msg1 ymm6,xmm5
\s*[a-f0-9]+:\s*c4 e2 7f cd f5\s+vsha512msg2 ymm6,ymm5
\s*[a-f0-9]+:\s*c4 e2 57 cb f4\s+vsha512rnds2 ymm6,ymm5,xmm4
+4
View File
@@ -0,0 +1,4 @@
.* Assembler messages:
.*:5: Error: operand .* mismatch for `vsha512msg1'
.*:6: Error: operand .* mismatch for `vsha512msg2'
.*:7: Error: operand .* mismatch for `vsha512rnds2'
+7
View File
@@ -0,0 +1,7 @@
# Check Illegal SHA512 instructions
.text
_start:
vsha512msg1 (%ecx), %ymm6
vsha512msg2 (%ecx), %ymm6
vsha512rnds2 (%ecx), %ymm5, %ymm6
+15
View File
@@ -0,0 +1,15 @@
#objdump: -dw
#name: i386 SHA512 insns
#source: sha512.s
.*: +file format .*
Disassembly of section \.text:
0+ <_start>:
\s*[a-f0-9]+:\s*c4 e2 7f cc f5\s+vsha512msg1 %xmm5,%ymm6
\s*[a-f0-9]+:\s*c4 e2 7f cd f5\s+vsha512msg2 %ymm5,%ymm6
\s*[a-f0-9]+:\s*c4 e2 57 cb f4\s+vsha512rnds2 %xmm4,%ymm5,%ymm6
\s*[a-f0-9]+:\s*c4 e2 7f cc f5\s+vsha512msg1 %xmm5,%ymm6
\s*[a-f0-9]+:\s*c4 e2 7f cd f5\s+vsha512msg2 %ymm5,%ymm6
\s*[a-f0-9]+:\s*c4 e2 57 cb f4\s+vsha512rnds2 %xmm4,%ymm5,%ymm6
+12
View File
@@ -0,0 +1,12 @@
# Check 32bit SHA512 instructions
.text
_start:
vsha512msg1 %xmm5, %ymm6 #SHA512
vsha512msg2 %ymm5, %ymm6 #SHA512
vsha512rnds2 %xmm4, %ymm5, %ymm6 #SHA512
.intel_syntax noprefix
vsha512msg1 ymm6, xmm5 #SHA512
vsha512msg2 ymm6, ymm5 #SHA512
vsha512rnds2 ymm6, ymm5, xmm4 #SHA512
@@ -0,0 +1,15 @@
#objdump: -dw -Mintel
#name: x86_64 SHA512 insns (Intel disassembly)
#source: x86-64-sha512.s
.*: +file format .*
Disassembly of section \.text:
0+ <_start>:
\s*[a-f0-9]+:\s*c4 c2 7f cc f7\s+vsha512msg1 ymm6,xmm15
\s*[a-f0-9]+:\s*c4 62 7f cd fd\s+vsha512msg2 ymm15,ymm5
\s*[a-f0-9]+:\s*c4 62 57 cb f4\s+vsha512rnds2 ymm14,ymm5,xmm4
\s*[a-f0-9]+:\s*c4 c2 7f cc f7\s+vsha512msg1 ymm6,xmm15
\s*[a-f0-9]+:\s*c4 62 7f cd fd\s+vsha512msg2 ymm15,ymm5
\s*[a-f0-9]+:\s*c4 62 57 cb f4\s+vsha512rnds2 ymm14,ymm5,xmm4
@@ -0,0 +1,4 @@
.* Assembler messages:
.*:5: Error: operand .* mismatch for `vsha512msg1'
.*:6: Error: operand .* mismatch for `vsha512msg2'
.*:7: Error: operand .* mismatch for `vsha512rnds2'
@@ -0,0 +1,7 @@
# Check Illegal SHA512 instructions
.text
_start:
vsha512msg1 (%ecx), %ymm6
vsha512msg2 (%ecx), %ymm6
vsha512rnds2 (%ecx), %ymm5, %ymm6
+15
View File
@@ -0,0 +1,15 @@
#objdump: -dw
#name: x86_64 SHA512 insns
#source: x86-64-sha512.s
.*: +file format .*
Disassembly of section \.text:
0+ <_start>:
\s*[a-f0-9]+:\s*c4 c2 7f cc f7\s+vsha512msg1 %xmm15,%ymm6
\s*[a-f0-9]+:\s*c4 62 7f cd fd\s+vsha512msg2 %ymm5,%ymm15
\s*[a-f0-9]+:\s*c4 62 57 cb f4\s+vsha512rnds2 %xmm4,%ymm5,%ymm14
\s*[a-f0-9]+:\s*c4 c2 7f cc f7\s+vsha512msg1 %xmm15,%ymm6
\s*[a-f0-9]+:\s*c4 62 7f cd fd\s+vsha512msg2 %ymm5,%ymm15
\s*[a-f0-9]+:\s*c4 62 57 cb f4\s+vsha512rnds2 %xmm4,%ymm5,%ymm14
+12
View File
@@ -0,0 +1,12 @@
# Check 64bit SHA512 instructions
.text
_start:
vsha512msg1 %xmm15, %ymm6 #SHA512
vsha512msg2 %ymm5, %ymm15 #SHA512
vsha512rnds2 %xmm4, %ymm5, %ymm14 #SHA512
.intel_syntax noprefix
vsha512msg1 ymm6, xmm15 #SHA512
vsha512msg2 ymm15, ymm5 #SHA512
vsha512rnds2 ymm14, ymm5, xmm4 #SHA512
+3
View File
@@ -441,6 +441,9 @@ run_dump_test "x86-64-lkgs-intel"
run_list_test "x86-64-lkgs-inval"
run_dump_test "x86-64-avx-vnni-int16"
run_dump_test "x86-64-avx-vnni-int16-intel"
run_dump_test "x86-64-sha512"
run_dump_test "x86-64-sha512-intel"
run_list_test "x86-64-sha512-inval"
run_dump_test "x86-64-clzero"
run_dump_test "x86-64-mwaitx-bdver4"
run_list_test "x86-64-mwaitx-reg"
+68 -3
View File
@@ -530,6 +530,8 @@ fetch_error (const instr_info *ins)
#define Nq { OP_R, q_mode }
#define Ux { OP_R, x_mode }
#define Uxmm { OP_R, xmm_mode }
#define Rxmmq { OP_R, xmmq_mode }
#define Rymm { OP_R, ymm_mode }
#define Rtmm { OP_R, tmm_mode }
#define EMCq { OP_EMC, q_mode }
#define MXC { OP_MXC, 0 }
@@ -1062,6 +1064,9 @@ enum
PREFIX_VEX_0F38B1_W_0,
PREFIX_VEX_0F38D2_W_0,
PREFIX_VEX_0F38D3_W_0,
PREFIX_VEX_0F38CB,
PREFIX_VEX_0F38CC,
PREFIX_VEX_0F38CD,
PREFIX_VEX_0F38F5_L_0,
PREFIX_VEX_0F38F6_L_0,
PREFIX_VEX_0F38F7_L_0,
@@ -1304,6 +1309,9 @@ enum
VEX_LEN_0F385C_X86_64,
VEX_LEN_0F385E_X86_64,
VEX_LEN_0F386C_X86_64,
VEX_LEN_0F38CB_P_3_W_0,
VEX_LEN_0F38CC_P_3_W_0,
VEX_LEN_0F38CD_P_3_W_0,
VEX_LEN_0F38DB,
VEX_LEN_0F38F2,
VEX_LEN_0F38F3,
@@ -1471,6 +1479,9 @@ enum
VEX_W_0F38B1,
VEX_W_0F38B4,
VEX_W_0F38B5,
VEX_W_0F38CB_P_3,
VEX_W_0F38CC_P_3,
VEX_W_0F38CD_P_3,
VEX_W_0F38CF,
VEX_W_0F38D2,
VEX_W_0F38D3,
@@ -3926,6 +3937,30 @@ static const struct dis386 prefix_table[][4] = {
{ "vpdpwusds", { XM, Vex, EXx }, 0 },
},
/* PREFIX_VEX_0F38CB */
{
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ VEX_W_TABLE (VEX_W_0F38CB_P_3) },
},
/* PREFIX_VEX_0F38CC */
{
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ VEX_W_TABLE (VEX_W_0F38CC_P_3) },
},
/* PREFIX_VEX_0F38CD */
{
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ VEX_W_TABLE (VEX_W_0F38CD_P_3) },
},
/* PREFIX_VEX_0F38F5_L_0 */
{
{ "bzhiS", { Gdq, Edq, VexGdq }, 0 },
@@ -6378,9 +6413,9 @@ static const struct dis386 vex_table[][256] = {
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ PREFIX_TABLE (PREFIX_VEX_0F38CB) },
{ PREFIX_TABLE (PREFIX_VEX_0F38CC) },
{ PREFIX_TABLE (PREFIX_VEX_0F38CD) },
{ Bad_Opcode },
{ VEX_W_TABLE (VEX_W_0F38CF) },
/* d0 */
@@ -6942,6 +6977,24 @@ static const struct dis386 vex_len_table[][2] = {
{ VEX_W_TABLE (VEX_W_0F386C_X86_64_L_0) },
},
/* VEX_LEN_0F38CB_P_3_W_0 */
{
{ Bad_Opcode },
{ "vsha512rnds2", { XM, Vex, Rxmmq }, 0 },
},
/* VEX_LEN_0F38CC_P_3_W_0 */
{
{ Bad_Opcode },
{ "vsha512msg1", { XM, Rxmmq }, 0 },
},
/* VEX_LEN_0F38CD_P_3_W_0 */
{
{ Bad_Opcode },
{ "vsha512msg2", { XM, Rymm }, 0 },
},
/* VEX_LEN_0F38DB */
{
{ "vaesimc", { XM, EXx }, PREFIX_DATA },
@@ -7612,6 +7665,18 @@ static const struct dis386 vex_w_table[][2] = {
{ Bad_Opcode },
{ "%XVvpmadd52huq", { XM, Vex, EXx }, PREFIX_DATA },
},
{
/* VEX_W_0F38CB_P_3 */
{ VEX_LEN_TABLE (VEX_LEN_0F38CB_P_3_W_0) },
},
{
/* VEX_W_0F38CC_P_3 */
{ VEX_LEN_TABLE (VEX_LEN_0F38CC_P_3_W_0) },
},
{
/* VEX_W_0F38CD_P_3 */
{ VEX_LEN_TABLE (VEX_LEN_0F38CD_P_3_W_0) },
},
{
/* VEX_W_0F38CF */
{ "%XEvgf2p8mulb", { XM, Vex, EXx }, PREFIX_DATA },
+3
View File
@@ -214,6 +214,8 @@ static const dependency isa_dependencies[] =
"XSAVE" },
{ "SHA",
"SSE2" },
{ "SHA512",
"AVX2" },
{ "XSAVES",
"XSAVEC" },
{ "XSAVEC",
@@ -338,6 +340,7 @@ static bitfield cpu_flags[] =
BITFIELD (PRFCHW),
BITFIELD (SMAP),
BITFIELD (SHA),
BITFIELD (SHA512),
BITFIELD (ClflushOpt),
BITFIELD (XSAVES),
BITFIELD (XSAVEC),
+439 -419
View File
File diff suppressed because it is too large Load Diff
+1976 -1973
View File
File diff suppressed because it is too large Load Diff
+3
View File
@@ -175,6 +175,8 @@ enum
CpuSMAP,
/* SHA instructions required. */
CpuSHA,
/* SHA512 instructions required. */
CpuSHA512,
/* CLFLUSHOPT instruction required */
CpuClflushOpt,
/* XSAVES/XRSTORS instruction required */
@@ -403,6 +405,7 @@ typedef union i386_cpu_flags
unsigned int cpuprfchw:1;
unsigned int cpusmap:1;
unsigned int cpusha:1;
unsigned int cpusha512:1;
unsigned int cpuclflushopt:1;
unsigned int cpuxsaves:1;
unsigned int cpuxsavec:1;
+8
View File
@@ -2043,6 +2043,14 @@ sha256rnds2, 0xf38cb, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
sha256msg1, 0xf38cc, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
sha256msg2, 0xf38cd, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
// SHA512 instructions.
vsha512rnds2, 0xf2cb, SHA512, Modrm|Vex256|Space0F38|VexVVVV|VexW0|NoSuf, { RegXMM, RegYMM, RegYMM }
vsha512msg1, 0xf2cc, SHA512, Modrm|Vex256|Space0F38|VexW0|NoSuf, { RegXMM, RegYMM }
vsha512msg2, 0xf2cd, SHA512, Modrm|Vex256|Space0F38|VexW0|NoSuf, { RegYMM, RegYMM }
// SHA512 instructions end.
// VPCLMULQDQ instructions
vpclmulqdq, 0x6644, VPCLMULQDQ, Modrm|Vex256|Space0F3A|VexWIG|VexVVVV|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
+4788 -4735
View File
File diff suppressed because it is too large Load Diff