replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
hanchenye-llvm-project/llvm/test/CodeGen/AMDGPU/rcp_iflag.ll

22 lines
756 B
LLVM
Raw Normal View History

[AMDGPU] Convert rcp to rcp_iflag If a source of rcp instruction is a result of any conversion from an integer convert it into rcp_iflag instruction. No FP exception can ever happen except division by zero if a single precision rcp argument is a representation of an integral number. Differential Revision: https://reviews.llvm.org/D48569 llvm-svn: 335742
2018-06-27 23:33:33 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
; GCN-LABEL: {{^}}rcp_uint:
; GCN: v_rcp_iflag_f32_e32
define amdgpu_kernel void @rcp_uint(i32 addrspace(1)* %in, float addrspace(1)* %out) {
%load = load i32, i32 addrspace(1)* %in, align 4
%cvt = uitofp i32 %load to float
%div = fdiv float 1.000000e+00, %cvt
store float %div, float addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}rcp_sint:
; GCN: v_rcp_iflag_f32_e32
define amdgpu_kernel void @rcp_sint(i32 addrspace(1)* %in, float addrspace(1)* %out) {
%load = load i32, i32 addrspace(1)* %in, align 4
%cvt = sitofp i32 %load to float
%div = fdiv float 1.000000e+00, %cvt
store float %div, float addrspace(1)* %out, align 4
ret void
}