Displaying 2 results from an estimated 2 matches for "__internal_dsmul_param_0".
Did you mean:
__internal_dsmul_param_1
2012 Jul 11
2
[LLVMdev] [NVPTX] llc -march=nvptx64 -mcpu=sm_20 generates invalid zero align for device function params
...mul.rn.f(float, float) nounwind readnone
> llc -march=nvptx64 -mcpu=sm_20 test.ll -o test.ptx
> cat test.ptx
//
// Generated by LLVM NVPTX Back-End
//
.version 3.0
.target sm_20, texmode_independent
.address_size 64
// .globl __internal_dsmul
.func __internal_dsmul(
.param .b64 __internal_dsmul_param_0,
.param .align 0 .b8 __internal_dsmul_param_1[8],
.param .align 0 .b8 __internal_dsmul_param_2[8]
) // @__internal_dsmul
{
.reg .pred %p<396>;
.reg .s16 %rc<396>;
.reg .s16 %rs<396>;
.reg .s32 %r<396>;
.reg .s...
2012 Nov 09
0
[LLVMdev] [NVPTX] llc -march=nvptx64 -mcpu=sm_20 generates invalid zero align for device function params
...mit? Do you think it needs a test case?
Thanks,
- D.
dmikushin at hp2:~/forge/align0> llc -march=nvptx64 -mcpu=sm_20 align0.ll -o -
//
// Generated by LLVM NVPTX Back-End
//
.version 3.1
.target sm_20
.address_size 64
// .globl __internal_dsmul
.visible .func __internal_dsmul(
.param .b64 __internal_dsmul_param_0,
.param .align 4 .b8 __internal_dsmul_param_1[8],
.param .align 4 .b8 __internal_dsmul_param_2[8]
) // @__internal_dsmul
{
.reg .pred %p<396>;
.reg .s16 %rc<396>;
.reg .s16 %rs<396>;
.reg .s32 %r<396>;
.reg .s64 %rl<396>;
....