summaryrefslogtreecommitdiff
path: root/src/arch/x86/isa
AgeCommit message (Collapse)Author
2007-10-02X86: Distinguish between the rep and repe prefixes.Gabe Black
STOS and MOVS only accept the rep prefix which always loops until rcx becomes 0. The other string instructions accept repe (same encoding as rep) and repne which also check the condition code flags each iteration. --HG-- extra : convert_revision : 544149f640302070810fb53e53bfeb0e87160ffc
2007-10-02X86: Fix places where movfp was used incorrectly.Gabe Black
--HG-- extra : convert_revision : a6b5688eaa53d2f6675df1be193726641e558d37
2007-10-02X86: Fix the movfp microop.Gabe Black
--HG-- extra : convert_revision : 23829782a2802a97a05e4dfdb5dd38fbe4165a90
2007-10-02X86: Fix x87 floating point stack register indexing.Gabe Black
--HG-- extra : convert_revision : b515ec20cbfc50b38aa7da6cf4d465acf9054c08
2007-10-02X86: Put ldst into the microcode (the earlier changeset didn't really).Gabe Black
Also clean things up as much as possible so that faulting won't break an instruction. More microops which verify addresses are needed. --HG-- extra : convert_revision : 7c6050cb4798d287fe7d3cc4bb8c20dfa40ad2be
2007-10-02X86: Implement the ldst microop and put it in existing microcode where ↵Gabe Black
appropriate. --HG-- extra : convert_revision : f08bd725d07a501bb7a0ce91590b5d37db99c6f3
2007-10-02X86: Fix up the microcode for the FST and FSTP instructions.Gabe Black
--HG-- extra : convert_revision : ad68633e9b7eab425593acb20cf242bf98c2b642
2007-10-02X86: Get rid of a hack for ruflag which is no longer necessary.Gabe Black
--HG-- extra : convert_revision : 1bb60c9ddb483aead2af0201bbda938cc6d3f7cb
2007-10-02X86: Allow logic instructions to set ECF as well as CF.Gabe Black
--HG-- extra : convert_revision : 6ac20f069c86c23a8d443a7127afd6015166c00d
2007-10-02X86: Add classes for the actual x86 faults.Gabe Black
--HG-- extra : convert_revision : bc060a01b5415551b335ca68ccbf126333ae20b0
2007-10-02X86: Hook in another version of the XCHG instruction.Gabe Black
--HG-- extra : convert_revision : 7b6f9cd2f59443622f6963dfee454175322c0ef5
2007-10-02X86: Implement MOVSGabe Black
--HG-- extra : convert_revision : 29147e1b86f7c54ce9b5ff68001725802c665fc0
2007-10-02X86: Implement STOS.Gabe Black
--HG-- extra : convert_revision : 95f3bf185f07fe644d6ab96bbb6e598e406b92f4
2007-09-19X86: Implement the fld, fst, and fstp instructions.Gabe Black
--HG-- extra : convert_revision : 7dd274bdc3c34839c17d9012a745d7c95dfcfdd8
2007-09-19X86: Move the fp microops to their own file with their own base classes in ↵Gabe Black
C++ and python. --HG-- extra : convert_revision : 9cd223f2005adb36fea2bb56fa39793a58ec958c
2007-09-19X86: Put in the foundation for x87 stack based fp registers.Gabe Black
--HG-- extra : convert_revision : 940f92efd4a9dc59106e991cc6d9836861ab69de
2007-09-19X86: Put in stubs for x87, 64 bit and 128 bit SIMD instruction microcode.Gabe Black
--HG-- rename : src/arch/x86/isa/insts/sse/__init__.py => src/arch/x86/isa/insts/simd128/__init__.py extra : convert_revision : efb4405aebaa4a04f33572e7d078ceca45872d9c
2007-09-13X86: Fix how ECF is computed in genFlags, and get rid of some duplicate code.Gabe Black
--HG-- extra : convert_revision : f86330a5a9fea782ee63aaa18ca964fb6f9cef0b
2007-09-13X86: Make the shift and rotate instructions set the carry flag(s) and ↵Gabe Black
overflow flags like they're supposed to. --HG-- extra : convert_revision : c0523a5bbf53375ce979ca7d98a95e465be66fbe
2007-09-13X86: Total overhaul of the division instructions and microops.Gabe Black
--HG-- extra : convert_revision : 303ea45f69f7805361ad877fe6bb43fbc3dfd7a6
2007-09-10X86: Move a comment to be next to the code it describes.Gabe Black
--HG-- extra : convert_revision : c384391175babb7cfdd3885ae9d9f1a9405ea44f
2007-09-06X86: Rework the multiplication microops so that they work like they would in ↵Gabe Black
the patent. --HG-- extra : convert_revision : 6fcf5dee440288d8bf92f6c5c2f97ef019975536
2007-09-06X86: Make signed multiplication do something different from unsigned.Gabe Black
--HG-- extra : convert_revision : 333c4a3464d708d4d8cea88931259ab96c2f75ed
2007-09-06X86: Make signed versions of partial register values available to microops.Gabe Black
--HG-- extra : convert_revision : c820d1250f505911a341ced42d4f73796ea77f87
2007-09-06X86: Correct how the hi portion of a product is computed.Gabe Black
--HG-- extra : convert_revision : 1f503e1cae0374e62e6254e8073e903adc29d067
2007-09-06X86: Add a square root microop and the SSE sqrt instruction.Gabe Black
--HG-- extra : convert_revision : ddc6e7e95111189d43f75bf84cd3d82433d982b3
2007-09-06X86: Add SSE comparison instructions and microops and move some FP microops ↵Gabe Black
to be with the other ones. --HG-- extra : convert_revision : ee0b5acde08d12c51a5282efb58d1ac72e0779af
2007-09-04X86: Implement an SSE xor microop and instruction.Gabe Black
--HG-- extra : convert_revision : 949737d0f5d6fe4aa77cc4680d0c88caab3e8174
2007-09-04X86: Make the movfp microop use FloatRegBits instead of FloatRegs.Gabe Black
This fixes a problem where interpreting arbitrary bits as floating point would change what the value was. These values are legitimate because the fp registers could be used to move around arbitrary data. --HG-- extra : convert_revision : f1d7159ba137702b5722cc7c1b64ed7dd06c21de
2007-09-04X86: Hook in the fp arithmetic instructions. Stale python made it work before.Gabe Black
--HG-- extra : convert_revision : af27f26ae810ebaae13faa572c5b4eb074620d91
2007-09-04X86: Implement some SSE fp microops and instructions.Gabe Black
--HG-- extra : convert_revision : 7e0595ef542fbfb701bfac7e9ac4648349a92b26
2007-09-04X86: Add some SSE floating point/integer conversion microops.Gabe Black
--HG-- extra : convert_revision : 2a1aa16709db940f5f40bbd84ca082f26b03b9c5
2007-09-04X86: Add floating point micro registers.Gabe Black
--HG-- extra : convert_revision : 442a5f8b9216638e4e6898f89eacb8695719e20f
2007-09-04X86: Fix a typo in the microassembly for the cqo instruction.Gabe Black
--HG-- extra : convert_revision : ddf739e591e4414ade37b806a88f3c11292627e2
2007-09-04X86: Implement idiv and propogate the mul corner case fix.Gabe Black
--HG-- extra : convert_revision : 348aa081067728afa14dc5b609fc7e26dbc5fad5
2007-09-04X86: Fix a corner case where mul would overwrite an original register value ↵Gabe Black
it still needed. --HG-- extra : convert_revision : 86ee0e2bf716d52c34ee731727d6366935f103ed
2007-08-31X86: Major rework of how regop microops are generated.Gabe Black
The new implementation uses metaclass, and gives a lot more precise control with a lot less verbosity. The flags/no flags reg/imm variants are all handled by the same python class now which supplies a constructor to the right C++ class based on context. --HG-- extra : convert_revision : 712e3ec6de7a5a038da083f79635fd7a687d56e5
2007-08-29X86: Fix the sra microop to get the sign bit from the right operand.Gabe Black
--HG-- extra : convert_revision : 71e58dd6dd6918ee403f2e332c47e29acdace464
2007-08-29X86: Implement the movaps instruction.Gabe Black
--HG-- extra : convert_revision : 2aeb1c05205f8ea8f7484e8bacf3fbbc581defd2
2007-08-29X86: Implement the movsd instruction.Gabe Black
--HG-- extra : convert_revision : a5a73e0ddd39144d2aeeb9cc6a299516752fd4c2
2007-08-29X86: Implement the movlpd instruction.Gabe Black
--HG-- extra : convert_revision : dddb20fe48c0ae9de7cd0ba1a1467ecb690056c1
2007-08-29X86: Add an fp move microop.Gabe Black
--HG-- extra : convert_revision : a9d6d3568cd2c6a65df91bf56ee1e43523f04630
2007-08-29X86: Add load and store microops that use the fp registers.Gabe Black
--HG-- extra : convert_revision : 153a055e888d8c47d59758a599dbd38f63008137
2007-08-29X86: Add operands to handle floating point registers.Gabe Black
--HG-- extra : convert_revision : 2e8289dbd3f5dda1221014d4ed0e9450f60de0cf
2007-08-29X86: Flesh out register indexing constants.Gabe Black
--HG-- extra : convert_revision : 56eedc076bbb7962c3976599a15ed93c7cb154c0
2007-08-28X86: More two byte opcode decoding. I missed two groups in the last changeset.Gabe Black
--HG-- extra : convert_revision : 1a2813b2e7d3e0e02c8f1474f372de5cf16e7d7b
2007-08-28X86: More fully decode two byte opcodes.Gabe Black
This includes the most of the SSE stuff, but not some of the "groups" of instructions. --HG-- extra : convert_revision : 4725c34f3d73971ae1763611685c5877b6c51412
2007-08-26X86: Make the Ruflag microop work correctly, and make the code a little clearer.Gabe Black
--HG-- extra : convert_revision : c551f51cdda46df99370363ed2d70916db8413eb
2007-08-26X86: Return values for some cpuid functions that match what my development ↵Gabe Black
machine returns. --HG-- extra : convert_revision : e6619da11f43bbe025ceabd06387dd24e1cd883b
2007-08-26X86: Make the microassembler accept lines which are just labels.Gabe Black
The labels on these lines will be associated with whatever the next microop is. --HG-- extra : convert_revision : 80c260e48ec1c16e6325061608e37c95a0610cfa
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-01 13:02:31 +0000