R600: Add 64-bit float load/store support
* Added R600_Reg64 class
* Added T#Index#.XY registers definition
* Added v2i32 register reads from parameter and global space
* Added f32 and i32 elements extraction from v2f32 and v2i32
* Added v2i32 -> v2f32 conversions
Tom Stellard:
- Mark vec2 operations as expand. The addition of a vec2 register
class made them all legal.
Patch by: Dmitry Cherkassov
Signed-off-by: Dmitry Cherkassov <dcherkassov@gmail.com>
llvm-svn: 187582
diff --git a/llvm/test/CodeGen/R600/64bit-kernel-args.ll b/llvm/test/CodeGen/R600/64bit-kernel-args.ll
index 3ad0e2a..34a0a87 100644
--- a/llvm/test/CodeGen/R600/64bit-kernel-args.ll
+++ b/llvm/test/CodeGen/R600/64bit-kernel-args.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=r600 -mcpu=tahiti | FileCheck %s
+; RUN: llc < %s -march=r600 -mcpu=tahiti | FileCheck %s --check-prefix=SI-CHECK
; SI-CHECK: @f64_kernel_arg
; SI-CHECK-DAG: S_LOAD_DWORDX2 SGPR{{[0-9]}}_SGPR{{[0-9]}}, SGPR0_SGPR1, 9