From: Tom Stellard <thomas.stellard@amd.com>
Date: Tue, 25 Jun 2013 02:39:25 +0000 (+0000)
Subject: R600/SI: Add support for v4i32 and v4f32 kernel args
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=fa57da12f7ce559d502a4319d39a1f0582f4d2b3;p=oota-llvm.git

R600/SI: Add support for v4i32 and v4f32 kernel args

Tested-By: Aaron Watry <awatry@gmail.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184820 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/R600/AMDGPUCallingConv.td b/lib/Target/R600/AMDGPUCallingConv.td
index 84e4f3a8a65..826932b3b84 100644
--- a/lib/Target/R600/AMDGPUCallingConv.td
+++ b/lib/Target/R600/AMDGPUCallingConv.td
@@ -38,10 +38,11 @@ def CC_SI : CallingConv<[
 
 // Calling convention for SI compute kernels
 def CC_SI_Kernel : CallingConv<[
-  CCIfType<[i64],      CCAssignToStack <8, 4>>,
-  CCIfType<[i32, f32], CCAssignToStack <4, 4>>,
-  CCIfType<[i16],      CCAssignToStack <2, 4>>,
-  CCIfType<[i8],       CCAssignToStack <1, 4>>
+  CCIfType<[v4i32, v4f32], CCAssignToStack <16, 4>>,
+  CCIfType<[i64],          CCAssignToStack < 8, 4>>,
+  CCIfType<[i32, f32],     CCAssignToStack < 4, 4>>,
+  CCIfType<[i16],          CCAssignToStack < 2, 4>>,
+  CCIfType<[i8],           CCAssignToStack < 1, 4>>
 ]>;
 
 def CC_AMDGPU : CallingConv<[
diff --git a/test/CodeGen/R600/128bit-kernel-args.ll b/test/CodeGen/R600/128bit-kernel-args.ll
index 114f9e74474..bd603854111 100644
--- a/test/CodeGen/R600/128bit-kernel-args.ll
+++ b/test/CodeGen/R600/128bit-kernel-args.ll
@@ -1,16 +1,20 @@
-;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
-
-; CHECK: @v4i32_kernel_arg
-; CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
+; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK
+; RUN: llc < %s -march=r600 -mcpu=SI | FileCheck %s --check-prefix=SI-CHECK
 
+; R600-CHECK: @v4i32_kernel_arg
+; R600-CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
+; SI-CHECK: @v4i32_kernel_arg
+; SI-CHECK: BUFFER_STORE_DWORDX4
 define void @v4i32_kernel_arg(<4 x i32> addrspace(1)* %out, <4 x i32>  %in) {
 entry:
   store <4 x i32> %in, <4 x i32> addrspace(1)* %out
   ret void
 }
 
-; CHECK: @v4f32_kernel_arg
-; CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
+; R600-CHECK: @v4f32_kernel_arg
+; R600-CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
+; SI-CHECK: @v4f32_kernel_arg
+; SI-CHECK: BUFFER_STORE_DWORDX4
 define void @v4f32_kernel_args(<4 x float> addrspace(1)* %out, <4 x float>  %in) {
 entry:
   store <4 x float> %in, <4 x float> addrspace(1)* %out