Michael Liao e830fa260d [clang][amdgpu] Prefer not using fp16 conversion intrinsics.
Reviewers: yaxunl, arsenm

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, dstuttard, tpr, t-tye, kerbowa, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D81849
2020-06-16 10:21:56 -04:00

17 lines
369 B
Plaintext

// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -x hip -emit-llvm -fcuda-is-device -o - %s | FileCheck %s
#define __device__ __attribute__((device))
// CHECK-LABEL: @_Z2d0DF16_
// CHECK: fpext
__device__ float d0(_Float16 x) {
return x;
}
// CHECK-LABEL: @_Z2d1f
// CHECK: fptrunc
__device__ _Float16 d1(float x) {
return x;
}