Create a gist now

Instantly share code, notes, and snippets.

// Generated by LLVM NVPTX Back-End
.version 3.0
.target sm_13, texmode_independent
.address_size 32
// .globl _ZN9add_float16_cb9e1b436595b333_00E
.func _ZN9add_float16_cb9e1b436595b333_00E(
.reg .b32 _ZN9add_float16_cb9e1b436595b333_00E_param_0,
.reg .b32 _ZN9add_float16_cb9e1b436595b333_00E_param_1,
.reg .b32 _ZN9add_float16_cb9e1b436595b333_00E_param_2,
.reg .b32 _ZN9add_float16_cb9e1b436595b333_00E_param_3,
.reg .b32 _ZN9add_float16_cb9e1b436595b333_00E_param_4
) // @_ZN9add_float16_cb9e1b436595b333_00E
.local .align 4 .b8 __local_depot0[12];
.reg .b32 %SP;
.reg .b32 %SPL;
.reg .pred %p<396>;
.reg .s16 %rc<396>;
.reg .s16 %rs<396>;
.reg .s32 %r<396>;
.reg .s64 %rl<396>;
.reg .f32 %f<396>;
.reg .f64 %fl<396>;
// BB#0: // %static_allocas
mov.u32 %SP, __local_depot0;
mov.b32 %r0, _ZN9add_float16_cb9e1b436595b333_00E_param_2;
mov.b32 %r1, _ZN9add_float16_cb9e1b436595b333_00E_param_3;
mov.b32 %r2, _ZN9add_float16_cb9e1b436595b333_00E_param_4; [%SP+0], %r0; [%SP+4], %r1; [%SP+8], %r2;
// inline asm
# *z = *x + *y; ( 3:16)
// inline asm %r0, [%SP+4]; %fl0, [%r0]; %r0, [%SP+0]; %fl1, [%r0];
add.f64 %fl0, %fl1, %fl0; %r0, [%SP+8]; [%r0], %fl0;
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment