[PATCH] D46871: [AMDGPU] Add interpolation builtins

[Matt Arsenault via Phabricator via cfe-commits]

arsenm added inline comments.


================
Comment at: test/CodeGenOpenCL/builtins-amdgcn-interp.cl:2-28
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -o - %s | FileCheck %s --check-prefixes=CHECK,GFX9,BANK32
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu fiji -S -o - %s | FileCheck %s --check-prefixes=CHECK,GFX8,BANK32
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx810 -S -o - %s | FileCheck %s --check-prefixes=CHECK,GFX8,BANK16
+
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+
+// CHECK-LABEL: test_interp_f16
----------------
These should be emitting / checking the IR, not the output asm


Repository:
  rC Clang

https://reviews.llvm.org/D46871