mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-06 05:06:45 +00:00
3e61ccdded
This makes the two intrinsics @llvm.convert.from.f16 and @llvm.convert.to.f16 accept types other than simple "float". This is only strictly needed for the truncate operation, since otherwise double rounding occurs and there's no way to represent the strict IEEE conversion. However, for symmetry we allow larger types in the extend too. During legalization, we can expand an "fp16_to_double" operation into two extends for convenience, but abort when the truncate isn't legal. A new libcall is probably needed here. Even after this commit, various target tweaks are needed to actually use the extended intrinsics. I've put these into separate commits for clarity, so there are no actual tests of f64 conversion here. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213248 91177308-0d34-0410-b5e6-96231b3b80d8
15 lines
630 B
LLVM
15 lines
630 B
LLVM
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
|
|
declare float @llvm.convert.from.fp16.f32(i16) nounwind readnone
|
|
|
|
; SI-LABEL: @test_convert_fp16_to_fp32:
|
|
; SI: BUFFER_LOAD_USHORT [[VAL:v[0-9]+]]
|
|
; SI: V_CVT_F32_F16_e32 [[RESULT:v[0-9]+]], [[VAL]]
|
|
; SI: BUFFER_STORE_DWORD [[RESULT]]
|
|
define void @test_convert_fp16_to_fp32(float addrspace(1)* noalias %out, i16 addrspace(1)* noalias %in) nounwind {
|
|
%val = load i16 addrspace(1)* %in, align 2
|
|
%cvt = call float @llvm.convert.from.fp16.f32(i16 %val) nounwind readnone
|
|
store float %cvt, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|