diff options
| author | Jan Beulich <jbeulich@suse.com> | 2024-06-28 08:22:39 +0200 |
|---|---|---|
| committer | Jan Beulich <jbeulich@suse.com> | 2024-06-28 08:22:39 +0200 |
| commit | 82e06fa803fd00c0640dd4b2078f829f832847fd (patch) | |
| tree | 06a6e2a5444425bb4dde267dba5be9cce1221dad /opcodes/i386-opc.tbl | |
| parent | 2a7f257afb4297394ea4239ed97c507d83220dd7 (diff) | |
| download | fsf-binutils-gdb-82e06fa803fd00c0640dd4b2078f829f832847fd.zip fsf-binutils-gdb-82e06fa803fd00c0640dd4b2078f829f832847fd.tar.gz fsf-binutils-gdb-82e06fa803fd00c0640dd4b2078f829f832847fd.tar.bz2 | |
x86/APX: optimize {nf}-form IMUL-by-power-of-2 to SHL
..., for differing only in the resulting EFLAGS, which are left
untouched anyway. That's a shorter encoding, available as long as
certain constraints on operands are met; see code comments. (SHL-by-1
forms may then be subject to further optimization that was introduced
earlier.)
Note that kind of as a side effect this also converts multiplication by
1 to shift by 0, which is a plain move or even no-op anyway. That could
be further shrunk (as could be presence of shifts/rotates by 0 in the
original code as well as a fair set of other {nf}-form insns), yet the
expectation (for now) is that people won't write such code in the first
place.
Diffstat (limited to 'opcodes/i386-opc.tbl')
| -rw-r--r-- | opcodes/i386-opc.tbl | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl index 934b456..42c52e4 100644 --- a/opcodes/i386-opc.tbl +++ b/opcodes/i386-opc.tbl @@ -419,21 +419,21 @@ imul, 0xfaf, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Reg16|Reg32|Reg64|U imul, 0xaf, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|EVexMap4|NF, { Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 } imul, 0x6b, i186, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 } imul, 0x6b, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|EVexMap4|NF|Optimize, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 } -imulzu, 0x6b, APX_F, Modrm|No_bSuf|No_sSuf|EVexMap4|NF|ZU, { Imm8S, Reg16|Unspecified|BaseIndex, Reg16 } +imulzu, 0x6b, APX_F, Modrm|No_bSuf|No_sSuf|EVexMap4|NF|ZU|Optimize, { Imm8S, Reg16|Unspecified|BaseIndex, Reg16 } imul, 0x69, i186, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 } -imul, 0x69, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|EVexMap4|NF, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 } -imulzu, 0x69, APX_F, Modrm|No_bSuf|No_sSuf|EVexMap4|NF|ZU, { Imm16, Reg16|Unspecified|BaseIndex, Reg16 } +imul, 0x69, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|EVexMap4|NF|Optimize, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 } +imulzu, 0x69, APX_F, Modrm|No_bSuf|No_sSuf|EVexMap4|NF|ZU|Optimize, { Imm16, Reg16|Unspecified|BaseIndex, Reg16 } // imul with 2 operands mimics imul with 3 by putting the register in // both i.rm.reg & i.rm.regmem fields. RegKludge enables this // transformation. imul, 0x6b, i186, Modrm|No_bSuf|No_sSuf|RegKludge, { Imm8S, Reg16|Reg32|Reg64 } imul, 0x6b, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF|Optimize, { Imm8S, Reg16|Reg32|Reg64 } imul, 0x69, i186, Modrm|No_bSuf|No_sSuf|RegKludge, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64 } -imul, 0x69, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64 } +imul, 0x69, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF|Optimize, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64 } // ZU is omitted here, for colliding with RegKludge. process_operands() will // replace the constraint value after processing RegKludge. -imulzu, 0x6b, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF/*|ZU*/, { Imm8S, Reg16 } -imulzu, 0x69, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF/*|ZU*/, { Imm16, Reg16 } +imulzu, 0x6b, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF/*|ZU*/|Optimize, { Imm8S, Reg16 } +imulzu, 0x69, APX_F, Modrm|No_bSuf|No_sSuf|RegKludge|EVexMap4|NF/*|ZU*/|Optimize, { Imm16, Reg16 } <mul> |