Displaying 2 results from an estimated 2 matches for "addssrr".
2013 Dec 05
3
[LLVMdev] X86 - Help on fixing a poor code generation bug
...or
X86ISD::INSERTPS depending on the target's SSE feature level.
To start I checked if this bug was caused simply by the lack of
specific tablegen patterns to match the complex sequence described
above into a single ADDSS instruction.
However X86InstrSSE.td already defines an instruction X86::ADDSSrr as
a commutative SSE scalar fp add instruction (that works on F32
ValueTypes). Instruction X86::ADDSSrr is used to select 'fadd' nodes
and it will be translated to 'addss' in assembly.
At this stage, the MOVSS/INSERTPS is still required since the ADDSS
alone would not be equivalent...
2013 Dec 05
0
[LLVMdev] X86 - Help on fixing a poor code generation bug
...on the target's SSE feature level.
>
> To start I checked if this bug was caused simply by the lack of
> specific tablegen patterns to match the complex sequence described
> above into a single ADDSS instruction.
>
> However X86InstrSSE.td already defines an instruction X86::ADDSSrr as
> a commutative SSE scalar fp add instruction (that works on F32
> ValueTypes). Instruction X86::ADDSSrr is used to select 'fadd' nodes
> and it will be translated to 'addss' in assembly.
>
> At this stage, the MOVSS/INSERTPS is still required since the ADDSS
>...