@@ -1,5 +1,7 @@
-*- text -*-
+* Add support for Intel SHA512 instructions.
+
* Add support for Intel AVX-VNNI-INT16 instructions.
Changes in 2.41:
@@ -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
@@ -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}
@@ -498,6 +498,8 @@ 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 "sg"
run_dump_test "clzero"
run_dump_test "invlpgb"
new file mode 100644
@@ -0,0 +1,16 @@
+#as:
+#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
new file mode 100644
@@ -0,0 +1,16 @@
+#as:
+#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
new file mode 100644
@@ -0,0 +1,13 @@
+# Check 32bit SHA512 instructions
+
+ .allow_index_reg
+ .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
new file mode 100644
@@ -0,0 +1,16 @@
+#as:
+#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 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
new file mode 100644
@@ -0,0 +1,16 @@
+#as:
+#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 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
new file mode 100644
@@ -0,0 +1,13 @@
+# Check 64bit SHA512 instructions
+
+ .allow_index_reg
+ .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
@@ -440,6 +440,8 @@ run_dump_test "x86-64-lkgs"
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_dump_test "x86-64-clzero"
run_dump_test "x86-64-mwaitx-bdver4"
run_list_test "x86-64-mwaitx-reg"
@@ -530,6 +530,7 @@ 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 Uymm { OP_R, ymm_mode }
#define Rtmm { OP_R, tmm_mode }
#define EMCq { OP_EMC, q_mode }
#define MXC { OP_MXC, 0 }
@@ -895,6 +896,8 @@ enum
MOD_0F38DC_PREFIX_1,
MOD_VEX_0F3849_X86_64_L_0_W_0,
+ MOD_VEX_0F38CB_P_3_W_0_L_1,
+ MOD_VEX_0F38CC_P_3_W_0_L_1,
};
enum
@@ -1064,6 +1067,9 @@ 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,
@@ -1306,6 +1312,9 @@ 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,
@@ -1473,6 +1482,9 @@ 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,
@@ -3928,6 +3940,30 @@ 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 },
@@ -6380,9 +6416,9 @@ 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 */
@@ -6944,6 +6980,24 @@ 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 },
+ { MOD_TABLE (MOD_VEX_0F38CB_P_3_W_0_L_1) },
+ },
+
+ /* VEX_LEN_0F38CC_P_3_W_0 */
+ {
+ { Bad_Opcode },
+ { MOD_TABLE (MOD_VEX_0F38CC_P_3_W_0_L_1) },
+ },
+
+ /* VEX_LEN_0F38CD_P_3_W_0 */
+ {
+ { Bad_Opcode },
+ { "vsha512msg2", { XM, Uymm }, 0 },
+ },
+
/* VEX_LEN_0F38DB */
{
{ "vaesimc", { XM, EXx }, PREFIX_DATA },
@@ -7614,6 +7668,18 @@ 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 },
@@ -8055,6 +8121,16 @@ static const struct dis386 mod_table[][2] = {
{ PREFIX_TABLE (PREFIX_VEX_0F3849_X86_64_L_0_W_0_M_0) },
{ PREFIX_TABLE (PREFIX_VEX_0F3849_X86_64_L_0_W_0_M_1) },
},
+ {
+ /* MOD_VEX_0F38CB_P_3_W_0_L_1 */
+ { Bad_Opcode },
+ { "vsha512rnds2", { XM, Vex, EXxmm }, 0 },
+ },
+ {
+ /* MOD_VEX_0F38CC_P_3_W_0_L_1 */
+ { Bad_Opcode },
+ { "vsha512msg1", { XM, EXxmm }, 0 },
+ },
#include "i386-dis-evex-mod.h"
};
@@ -168,6 +168,8 @@ static const dependency isa_dependencies[] =
"LKGS" },
{ "AVX_VNNI_INT16",
"AVX2" },
+ { "SHA512",
+ "AVX" },
{ "AVX512F",
"AVX2" },
{ "AVX512CD",
@@ -369,6 +371,7 @@ static bitfield cpu_flags[] =
BITFIELD (FRED),
BITFIELD (LKGS),
BITFIELD (AVX_VNNI_INT16),
+ BITFIELD (SHA512),
BITFIELD (MWAITX),
BITFIELD (CLZERO),
BITFIELD (OSPKE),
@@ -235,6 +235,8 @@ enum
CpuLKGS,
/* Intel AVX VNNI-INT16 Instructions support required. */
CpuAVX_VNNI_INT16,
+ /* Intel SHA512 Instructions support required. */
+ CpuSHA512,
/* mwaitx instruction required */
CpuMWAITX,
/* Clzero instruction required */
@@ -433,6 +435,7 @@ typedef union i386_cpu_flags
unsigned int cpufred:1;
unsigned int cpulkgs:1;
unsigned int cpuavx_vnni_int16:1;
+ unsigned int cpusha512:1;
unsigned int cpumwaitx:1;
unsigned int cpuclzero:1;
unsigned int cpuospke:1;
@@ -3375,3 +3375,11 @@ vpdpwsud, 0xf3d2, AVX_VNNI_INT16, Modrm|Vex|Space0F38|VexVVVV|VexW0|CheckOperand
vpdpwsuds, 0xf3d3, AVX_VNNI_INT16, Modrm|Vex|Space0F38|VexVVVV|VexW0|CheckOperandSize|NoSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
// AVX_VNNI_INT16 instructions end.
+
+// SHA512 instructions.
+
+vsha512rnds2, 0xf2cb, SHA512, Vex256|Space0F38|Modrm|VexVVVV|VexW0|NoSuf, { RegXMM, RegYMM, RegYMM }
+vsha512msg1, 0xf2cc, SHA512, Vex256|Space0F38|Modrm|VexW0|NoSuf, { RegXMM, RegYMM }
+vsha512msg2, 0xf2cd, SHA512, Vex256|Space0F38|Modrm|VexW0|NoSuf, { RegYMM, RegYMM }
+
+// SHA512 instructions end.