mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-01-19 20:34:38 +00:00
1f996fa36b
This is equivalent to the AMDGPUTargetMachine now, but it is the starting point for separating R600 and GCN functionality into separate targets. It is recommened that users start using the gcn triple for GCN-based GPUs, because using the r600 triple for these GPUs will be deprecated in the future. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225277 91177308-0d34-0410-b5e6-96231b3b80d8
25 lines
776 B
LLVM
25 lines
776 B
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=tahiti -verify-machineinstrs | FileCheck %s
|
|
|
|
; CHECK: {{^}}fsqrt_f32:
|
|
; CHECK: v_sqrt_f32_e32 {{v[0-9]+, v[0-9]+}}
|
|
|
|
define void @fsqrt_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
|
|
%r0 = load float addrspace(1)* %in
|
|
%r1 = call float @llvm.sqrt.f32(float %r0)
|
|
store float %r1, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; CHECK: {{^}}fsqrt_f64:
|
|
; CHECK: v_sqrt_f64_e32 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\]}}
|
|
|
|
define void @fsqrt_f64(double addrspace(1)* %out, double addrspace(1)* %in) {
|
|
%r0 = load double addrspace(1)* %in
|
|
%r1 = call double @llvm.sqrt.f64(double %r0)
|
|
store double %r1, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.sqrt.f32(float %Val)
|
|
declare double @llvm.sqrt.f64(double %Val)
|