From 3ab0ba3cd8a499ebcc7eda3d7585c5ab4e7f0711 Mon Sep 17 00:00:00 2001
From: Vincent Lejeune <vljn@ovi.com>
Date: Thu, 14 Mar 2013 15:50:45 +0000
Subject: R600: Factorize code handling Const Read Port limitation

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177078 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/R600/kcache-fold.ll | 52 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 2 deletions(-)

(limited to 'test/CodeGen/R600')

diff --git a/test/CodeGen/R600/kcache-fold.ll b/test/CodeGen/R600/kcache-fold.ll
index 82fb925c0d..e8e2bf5f0f 100644
--- a/test/CodeGen/R600/kcache-fold.ll
+++ b/test/CodeGen/R600/kcache-fold.ll
@@ -1,8 +1,8 @@
 ;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
 
+; CHECK: @main1
 ; CHECK: MOV T{{[0-9]+\.[XYZW], CBuf0\[[0-9]+\]\.[XYZW]}}
-
-define void @main() {
+define void @main1() {
 main_body:
   %0 = load <4 x float> addrspace(8)* null
   %1 = extractelement <4 x float> %0, i32 0
@@ -48,5 +48,53 @@ main_body:
   ret void
 }
 
+; CHECK: @main2
+; CHECK-NOT: MOV
+define void @main2() {
+main_body:
+  %0 = load <4 x float> addrspace(8)* null
+  %1 = extractelement <4 x float> %0, i32 0
+  %2 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+  %3 = extractelement <4 x float> %2, i32 0
+  %4 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+  %5 = extractelement <4 x float> %4, i32 1
+  %6 = fcmp ult float %1, 0.000000e+00
+  %7 = select i1 %6, float %3, float %5
+  %8 = load <4 x float> addrspace(8)* null
+  %9 = extractelement <4 x float> %8, i32 1
+  %10 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+  %11 = extractelement <4 x float> %10, i32 0
+  %12 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+  %13 = extractelement <4 x float> %12, i32 1
+  %14 = fcmp ult float %9, 0.000000e+00
+  %15 = select i1 %14, float %11, float %13
+  %16 = load <4 x float> addrspace(8)* null
+  %17 = extractelement <4 x float> %16, i32 2
+  %18 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+  %19 = extractelement <4 x float> %18, i32 3
+  %20 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+  %21 = extractelement <4 x float> %20, i32 2
+  %22 = fcmp ult float %17, 0.000000e+00
+  %23 = select i1 %22, float %19, float %21
+  %24 = load <4 x float> addrspace(8)* null
+  %25 = extractelement <4 x float> %24, i32 3
+  %26 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+  %27 = extractelement <4 x float> %26, i32 3
+  %28 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+  %29 = extractelement <4 x float> %28, i32 2
+  %30 = fcmp ult float %25, 0.000000e+00
+  %31 = select i1 %30, float %27, float %29
+  %32 = call float @llvm.AMDIL.clamp.(float %7, float 0.000000e+00, float 1.000000e+00)
+  %33 = call float @llvm.AMDIL.clamp.(float %15, float 0.000000e+00, float 1.000000e+00)
+  %34 = call float @llvm.AMDIL.clamp.(float %23, float 0.000000e+00, float 1.000000e+00)
+  %35 = call float @llvm.AMDIL.clamp.(float %31, float 0.000000e+00, float 1.000000e+00)
+  %36 = insertelement <4 x float> undef, float %32, i32 0
+  %37 = insertelement <4 x float> %36, float %33, i32 1
+  %38 = insertelement <4 x float> %37, float %34, i32 2
+  %39 = insertelement <4 x float> %38, float %35, i32 3
+  call void @llvm.R600.store.swizzle(<4 x float> %39, i32 0, i32 0)
+  ret void
+}
+
 declare float @llvm.AMDIL.clamp.(float, float, float) readnone
 declare void @llvm.R600.store.swizzle(<4 x float>, i32, i32)
-- 
cgit v1.2.3-18-g5258