mirrors/Bochs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
7775483d5e
Bochs/bochs/cpu
History
Stanislav Shwartsman 7775483d5e Implemented VCVTPS2PH AVX-512 instruction 
Now only missed AVX-512 opcodes now are:

512.66.0F38.W0 2C VSCALEFPS
512.66.0F38.W1 2C VSCALEFPD
NDS.LIG.66.0F38.W0 2D VSCALESS
NDS.LIG.66.0F38.W1 2D VSCALESD

512.66.0F38.W0 4C VRCP14PS
512.66.0F38.W1 4C VRCP14PD
NDS.LIG.66.0F38.W0 4D VRCP14SS
NDS.LIG.66.0F38.W1 4D VRCP14SD
512.66.0F38.W0 4E VRSQRT14PS
512.66.0F38.W1 4E VRSQRT14PD
NDS.LIG.66.0F38.W0 4F VRSQRT14SS
NDS.LIG.66.0F38.W1 4F VRSQRT14SD

512.66.0F3A.W0 08 VRNDSCALEPS
512.66.0F3A.W1 09 VRNDSCALEPD
NDS.LIG.66.0F3A.W1 0A VRNDSCALESS
NDS.LIG.66.0F3A.W1 0B VRNDSCALESD
2014-02-15 19:21:08 +00:00
..
cpudb various fixes 2013-08-29 19:43:15 +00:00
fpu bugfix and code cleanup 2014-02-12 20:31:22 +00:00
3dnow.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
access32.cc first infrastructure changes to support EVEX prefix and AVX-512 extensions recently published by Intel 2013-07-26 12:50:56 +00:00
access64.cc fixed segfault in AVX emulation 2013-12-22 21:16:10 +00:00
access.cc move canonical check of high part of page split access to another function to fix code duplication 2013-12-21 21:56:55 +00:00
aes.cc Implemented VCMPPS/PD/SS/SD AVX512 instructions 2013-12-03 15:44:23 +00:00
apic.cc Move INTR, Local APIC INTR and SVN VINTR into new event interface (hardest part) 2012-10-03 20:24:29 +00:00
apic.h preparations for apic regs virtualization feature described in SDM rev044 2012-09-06 15:21:08 +00:00
arith8.cc CMPXHG should always write to memory dest - affects APIC virtualization VMEXIT conditions 2013-07-24 21:06:24 +00:00
arith16.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
arith32.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
arith64.cc VMX: CMPXHG instructions should always write to the memory destination, even if the value unchanged - it affects VMEXIT conditions for the full apic virtualization 2013-08-04 19:37:04 +00:00
avx2.cc Implemented VPMOVSX*/VPMOVZX* AVX-512 instructions 2014-02-02 19:56:08 +00:00
avx512_cvt.cc Implemented VCVTPS2PH AVX-512 instruction 2014-02-15 19:21:08 +00:00
avx512_fma.cc implement EVEX SAE (suppress all exceptions) contol, implement AVX512 INSTERT/EXTRACTPS opcodes 2013-12-14 12:45:06 +00:00
avx512_mask16.cc avx512 implementation fixes and next steps 2013-10-08 18:31:18 +00:00
avx512_move.cc Implemented VPMOVSX*/VPMOVZX* AVX-512 instructions 2014-02-02 19:56:08 +00:00
avx512_pfp.cc complete compressed displ feature support, bugfixes in AVX-512 code 2014-02-11 16:10:31 +00:00
avx512.cc bugfix 2014-02-11 17:47:52 +00:00
avx_cvt.cc remove code duplication, prepare for 512-bit evrsion of cvtps2ph 2014-02-08 19:18:17 +00:00
avx_fma.cc implement EVEX SAE (suppress all exceptions) contol, implement AVX512 INSTERT/EXTRACTPS opcodes 2013-12-14 12:45:06 +00:00
avx_pfp.cc implement DPPS/DPPD ops using existing primitives; added some missing defs 2014-02-02 18:57:25 +00:00
avx.cc infrastructure change for avx-512: before going to more new instructions modelling 2014-01-10 19:40:38 +00:00
bcd.cc reword all the CPU code in preparation for future CPU speedup implementation. 2011-07-06 20:01:18 +00:00
bit16.cc optimize POPCNT implementation 2012-09-21 14:56:56 +00:00
bit32.cc optimize POPCNT implementation 2012-09-21 14:56:56 +00:00
bit64.cc optimize POPCNT implementation 2012-09-21 14:56:56 +00:00
bit.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
bmi32.cc add dedicated 8bit low register accessor 2013-12-01 22:18:38 +00:00
bmi64.cc add dedicated 8bit low register accessor 2013-12-01 22:18:38 +00:00
call_far.cc stack direct access optimization - 5% emu speedup to all 32-bit guests, for 64-bit guests speedup is less because they have less stack accesses 2012-03-25 11:54:32 +00:00
cpu.cc added lock prefix used info into bx_Instriction_c and use it in disasm 2013-11-08 21:43:21 +00:00
cpu.h Implemented VCVTPS2PH AVX-512 instruction 2014-02-15 19:21:08 +00:00
cpuid.h added definitions (CPUID bit, VMX fields and VMXEXIT reasons, etc) from recently published Intel SDM rev049 2014-02-06 17:05:20 +00:00
crc32.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
crregs.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
crregs.h more avx-512 instructions implemented 2013-12-01 19:39:18 +00:00
ctrl_xfer16.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
ctrl_xfer32.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
ctrl_xfer64.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
ctrl_xfer_pro.cc - Do not compile support for alignment check (#AC exception) by default 2012-03-25 19:07:17 +00:00
data_xfer8.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
data_xfer16.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
data_xfer32.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
data_xfer64.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
debugstuff.cc fixed compilation error with vs2008 2013-10-25 05:36:10 +00:00
descriptor.h fixed 64-bit segment print from internal debugger 2012-06-14 18:56:47 +00:00
disasm.cc cover some more opcodes with compressed displ 2014-02-10 21:34:26 +00:00
event.cc update (c) for few files 2013-09-05 18:40:14 +00:00
exception.cc Added VMEXIT instrumentation callback 2013-10-23 21:18:19 +00:00
fetchdecode64.cc implementation of AVX-512 compressed displacement feature which is required for AVX-512 emu correctness (first step). todo: fix rest of EVEX opcodes 2014-02-10 21:12:08 +00:00
fetchdecode_avx.h implemented few more avx-512 cvt opcodes 2014-01-21 21:00:40 +00:00
fetchdecode_evex.h Implemented VCVTPS2PH AVX-512 instruction 2014-02-15 19:21:08 +00:00
fetchdecode_sse.h finish sse tables cleanup in disasm and fetchdecode 2013-10-11 20:09:51 +00:00
fetchdecode_x87.h disasm fixes 2013-10-07 19:02:53 +00:00
fetchdecode_xop.h Debugger: fixed param tree access to 64-bit variables (need to use get64() instead of get()) 2013-12-05 19:17:16 +00:00
fetchdecode.cc complete compressed displ feature support, bugfixes in AVX-512 code 2014-02-11 16:10:31 +00:00
fetchdecode.h cover some more opcodes with compressed displ 2014-02-10 21:34:26 +00:00
flag_ctrl_pro.cc Move INTR, Local APIC INTR and SVN VINTR into new event interface (hardest part) 2012-10-03 20:24:29 +00:00
flag_ctrl.cc Move INTR, Local APIC INTR and SVN VINTR into new event interface (hardest part) 2012-10-03 20:24:29 +00:00
fpu_emu.cc reword all the CPU code in preparation for future CPU speedup implementation. 2011-07-06 20:01:18 +00:00
gather.cc implemented few more AVX-512 floating point convert instructions 2014-01-18 20:10:05 +00:00
generic_cpuid.cc updates to AVX512 decoding and CPUID 2013-10-07 20:39:34 +00:00
generic_cpuid.h remove unused leafs from generic_cpuid 2012-05-11 06:51:04 +00:00
i387.h Adding Id and Rev property to all files 2011-02-24 21:54:04 +00:00
ia_opcodes.h Implemented VCVTPS2PH AVX-512 instruction 2014-02-15 19:21:08 +00:00
icache.cc fixes for disasm 2013-10-02 19:23:34 +00:00
icache.h Thanks to avanced trace linking 256K entries ICache is not needed anymore. 2013-06-29 10:25:56 +00:00
init.cc Debugger: fixed param tree access to 64-bit variables (need to use get64() instead of get()) 2013-12-05 19:17:16 +00:00
instr.h new function for disasm. todo: support it independently of CPU 2014-01-26 20:01:50 +00:00
io.cc updated + fixed instrumentation example for instr histogram, code cleanup in the cpu 2012-03-28 21:11:19 +00:00
iret.cc stack direct access optimization - 5% emu speedup to all 32-bit guests, for 64-bit guests speedup is less because they have less stack accesses 2012-03-25 11:54:32 +00:00
jmp_far.cc - Implemented Task Switch intercept in SVM, cleanup in task switch handling code 2012-01-11 20:21:29 +00:00
lazy_flags.h small optimization in lazy flags code 2012-09-06 19:49:14 +00:00
load.cc fixed bug in LOAD_BROADCAST_MASK_Half_VectorD method 2014-02-11 20:13:42 +00:00
logical8.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
logical16.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
logical32.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
logical64.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
Makefile.in do not compile AVX objects if AVX support is not enabled in configure 2014-01-26 19:20:44 +00:00
mmx.cc Implemented VPCMP* AVX512 instructions 2013-12-02 18:05:18 +00:00
msr.cc do not recognize MTRR MSRs when mtrr is not enabled 2013-04-17 19:59:56 +00:00
mult8.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
mult16.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
mult32.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
mult64.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
paging.cc move canonical check of high part of page split access to another function to fix code duplication 2013-12-21 21:56:55 +00:00
proc_ctrl.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
protect_ctrl.cc SVM: implemented missed RSM, LDTR READ/WRITE, TR READ/WRITE and IRET intercepts 2013-02-25 19:36:41 +00:00
rdrand.cc Add RDRAND/RDSEED instructions support (+ disasm) 2012-10-09 15:16:48 +00:00
resolver.cc Adding Id and Rev property to all files 2011-02-24 21:54:04 +00:00
ret_far.cc stack direct access optimization - 5% emu speedup to all 32-bit guests, for 64-bit guests speedup is less because they have less stack accesses 2012-03-25 11:54:32 +00:00
segment_ctrl_pro.cc - Do not compile support for alignment check (#AC exception) by default 2012-03-25 19:07:17 +00:00
segment_ctrl.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
sha.cc properly added sha.cc to the tree 2013-07-24 18:56:37 +00:00
shift8.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
shift16.cc fixed comments for SHLD/SHRD instructrions and make code a little more clear 2012-09-09 17:44:42 +00:00
shift32.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
shift64.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
simd_compare.h Implemented VPERMILPS/PD AVX512 instructions 2013-12-04 18:30:44 +00:00
simd_int.h fixed compilation err without avx 2014-01-23 17:08:30 +00:00
simd_pfp.h implemented avx-512 getexp instructions 2014-01-27 21:25:07 +00:00
smm.cc implementation of virtual NMI 2013-03-05 21:12:43 +00:00
smm.h Fixed SF bug [3548109] VMX State Not Restored After Entering SMM on 32-bit Systems 2012-07-27 08:13:39 +00:00
soft_int.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
sse_move.cc Implemented VPCMP* AVX512 instructions 2013-12-02 18:05:18 +00:00
sse_pfp.cc implemented AVX-512 version of VCVTPH2PS 2014-02-04 20:32:54 +00:00
sse_rcp.cc implemented VFIXUPIMM AVX-512 opcodes 2013-12-17 16:44:46 +00:00
sse_string.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
sse.cc make use of new accessor 2013-12-01 22:21:55 +00:00
stack16.cc small optimization 2014-02-01 19:23:41 +00:00
stack32.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
stack64.cc Infrstructure change to support disasm of BxInstruction_c directly (without calling disasm) 2013-09-24 05:21:00 +00:00
stack.cc properly added sha.cc to the tree 2013-07-24 18:56:37 +00:00
stack.h stack direct access optimization - 5% emu speedup to all 32-bit guests, for 64-bit guests speedup is less because they have less stack accesses 2012-03-25 11:54:32 +00:00
string.cc fixes for disasm 2013-10-15 17:19:18 +00:00
svm.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
svm.h updates in CPUID defines after new published AMD SDM 2013-05-17 19:41:57 +00:00
tasking.cc hw task switch tempdr6 hanlding fix 2013-03-15 08:26:22 +00:00
tbm32.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
tbm64.cc Standartization of Bochs instruction handlers. 2012-08-05 13:52:40 +00:00
todo added masked operations to simd_pfp.h, optimize simd_int.h, rewrite dpps instr using new masked op from simd_pfp.h 2013-09-17 20:49:26 +00:00
vapic.cc fixed compilation issue 2012-11-05 06:41:10 +00:00
vm8086.cc - Do not compile support for alignment check (#AC exception) by default 2012-03-25 19:07:17 +00:00
vmcs.cc rename some VMX controls to match intel docs. added missed VMX consistency check 2013-02-24 20:22:22 +00:00
vmexit.cc use shorter opcode names in the debug prints (skip the BX_IA_ prefix) 2013-12-02 20:06:59 +00:00
vmfunc.cc implemented virtualization exception feature 2013-01-28 16:30:25 +00:00
vmx.cc downgrade VMEXIT message to BX_DEBUG 2014-01-24 18:58:57 +00:00
vmx.h moved (c) to year 2014 for few files 2014-02-06 17:06:25 +00:00
xmm.h complete compressed displ feature support, bugfixes in AVX-512 code 2014-02-11 16:10:31 +00:00
xop.cc implemented few more AVX-512 floating point convert instructions 2014-01-18 20:10:05 +00:00
xsave.cc Implemented last missed AVX-512 unsigned convert instructions 2014-01-28 12:57:38 +00:00