Ruiling Song via llvm-dev
2016-Sep-09 12:56 UTC
[llvm-dev] how to allocate consecutive register?
Hi, The gpu target I am working on requires the 'value' and 'address' operands of memory store instruction in consecutive register. Anybody has suggestion? - Ruiling -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160909/e9d330bc/attachment.html>
Quentin Colombet via llvm-dev
2016-Sep-09 20:19 UTC
[llvm-dev] how to allocate consecutive register?
Hi Ruiling, Make the store instruction takes only one operand, a tuple register. You have examples of tuple registers in the ARM backend. Cheers, -Quentin> On Sep 9, 2016, at 5:56 AM, Ruiling Song via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Hi, > > The gpu target I am working on requires the 'value' and 'address' operands of memory store instruction in consecutive register. Anybody has suggestion? > > - Ruiling > _______________________________________________ > LLVM Developers mailing list > llvm-dev at lists.llvm.org > http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
Bruce Hoult via llvm-dev
2016-Sep-09 20:23 UTC
[llvm-dev] how to allocate consecutive register?
There are other CPUs with similar restrictions. You could look at how they handle it. An example which springs to mind is ARM A32 LDRD and STRD (load/store two consecutive registers). I think some other architectures do the same for operations which return two results, such as div/mod or NxN->2N multiply. On Fri, Sep 9, 2016 at 3:56 PM, Ruiling Song via llvm-dev < llvm-dev at lists.llvm.org> wrote:> Hi, > > The gpu target I am working on requires the 'value' and 'address' > operands of memory store instruction in consecutive register. Anybody has > suggestion? > > - Ruiling > > _______________________________________________ > LLVM Developers mailing list > llvm-dev at lists.llvm.org > http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev > >-------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160909/4434d431/attachment.html>
Tim Northover via llvm-dev
2016-Sep-11 06:50 UTC
[llvm-dev] how to allocate consecutive register?
On 9 September 2016 at 21:19, Quentin Colombet via llvm-dev <llvm-dev at lists.llvm.org> wrote:> Make the store instruction takes only one operand, a tuple register. > You have examples of tuple registers in the ARM backend.The difficult bit will be if there are loads with the same property. I don't think you can easily encode the fact that one half of a register is read and the other written. Tim.
Apparently Analagous Threads
- [LLVMdev] Use of 'ldrd' instructions with unaligned addresses on armv7 (Major bug in LLVM optimizer?)
- [LLVMdev] Use of 'ldrd' instructions with unaligned addresses on armv7 (Major bug in LLVM optimizer?)
- [LLVMdev] Use of 'ldrd' instructions with unaligned addresses on armv7 (Major bug in LLVM optimizer?)
- [LLVMdev] Problems with 64-bit register operands of inline asm on ARM
- [LLVMdev] Problems with 64-bit register operands of inline asm on ARM