Update aosp/master llvm for rebase to r233350

Change-Id: I07d935f8793ee8ec6b7da003f6483046594bca49

142 files changed, 555 insertions, 496 deletions

diff --git a/test/ExecutionEngine/MCJIT/2002-12-16-ArgTest.ll b/test/ExecutionEngine/MCJIT/2002-12-16-ArgTest.ll
index eb2fe8c..1ddc5ce 100644
--- a/test/ExecutionEngine/MCJIT/2002-12-16-ArgTest.ll
+++ b/test/ExecutionEngine/MCJIT/2002-12-16-ArgTest.ll
@@ -13,7 +13,7 @@ declare i32 @printf(i8*, ...)
 
 define i32 @main(i32 %argc, i8** %argv) {
 bb0:
-	call i32 (i8*, ...)* @printf( i8* getelementptr ([10 x i8]* @.LC0, i64 0, i64 0), i32 %argc )		; <i32>:0 [#uses=0]
+	call i32 (i8*, ...)* @printf( i8* getelementptr ([10 x i8], [10 x i8]* @.LC0, i64 0, i64 0), i32 %argc )		; <i32>:0 [#uses=0]
 	%cast224 = bitcast i8** %argv to i8*		; <i8*> [#uses=1]
 	%local = alloca i8*		; <i8**> [#uses=3]
 	store i8* %cast224, i8** %local
@@ -24,9 +24,9 @@ bb2:		; preds = %bb2, %bb0
 	%add1-indvar = add i32 %cann-indvar, 1		; <i32> [#uses=2]
 	%cann-indvar-idxcast = sext i32 %cann-indvar to i64		; <i64> [#uses=1]
 	%CT = bitcast i8** %local to i8***		; <i8***> [#uses=1]
-	%reg115 = load i8*** %CT		; <i8**> [#uses=1]
-	%cast235 = getelementptr i8** %reg115, i64 %cann-indvar-idxcast		; <i8**> [#uses=1]
-	%reg117 = load i8** %cast235		; <i8*> [#uses=1]
+	%reg115 = load i8**, i8*** %CT		; <i8**> [#uses=1]
+	%cast235 = getelementptr i8*, i8** %reg115, i64 %cann-indvar-idxcast		; <i8**> [#uses=1]
+	%reg117 = load i8*, i8** %cast235		; <i8*> [#uses=1]
 	%reg236 = call i32 @puts( i8* %reg117 )		; <i32> [#uses=0]
 	%cond239 = icmp slt i32 %add1-indvar, %argc		; <i1> [#uses=1]
 	br i1 %cond239, label %bb2, label %bb3
diff --git a/test/ExecutionEngine/MCJIT/2003-05-06-LivenessClobber.ll b/test/ExecutionEngine/MCJIT/2003-05-06-LivenessClobber.ll
index 576ef7c..d714bf7 100644
--- a/test/ExecutionEngine/MCJIT/2003-05-06-LivenessClobber.ll
+++ b/test/ExecutionEngine/MCJIT/2003-05-06-LivenessClobber.ll
@@ -5,7 +5,7 @@
 @test = global i64 0		; <i64*> [#uses=1]
 
 define internal i64 @test.upgrd.1() {
-	%tmp.0 = load i64* @test		; <i64> [#uses=1]
+	%tmp.0 = load i64, i64* @test		; <i64> [#uses=1]
 	%tmp.1 = add i64 %tmp.0, 1		; <i64> [#uses=1]
 	ret i64 %tmp.1
 }
diff --git a/test/ExecutionEngine/MCJIT/2003-05-07-ArgumentTest.ll b/test/ExecutionEngine/MCJIT/2003-05-07-ArgumentTest.ll
index 42db5fe..0538201 100644
--- a/test/ExecutionEngine/MCJIT/2003-05-07-ArgumentTest.ll
+++ b/test/ExecutionEngine/MCJIT/2003-05-07-ArgumentTest.ll
@@ -3,8 +3,8 @@
 declare i32 @puts(i8*)
 
 define i32 @main(i32 %argc.1, i8** %argv.1) {
-	%tmp.5 = getelementptr i8** %argv.1, i64 1		; <i8**> [#uses=1]
-	%tmp.6 = load i8** %tmp.5		; <i8*> [#uses=1]
+	%tmp.5 = getelementptr i8*, i8** %argv.1, i64 1		; <i8**> [#uses=1]
+	%tmp.6 = load i8*, i8** %tmp.5		; <i8*> [#uses=1]
 	%tmp.0 = call i32 @puts( i8* %tmp.6 )		; <i32> [#uses=0]
 	ret i32 0
 }
diff --git a/test/ExecutionEngine/MCJIT/2003-08-21-EnvironmentTest.ll b/test/ExecutionEngine/MCJIT/2003-08-21-EnvironmentTest.ll
index 63303fc..e2c52b4 100644
--- a/test/ExecutionEngine/MCJIT/2003-08-21-EnvironmentTest.ll
+++ b/test/ExecutionEngine/MCJIT/2003-08-21-EnvironmentTest.ll
@@ -12,7 +12,7 @@
 declare i32 @strlen(i8*)
 
 define i32 @main(i32 %argc.1, i8** %argv.1, i8** %envp.1) {
-	%tmp.2 = load i8** %envp.1		; <i8*> [#uses=1]
+	%tmp.2 = load i8*, i8** %envp.1		; <i8*> [#uses=1]
 	%tmp.3 = call i32 @strlen( i8* %tmp.2 )		; <i32> [#uses=1]
 	%T = icmp eq i32 %tmp.3, 0		; <i1> [#uses=1]
 	%R = zext i1 %T to i32		; <i32> [#uses=1]
diff --git a/test/ExecutionEngine/MCJIT/2007-12-10-APIntLoadStore.ll b/test/ExecutionEngine/MCJIT/2007-12-10-APIntLoadStore.ll
index 4183611..d557f57 100644
--- a/test/ExecutionEngine/MCJIT/2007-12-10-APIntLoadStore.ll
+++ b/test/ExecutionEngine/MCJIT/2007-12-10-APIntLoadStore.ll
@@ -9,11 +9,11 @@ entry:
     %"alloca point" = bitcast i32 0 to i32      ; <i32> [#uses=0]
     store i75 999, i75* %x, align 16
     store i32 0, i32* %tmp, align 4
-    %tmp1 = load i32* %tmp, align 4     ; <i32> [#uses=1]
+    %tmp1 = load i32, i32* %tmp, align 4     ; <i32> [#uses=1]
     store i32 %tmp1, i32* %retval, align 4
     br label %return
 
 return:     ; preds = %entry
-    %retval2 = load i32* %retval        ; <i32> [#uses=1]
+    %retval2 = load i32, i32* %retval        ; <i32> [#uses=1]
     ret i32 %retval2
 }
diff --git a/test/ExecutionEngine/MCJIT/2008-06-05-APInt-OverAShr.ll b/test/ExecutionEngine/MCJIT/2008-06-05-APInt-OverAShr.ll
index 349db69..4e4ad2a 100644
--- a/test/ExecutionEngine/MCJIT/2008-06-05-APInt-OverAShr.ll
+++ b/test/ExecutionEngine/MCJIT/2008-06-05-APInt-OverAShr.ll
@@ -12,15 +12,15 @@ entry:
 	%tmp = alloca i65		; <i65*> [#uses=2]
 	%"alloca point" = bitcast i65 0 to i65		; <i65> [#uses=0]
 	store i65 %x, i65* %x_addr
-	%tmp1 = load i65* %x_addr, align 4		; <i65> [#uses=1]
+	%tmp1 = load i65, i65* %x_addr, align 4		; <i65> [#uses=1]
 	%tmp2 = ashr i65 %tmp1, 65		; <i65> [#uses=1]
 	store i65 %tmp2, i65* %tmp, align 4
-	%tmp3 = load i65* %tmp, align 4		; <i65> [#uses=1]
+	%tmp3 = load i65, i65* %tmp, align 4		; <i65> [#uses=1]
 	store i65 %tmp3, i65* %retval, align 4
 	br label %return
 
 return:		; preds = %entry
-	%retval4 = load i65* %retval		; <i65> [#uses=1]
+	%retval4 = load i65, i65* %retval		; <i65> [#uses=1]
 	ret i65 %retval4
 }
 
@@ -46,14 +46,14 @@ cond_false:		; preds = %entry
 	br label %cond_next
 
 cond_next:		; preds = %cond_false, %cond_true
-	%tmp5 = getelementptr [10 x i8]* @.str, i32 0, i32 0		; <i8*> [#uses=1]
-	%tmp6 = load i32* %iftmp.0, align 4		; <i32> [#uses=1]
+	%tmp5 = getelementptr [10 x i8], [10 x i8]* @.str, i32 0, i32 0		; <i8*> [#uses=1]
+	%tmp6 = load i32, i32* %iftmp.0, align 4		; <i32> [#uses=1]
 	%tmp7 = call i32 (i8*, ...)* @printf( i8* noalias  %tmp5, i32 %tmp6 ) nounwind 		; <i32> [#uses=0]
 	br label %return
 
 return:		; preds = %cond_next
     store i32 0, i32* %retval, align 4
-	%retval8 = load i32* %retval		; <i32> [#uses=1]
+	%retval8 = load i32, i32* %retval		; <i32> [#uses=1]
 	ret i32 %retval8
 }
 
diff --git a/test/ExecutionEngine/MCJIT/2013-04-04-RelocAddend.ll b/test/ExecutionEngine/MCJIT/2013-04-04-RelocAddend.ll
index d9ff347..631cb2f 100644
--- a/test/ExecutionEngine/MCJIT/2013-04-04-RelocAddend.ll
+++ b/test/ExecutionEngine/MCJIT/2013-04-04-RelocAddend.ll
@@ -14,12 +14,12 @@
 ; 
 
 @test = global [2 x i32] [i32 -1, i32 0], align 4
-@p = global i32* getelementptr inbounds ([2 x i32]* @test, i64 0, i64 1), align 8
+@p = global i32* getelementptr inbounds ([2 x i32], [2 x i32]* @test, i64 0, i64 1), align 8
 
 define i32 @main() {
 entry:
-  %0 = load i32** @p, align 8
-  %1 = load i32* %0, align 4
+  %0 = load i32*, i32** @p, align 8
+  %1 = load i32, i32* %0, align 4
   ret i32 %1
 }
 
diff --git a/test/ExecutionEngine/MCJIT/fpbitcast.ll b/test/ExecutionEngine/MCJIT/fpbitcast.ll
index e6d06f8..bd7beb8 100644
--- a/test/ExecutionEngine/MCJIT/fpbitcast.ll
+++ b/test/ExecutionEngine/MCJIT/fpbitcast.ll
@@ -12,7 +12,7 @@ entry:
 define i32 @main()
 {
        %res = call i32 @test(double 3.14)
-       %ptr = getelementptr [4 x i8]* @format, i32 0, i32 0
+       %ptr = getelementptr [4 x i8], [4 x i8]* @format, i32 0, i32 0
        call i32 (i8*,...)* @printf(i8* %ptr, i32 %res)
        ret i32 0
 }
diff --git a/test/ExecutionEngine/MCJIT/hello-sm-pic.ll b/test/ExecutionEngine/MCJIT/hello-sm-pic.ll
index 7db60f7..4843f4e 100644
--- a/test/ExecutionEngine/MCJIT/hello-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/hello-sm-pic.ll
@@ -6,7 +6,7 @@
 declare i32 @puts(i8*)
 
 define i32 @main() {
-	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
+	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8], [12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
 	ret i32 0
 }
 
diff --git a/test/ExecutionEngine/MCJIT/hello.ll b/test/ExecutionEngine/MCJIT/hello.ll
index 47e36a5..516f57a 100644
--- a/test/ExecutionEngine/MCJIT/hello.ll
+++ b/test/ExecutionEngine/MCJIT/hello.ll
@@ -5,7 +5,7 @@
 declare i32 @puts(i8*)
 
 define i32 @main() {
-	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
+	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8], [12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
 	ret i32 0
 }
 
diff --git a/test/ExecutionEngine/MCJIT/pr13727.ll b/test/ExecutionEngine/MCJIT/pr13727.ll
index 6f5ae39..79dd9b4 100644
--- a/test/ExecutionEngine/MCJIT/pr13727.ll
+++ b/test/ExecutionEngine/MCJIT/pr13727.ll
@@ -31,20 +31,20 @@ entry:
   %retval = alloca i32, align 4
   %i = alloca i32, align 4
   store i32 0, i32* %retval
-  %0 = load i32* @zero_int, align 4
+  %0 = load i32, i32* @zero_int, align 4
   %add = add nsw i32 %0, 5
   %idxprom = sext i32 %add to i64
-  %arrayidx = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom
+  %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom
   store i32 40, i32* %arrayidx, align 4
-  %1 = load double* @zero_double, align 8
+  %1 = load double, double* @zero_double, align 8
   %cmp = fcmp olt double %1, 1.100000e+00
   br i1 %cmp, label %if.then, label %if.end
 
 if.then:                                          ; preds = %entry
-  %2 = load i32* @zero_int, align 4
+  %2 = load i32, i32* @zero_int, align 4
   %add1 = add nsw i32 %2, 2
   %idxprom2 = sext i32 %add1 to i64
-  %arrayidx3 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
+  %arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
   store i32 70, i32* %arrayidx3, align 4
   br label %if.end
 
@@ -53,35 +53,35 @@ if.end:                                           ; preds = %if.then, %entry
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %if.end
-  %3 = load i32* %i, align 4
+  %3 = load i32, i32* %i, align 4
   %cmp4 = icmp slt i32 %3, 10
   br i1 %cmp4, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %sub = sub nsw i32 %4, 1
   %idxprom5 = sext i32 %sub to i64
-  %arrayidx6 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
-  %5 = load i32* %arrayidx6, align 4
-  %6 = load i32* %i, align 4
+  %arrayidx6 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
+  %5 = load i32, i32* %arrayidx6, align 4
+  %6 = load i32, i32* %i, align 4
   %idxprom7 = sext i32 %6 to i64
-  %arrayidx8 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
-  %7 = load i32* %arrayidx8, align 4
+  %arrayidx8 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
+  %7 = load i32, i32* %arrayidx8, align 4
   %add9 = add nsw i32 %5, %7
-  %8 = load i32* %i, align 4
+  %8 = load i32, i32* %i, align 4
   %idxprom10 = sext i32 %8 to i64
-  %arrayidx11 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
+  %arrayidx11 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
   store i32 %add9, i32* %arrayidx11, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %inc = add nsw i32 %9, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %10 = load i32* getelementptr inbounds ([10 x i32]* @zero_arr, i32 0, i64 9), align 4
+  %10 = load i32, i32* getelementptr inbounds ([10 x i32], [10 x i32]* @zero_arr, i32 0, i64 9), align 4
   %cmp12 = icmp eq i32 %10, 110
   %cond = select i1 %cmp12, i32 0, i32 -1
   ret i32 %cond
diff --git a/test/ExecutionEngine/MCJIT/remote/stubs-remote.ll b/test/ExecutionEngine/MCJIT/remote/stubs-remote.ll
index da4ddc6..a834ac5 100644
--- a/test/ExecutionEngine/MCJIT/remote/stubs-remote.ll
+++ b/test/ExecutionEngine/MCJIT/remote/stubs-remote.ll
@@ -21,14 +21,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/MCJIT/remote/stubs-sm-pic.ll b/test/ExecutionEngine/MCJIT/remote/stubs-sm-pic.ll
index f6a1607..62e89ca 100644
--- a/test/ExecutionEngine/MCJIT/remote/stubs-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/remote/stubs-sm-pic.ll
@@ -21,14 +21,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/MCJIT/remote/test-common-symbols-remote.ll b/test/ExecutionEngine/MCJIT/remote/test-common-symbols-remote.ll
index 0f58710..fb7750a 100644
--- a/test/ExecutionEngine/MCJIT/remote/test-common-symbols-remote.ll
+++ b/test/ExecutionEngine/MCJIT/remote/test-common-symbols-remote.ll
@@ -31,20 +31,20 @@ entry:
   %retval = alloca i32, align 4
   %i = alloca i32, align 4
   store i32 0, i32* %retval
-  %0 = load i32* @zero_int, align 4
+  %0 = load i32, i32* @zero_int, align 4
   %add = add nsw i32 %0, 5
   %idxprom = sext i32 %add to i64
-  %arrayidx = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom
+  %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom
   store i32 40, i32* %arrayidx, align 4
-  %1 = load double* @zero_double, align 8
+  %1 = load double, double* @zero_double, align 8
   %cmp = fcmp olt double %1, 1.000000e+00
   br i1 %cmp, label %if.then, label %if.end
 
 if.then:                                          ; preds = %entry
-  %2 = load i32* @zero_int, align 4
+  %2 = load i32, i32* @zero_int, align 4
   %add1 = add nsw i32 %2, 2
   %idxprom2 = sext i32 %add1 to i64
-  %arrayidx3 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
+  %arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
   store i32 70, i32* %arrayidx3, align 4
   br label %if.end
 
@@ -53,35 +53,35 @@ if.end:                                           ; preds = %if.then, %entry
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %if.end
-  %3 = load i32* %i, align 4
+  %3 = load i32, i32* %i, align 4
   %cmp4 = icmp slt i32 %3, 10
   br i1 %cmp4, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %sub = sub nsw i32 %4, 1
   %idxprom5 = sext i32 %sub to i64
-  %arrayidx6 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
-  %5 = load i32* %arrayidx6, align 4
-  %6 = load i32* %i, align 4
+  %arrayidx6 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
+  %5 = load i32, i32* %arrayidx6, align 4
+  %6 = load i32, i32* %i, align 4
   %idxprom7 = sext i32 %6 to i64
-  %arrayidx8 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
-  %7 = load i32* %arrayidx8, align 4
+  %arrayidx8 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
+  %7 = load i32, i32* %arrayidx8, align 4
   %add9 = add nsw i32 %5, %7
-  %8 = load i32* %i, align 4
+  %8 = load i32, i32* %i, align 4
   %idxprom10 = sext i32 %8 to i64
-  %arrayidx11 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
+  %arrayidx11 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
   store i32 %add9, i32* %arrayidx11, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %inc = add nsw i32 %9, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %10 = load i32* getelementptr inbounds ([10 x i32]* @zero_arr, i32 0, i64 9), align 4
+  %10 = load i32, i32* getelementptr inbounds ([10 x i32], [10 x i32]* @zero_arr, i32 0, i64 9), align 4
   %cmp12 = icmp eq i32 %10, 110
   %cond = select i1 %cmp12, i32 0, i32 -1
   ret i32 %cond
diff --git a/test/ExecutionEngine/MCJIT/remote/test-fp-no-external-funcs-remote.ll b/test/ExecutionEngine/MCJIT/remote/test-fp-no-external-funcs-remote.ll
index 9d11415..6134b8b 100644
--- a/test/ExecutionEngine/MCJIT/remote/test-fp-no-external-funcs-remote.ll
+++ b/test/ExecutionEngine/MCJIT/remote/test-fp-no-external-funcs-remote.ll
@@ -1,7 +1,7 @@
 ; RUN: %lli -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
 
 define double @test(double* %DP, double %Arg) nounwind {
-	%D = load double* %DP		; <double> [#uses=1]
+	%D = load double, double* %DP		; <double> [#uses=1]
 	%V = fadd double %D, 1.000000e+00		; <double> [#uses=2]
 	%W = fsub double %V, %V		; <double> [#uses=3]
 	%X = fmul double %W, %W		; <double> [#uses=2]
diff --git a/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-remote.ll b/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-remote.ll
index 40b514f..5b7999c 100644
--- a/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-remote.ll
+++ b/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-remote.ll
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-sm-pic.ll b/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-sm-pic.ll
index 5119b72..f9184b4 100644
--- a/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/remote/test-global-init-nonzero-sm-pic.ll
@@ -12,24 +12,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-remote.ll b/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-remote.ll
index ba3ffff..ad1af93 100644
--- a/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-remote.ll
+++ b/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-remote.ll
@@ -1,14 +1,14 @@
 ; RUN: %lli -remote-mcjit -O0 -mcjit-remote-process=lli-child-target%exeext %s
 
 @.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
 @.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
 
 define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
 entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
   %cmp = icmp eq i8* %0, %1
   %. = zext i1 %cmp to i32
   ret i32 %.
diff --git a/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-sm-pic.ll b/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-sm-pic.ll
index bbc71af..d9a4faa 100644
--- a/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/remote/test-ptr-reloc-sm-pic.ll
@@ -2,14 +2,14 @@
 ; XFAIL: mips, aarch64, arm, i686, i386
 
 @.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
 @.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
 
 define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
 entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
   %cmp = icmp eq i8* %0, %1
   %. = zext i1 %cmp to i32
   ret i32 %.
diff --git a/test/ExecutionEngine/MCJIT/stubs-sm-pic.ll b/test/ExecutionEngine/MCJIT/stubs-sm-pic.ll
index 9b83ed2..6eebe44 100644
--- a/test/ExecutionEngine/MCJIT/stubs-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/stubs-sm-pic.ll
@@ -20,14 +20,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/MCJIT/stubs.ll b/test/ExecutionEngine/MCJIT/stubs.ll
index b7d922f..5b7acc7 100644
--- a/test/ExecutionEngine/MCJIT/stubs.ll
+++ b/test/ExecutionEngine/MCJIT/stubs.ll
@@ -19,14 +19,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/MCJIT/test-common-symbols-alignment.ll b/test/ExecutionEngine/MCJIT/test-common-symbols-alignment.ll
index a425b5c..1bb0744 100644
--- a/test/ExecutionEngine/MCJIT/test-common-symbols-alignment.ll
+++ b/test/ExecutionEngine/MCJIT/test-common-symbols-alignment.ll
@@ -13,7 +13,7 @@ entry:
     %ptr = alloca i32, align 4
     store i32 0, i32* %retval
     store i32 ptrtoint (i32* @CS3 to i32), i32* %ptr, align 4
-    %0 = load i32* %ptr, align 4
+    %0 = load i32, i32* %ptr, align 4
     %and = and i32 %0, 15
     %tobool = icmp ne i32 %and, 0
     br i1 %tobool, label %if.then, label %if.else
@@ -27,6 +27,6 @@ if.else:                                          ; preds = %entry
     br label %return
 
 return:                                           ; preds = %if.else, %if.then
-    %1 = load i32* %retval
+    %1 = load i32, i32* %retval
     ret i32 %1
 }
diff --git a/test/ExecutionEngine/MCJIT/test-common-symbols.ll b/test/ExecutionEngine/MCJIT/test-common-symbols.ll
index 19e2ce5..b63c2fe 100644
--- a/test/ExecutionEngine/MCJIT/test-common-symbols.ll
+++ b/test/ExecutionEngine/MCJIT/test-common-symbols.ll
@@ -31,20 +31,20 @@ entry:
   %retval = alloca i32, align 4
   %i = alloca i32, align 4
   store i32 0, i32* %retval
-  %0 = load i32* @zero_int, align 4
+  %0 = load i32, i32* @zero_int, align 4
   %add = add nsw i32 %0, 5
   %idxprom = sext i32 %add to i64
-  %arrayidx = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom
+  %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom
   store i32 40, i32* %arrayidx, align 4
-  %1 = load double* @zero_double, align 8
+  %1 = load double, double* @zero_double, align 8
   %cmp = fcmp olt double %1, 1.000000e+00
   br i1 %cmp, label %if.then, label %if.end
 
 if.then:                                          ; preds = %entry
-  %2 = load i32* @zero_int, align 4
+  %2 = load i32, i32* @zero_int, align 4
   %add1 = add nsw i32 %2, 2
   %idxprom2 = sext i32 %add1 to i64
-  %arrayidx3 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
+  %arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
   store i32 70, i32* %arrayidx3, align 4
   br label %if.end
 
@@ -53,35 +53,35 @@ if.end:                                           ; preds = %if.then, %entry
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %if.end
-  %3 = load i32* %i, align 4
+  %3 = load i32, i32* %i, align 4
   %cmp4 = icmp slt i32 %3, 10
   br i1 %cmp4, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %sub = sub nsw i32 %4, 1
   %idxprom5 = sext i32 %sub to i64
-  %arrayidx6 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
-  %5 = load i32* %arrayidx6, align 4
-  %6 = load i32* %i, align 4
+  %arrayidx6 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
+  %5 = load i32, i32* %arrayidx6, align 4
+  %6 = load i32, i32* %i, align 4
   %idxprom7 = sext i32 %6 to i64
-  %arrayidx8 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
-  %7 = load i32* %arrayidx8, align 4
+  %arrayidx8 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
+  %7 = load i32, i32* %arrayidx8, align 4
   %add9 = add nsw i32 %5, %7
-  %8 = load i32* %i, align 4
+  %8 = load i32, i32* %i, align 4
   %idxprom10 = sext i32 %8 to i64
-  %arrayidx11 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
+  %arrayidx11 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
   store i32 %add9, i32* %arrayidx11, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %inc = add nsw i32 %9, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %10 = load i32* getelementptr inbounds ([10 x i32]* @zero_arr, i32 0, i64 9), align 4
+  %10 = load i32, i32* getelementptr inbounds ([10 x i32], [10 x i32]* @zero_arr, i32 0, i64 9), align 4
   %cmp12 = icmp eq i32 %10, 110
   %cond = select i1 %cmp12, i32 0, i32 -1
   ret i32 %cond
diff --git a/test/ExecutionEngine/MCJIT/test-fp-no-external-funcs.ll b/test/ExecutionEngine/MCJIT/test-fp-no-external-funcs.ll
index adb0550..c549a44 100644
--- a/test/ExecutionEngine/MCJIT/test-fp-no-external-funcs.ll
+++ b/test/ExecutionEngine/MCJIT/test-fp-no-external-funcs.ll
@@ -1,7 +1,7 @@
 ; RUN: %lli %s > /dev/null
 
 define double @test(double* %DP, double %Arg) {
-	%D = load double* %DP		; <double> [#uses=1]
+	%D = load double, double* %DP		; <double> [#uses=1]
 	%V = fadd double %D, 1.000000e+00		; <double> [#uses=2]
 	%W = fsub double %V, %V		; <double> [#uses=3]
 	%X = fmul double %W, %W		; <double> [#uses=2]
diff --git a/test/ExecutionEngine/MCJIT/test-fp.ll b/test/ExecutionEngine/MCJIT/test-fp.ll
index 2bf0210..c65b5a6 100644
--- a/test/ExecutionEngine/MCJIT/test-fp.ll
+++ b/test/ExecutionEngine/MCJIT/test-fp.ll
@@ -1,7 +1,7 @@
 ; RUN: %lli %s > /dev/null
 
 define double @test(double* %DP, double %Arg) {
-	%D = load double* %DP		; <double> [#uses=1]
+	%D = load double, double* %DP		; <double> [#uses=1]
 	%V = fadd double %D, 1.000000e+00		; <double> [#uses=2]
 	%W = fsub double %V, %V		; <double> [#uses=3]
 	%X = fmul double %W, %W		; <double> [#uses=2]
diff --git a/test/ExecutionEngine/MCJIT/test-global-ctors.ll b/test/ExecutionEngine/MCJIT/test-global-ctors.ll
index ec87d15..6d13271 100644
--- a/test/ExecutionEngine/MCJIT/test-global-ctors.ll
+++ b/test/ExecutionEngine/MCJIT/test-global-ctors.ll
@@ -6,7 +6,7 @@
 
 define i32 @main() nounwind {
 entry:
-  %0 = load i32* @var, align 4
+  %0 = load i32, i32* @var, align 4
   ret i32 %0
 }
 
diff --git a/test/ExecutionEngine/MCJIT/test-global-init-nonzero-sm-pic.ll b/test/ExecutionEngine/MCJIT/test-global-init-nonzero-sm-pic.ll
index 26bd838..8ae496d 100644
--- a/test/ExecutionEngine/MCJIT/test-global-init-nonzero-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/test-global-init-nonzero-sm-pic.ll
@@ -12,24 +12,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/MCJIT/test-global-init-nonzero.ll b/test/ExecutionEngine/MCJIT/test-global-init-nonzero.ll
index 3877e9a..4595219 100644
--- a/test/ExecutionEngine/MCJIT/test-global-init-nonzero.ll
+++ b/test/ExecutionEngine/MCJIT/test-global-init-nonzero.ll
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/MCJIT/test-global.ll b/test/ExecutionEngine/MCJIT/test-global.ll
index 69e5455..2760ecd 100644
--- a/test/ExecutionEngine/MCJIT/test-global.ll
+++ b/test/ExecutionEngine/MCJIT/test-global.ll
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 50
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/MCJIT/test-loadstore.ll b/test/ExecutionEngine/MCJIT/test-loadstore.ll
index 1797599..68c8505 100644
--- a/test/ExecutionEngine/MCJIT/test-loadstore.ll
+++ b/test/ExecutionEngine/MCJIT/test-loadstore.ll
@@ -1,13 +1,13 @@
 ; RUN: %lli %s > /dev/null
 
 define void @test(i8* %P, i16* %P.upgrd.1, i32* %P.upgrd.2, i64* %P.upgrd.3) {
-	%V = load i8* %P		; <i8> [#uses=1]
+	%V = load i8, i8* %P		; <i8> [#uses=1]
 	store i8 %V, i8* %P
-	%V.upgrd.4 = load i16* %P.upgrd.1		; <i16> [#uses=1]
+	%V.upgrd.4 = load i16, i16* %P.upgrd.1		; <i16> [#uses=1]
 	store i16 %V.upgrd.4, i16* %P.upgrd.1
-	%V.upgrd.5 = load i32* %P.upgrd.2		; <i32> [#uses=1]
+	%V.upgrd.5 = load i32, i32* %P.upgrd.2		; <i32> [#uses=1]
 	store i32 %V.upgrd.5, i32* %P.upgrd.2
-	%V.upgrd.6 = load i64* %P.upgrd.3		; <i64> [#uses=1]
+	%V.upgrd.6 = load i64, i64* %P.upgrd.3		; <i64> [#uses=1]
 	store i64 %V.upgrd.6, i64* %P.upgrd.3
 	ret void
 }
@@ -16,7 +16,7 @@ define i32 @varalloca(i32 %Size) {
         ;; Variable sized alloca
 	%X = alloca i32, i32 %Size		; <i32*> [#uses=2]
 	store i32 %Size, i32* %X
-	%Y = load i32* %X		; <i32> [#uses=1]
+	%Y = load i32, i32* %X		; <i32> [#uses=1]
 	ret i32 %Y
 }
 
diff --git a/test/ExecutionEngine/MCJIT/test-local.ll b/test/ExecutionEngine/MCJIT/test-local.ll
index ec5ba16..832e178 100644
--- a/test/ExecutionEngine/MCJIT/test-local.ll
+++ b/test/ExecutionEngine/MCJIT/test-local.ll
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 50
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %count, align 4
+  %1 = load i32, i32* %count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* %count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* %count, align 4
+  %3 = load i32, i32* %count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/MCJIT/test-ptr-reloc-sm-pic.ll b/test/ExecutionEngine/MCJIT/test-ptr-reloc-sm-pic.ll
index 21bcaef..d50ba9d 100644
--- a/test/ExecutionEngine/MCJIT/test-ptr-reloc-sm-pic.ll
+++ b/test/ExecutionEngine/MCJIT/test-ptr-reloc-sm-pic.ll
@@ -2,14 +2,14 @@
 ; XFAIL: mips, aarch64, arm, i686, i386
 
 @.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
 @.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
 
 define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
 entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
   %cmp = icmp eq i8* %0, %1
   %. = zext i1 %cmp to i32
   ret i32 %.
diff --git a/test/ExecutionEngine/MCJIT/test-ptr-reloc.ll b/test/ExecutionEngine/MCJIT/test-ptr-reloc.ll
index f139ddf..9cb4274 100644
--- a/test/ExecutionEngine/MCJIT/test-ptr-reloc.ll
+++ b/test/ExecutionEngine/MCJIT/test-ptr-reloc.ll
@@ -1,14 +1,14 @@
 ; RUN: %lli -O0 %s
 
 @.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
 @.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
 
 define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
 entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
   %cmp = icmp eq i8* %0, %1
   %. = zext i1 %cmp to i32
   ret i32 %.
diff --git a/test/ExecutionEngine/OrcJIT/2003-05-07-ArgumentTest.ll b/test/ExecutionEngine/OrcJIT/2003-05-07-ArgumentTest.ll
deleted file mode 100644
index b45178e..0000000
--- a/test/ExecutionEngine/OrcJIT/2003-05-07-ArgumentTest.ll
+++ /dev/null
@@ -1,11 +0,0 @@
-; RUN: %lli -use-orcmcjit %s test
-
-declare i32 @puts(i8*)
-
-define i32 @main(i32 %argc.1, i8** %argv.1) {
-	%tmp.5 = getelementptr i8** %argv.1, i64 1		; <i8**> [#uses=1]
-	%tmp.6 = load i8** %tmp.5		; <i8*> [#uses=1]
-	%tmp.0 = call i32 @puts( i8* %tmp.6 )		; <i32> [#uses=0]
-	ret i32 0
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/hello-sm-pic.ll b/test/ExecutionEngine/OrcJIT/hello-sm-pic.ll
deleted file mode 100644
index ae98ae4..0000000
--- a/test/ExecutionEngine/OrcJIT/hello-sm-pic.ll
+++ /dev/null
@@ -1,12 +0,0 @@
-; RUN: %lli -use-orcmcjit -relocation-model=pic -code-model=small %s > /dev/null
-; XFAIL: mips, i686, i386, darwin, aarch64, arm
-
-@.LC0 = internal global [12 x i8] c"Hello World\00"		; <[12 x i8]*> [#uses=1]
-
-declare i32 @puts(i8*)
-
-define i32 @main() {
-	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
-	ret i32 0
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/hello.ll b/test/ExecutionEngine/OrcJIT/hello.ll
deleted file mode 100644
index f96e3ee..0000000
--- a/test/ExecutionEngine/OrcJIT/hello.ll
+++ /dev/null
@@ -1,11 +0,0 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
-
-@.LC0 = internal global [12 x i8] c"Hello World\00"		; <[12 x i8]*> [#uses=1]
-
-declare i32 @puts(i8*)
-
-define i32 @main() {
-	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
-	ret i32 0
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/multi-module-a.ll b/test/ExecutionEngine/OrcJIT/multi-module-a.ll
deleted file mode 100644
index 587a1e8..0000000
--- a/test/ExecutionEngine/OrcJIT/multi-module-a.ll
+++ /dev/null
@@ -1,9 +0,0 @@
-; RUN: %lli -use-orcmcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll %s > /dev/null
-
-declare i32 @FB()
-
-define i32 @main() {
-  %r = call i32 @FB( )   ; <i32> [#uses=1]
-  ret i32 %r
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/multi-module-sm-pic-a.ll b/test/ExecutionEngine/OrcJIT/multi-module-sm-pic-a.ll
deleted file mode 100644
index b5ee3d1..0000000
--- a/test/ExecutionEngine/OrcJIT/multi-module-sm-pic-a.ll
+++ /dev/null
@@ -1,10 +0,0 @@
-; RUN: %lli -use-orcmcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -relocation-model=pic -code-model=small %s > /dev/null
-; XFAIL: mips, i686, i386
-
-declare i32 @FB()
-
-define i32 @main() {
-  %r = call i32 @FB( )   ; <i32> [#uses=1]
-  ret i32 %r
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/remote/cross-module-a.ll b/test/ExecutionEngine/OrcJIT/remote/cross-module-a.ll
deleted file mode 100644
index c315723..0000000
--- a/test/ExecutionEngine/OrcJIT/remote/cross-module-a.ll
+++ /dev/null
@@ -1,12 +0,0 @@
-; RUN: %lli -extra-module=%p/Inputs/cross-module-b.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
-
-declare i32 @FB()
-
-define i32 @FA() nounwind {
-  ret i32 0
-}
-
-define i32 @main() nounwind {
-  %r = call i32 @FB( )   ; <i32> [#uses=1]
-  ret i32 %r
-}
diff --git a/test/ExecutionEngine/OrcJIT/remote/cross-module-sm-pic-a.ll b/test/ExecutionEngine/OrcJIT/remote/cross-module-sm-pic-a.ll
deleted file mode 100644
index d47fc6c..0000000
--- a/test/ExecutionEngine/OrcJIT/remote/cross-module-sm-pic-a.ll
+++ /dev/null
@@ -1,14 +0,0 @@
-; RUN: %lli -extra-module=%p/Inputs/cross-module-b.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext -relocation-model=pic -code-model=small %s > /dev/null
-; XFAIL: mips, i686, i386, arm
-
-declare i32 @FB()
-
-define i32 @FA() {
-  ret i32 0
-}
-
-define i32 @main() {
-  %r = call i32 @FB( )   ; <i32> [#uses=1]
-  ret i32 %r
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/remote/multi-module-a.ll b/test/ExecutionEngine/OrcJIT/remote/multi-module-a.ll
deleted file mode 100644
index 0fd363b..0000000
--- a/test/ExecutionEngine/OrcJIT/remote/multi-module-a.ll
+++ /dev/null
@@ -1,9 +0,0 @@
-; RUN: %lli -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
-
-declare i32 @FB()
-
-define i32 @main() nounwind {
-  %r = call i32 @FB( )   ; <i32> [#uses=1]
-  ret i32 %r
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/remote/multi-module-sm-pic-a.ll b/test/ExecutionEngine/OrcJIT/remote/multi-module-sm-pic-a.ll
deleted file mode 100644
index d248c4b..0000000
--- a/test/ExecutionEngine/OrcJIT/remote/multi-module-sm-pic-a.ll
+++ /dev/null
@@ -1,10 +0,0 @@
-; RUN: %lli -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext -relocation-model=pic -code-model=small %s > /dev/null
-; XFAIL: mips, i686, i386, arm
-
-declare i32 @FB()
-
-define i32 @main() {
-  %r = call i32 @FB( )   ; <i32> [#uses=1]
-  ret i32 %r
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-ptr-reloc-remote.ll b/test/ExecutionEngine/OrcJIT/remote/test-ptr-reloc-remote.ll
deleted file mode 100644
index ba3ffff..0000000
--- a/test/ExecutionEngine/OrcJIT/remote/test-ptr-reloc-remote.ll
+++ /dev/null
@@ -1,15 +0,0 @@
-; RUN: %lli -remote-mcjit -O0 -mcjit-remote-process=lli-child-target%exeext %s
-
-@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
-@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
-
-define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
-entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
-  %cmp = icmp eq i8* %0, %1
-  %. = zext i1 %cmp to i32
-  ret i32 %.
-}
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-ptr-reloc-sm-pic.ll b/test/ExecutionEngine/OrcJIT/remote/test-ptr-reloc-sm-pic.ll
deleted file mode 100644
index bbc71af..0000000
--- a/test/ExecutionEngine/OrcJIT/remote/test-ptr-reloc-sm-pic.ll
+++ /dev/null
@@ -1,17 +0,0 @@
-; RUN: %lli -remote-mcjit -O0 -relocation-model=pic -code-model=small %s
-; XFAIL: mips, aarch64, arm, i686, i386
-
-@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
-@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
-
-define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
-entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
-  %cmp = icmp eq i8* %0, %1
-  %. = zext i1 %cmp to i32
-  ret i32 %.
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/simplesttest.ll b/test/ExecutionEngine/OrcJIT/simplesttest.ll
deleted file mode 100644
index c2f24f6..0000000
--- a/test/ExecutionEngine/OrcJIT/simplesttest.ll
+++ /dev/null
@@ -1,6 +0,0 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
-
-define i32 @main() {
-	ret i32 0
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/test-ptr-reloc-sm-pic.ll b/test/ExecutionEngine/OrcJIT/test-ptr-reloc-sm-pic.ll
deleted file mode 100644
index d940adc..0000000
--- a/test/ExecutionEngine/OrcJIT/test-ptr-reloc-sm-pic.ll
+++ /dev/null
@@ -1,17 +0,0 @@
-; RUN: %lli -use-orcmcjit -O0 -relocation-model=pic -code-model=small %s
-; XFAIL: mips, aarch64, arm, i686, i386
-
-@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
-@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
-
-define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
-entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
-  %cmp = icmp eq i8* %0, %1
-  %. = zext i1 %cmp to i32
-  ret i32 %.
-}
-
diff --git a/test/ExecutionEngine/OrcJIT/test-ptr-reloc.ll b/test/ExecutionEngine/OrcJIT/test-ptr-reloc.ll
deleted file mode 100644
index 95fa106..0000000
--- a/test/ExecutionEngine/OrcJIT/test-ptr-reloc.ll
+++ /dev/null
@@ -1,16 +0,0 @@
-; RUN: %lli -use-orcmcjit -O0 %s
-
-@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
-@ptr = global i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), align 4
-@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
-@ptr2 = global i8* getelementptr inbounds ([6 x i8]* @.str1, i32 0, i32 0), align 4
-
-define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
-entry:
-  %0 = load i8** @ptr, align 4
-  %1 = load i8** @ptr2, align 4
-  %cmp = icmp eq i8* %0, %1
-  %. = zext i1 %cmp to i32
-  ret i32 %.
-}
-
diff --git a/test/ExecutionEngine/OrcLazy/lit.local.cfg b/test/ExecutionEngine/OrcLazy/lit.local.cfg
new file mode 100644
index 0000000..bf63c4f
--- /dev/null
+++ b/test/ExecutionEngine/OrcLazy/lit.local.cfg
@@ -0,0 +1,2 @@
+if config.root.host_arch not in ['x86_64']:
+    config.unsupported = True
diff --git a/test/ExecutionEngine/OrcLazy/trivial_retval_1.ll b/test/ExecutionEngine/OrcLazy/trivial_retval_1.ll
new file mode 100644
index 0000000..701f22c
--- /dev/null
+++ b/test/ExecutionEngine/OrcLazy/trivial_retval_1.ll
@@ -0,0 +1,26 @@
+; RUN: sh -c 'lli -jit-kind=orc-lazy %s; echo $?' | FileCheck %s
+; CHECK: {{^30$}}
+define i32 @baz() {
+entry:
+  ret i32 2
+}
+
+define i32 @bar() {
+entry:
+  %call = call i32 @baz()
+  %mul = mul nsw i32 3, %call
+  ret i32 %mul
+}
+
+define i32 @foo() {
+entry:
+  %call = call i32 @bar()
+  %mul = mul nsw i32 5, %call
+  ret i32 %mul
+}
+
+define i32 @main(i32 %argc, i8** %argv) {
+entry:
+  %call = call i32 @foo()
+  ret i32 %call
+}
diff --git a/test/ExecutionEngine/OrcJIT/2002-12-16-ArgTest.ll b/test/ExecutionEngine/OrcMCJIT/2002-12-16-ArgTest.ll
index e2fee8d..e8eb693 100644
--- a/test/ExecutionEngine/OrcJIT/2002-12-16-ArgTest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2002-12-16-ArgTest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 @.LC0 = internal global [10 x i8] c"argc: %d\0A\00"		; <[10 x i8]*> [#uses=1]
 
@@ -13,7 +13,7 @@ declare i32 @printf(i8*, ...)
 
 define i32 @main(i32 %argc, i8** %argv) {
 bb0:
-	call i32 (i8*, ...)* @printf( i8* getelementptr ([10 x i8]* @.LC0, i64 0, i64 0), i32 %argc )		; <i32>:0 [#uses=0]
+	call i32 (i8*, ...)* @printf( i8* getelementptr ([10 x i8], [10 x i8]* @.LC0, i64 0, i64 0), i32 %argc )		; <i32>:0 [#uses=0]
 	%cast224 = bitcast i8** %argv to i8*		; <i8*> [#uses=1]
 	%local = alloca i8*		; <i8**> [#uses=3]
 	store i8* %cast224, i8** %local
@@ -24,9 +24,9 @@ bb2:		; preds = %bb2, %bb0
 	%add1-indvar = add i32 %cann-indvar, 1		; <i32> [#uses=2]
 	%cann-indvar-idxcast = sext i32 %cann-indvar to i64		; <i64> [#uses=1]
 	%CT = bitcast i8** %local to i8***		; <i8***> [#uses=1]
-	%reg115 = load i8*** %CT		; <i8**> [#uses=1]
-	%cast235 = getelementptr i8** %reg115, i64 %cann-indvar-idxcast		; <i8**> [#uses=1]
-	%reg117 = load i8** %cast235		; <i8*> [#uses=1]
+	%reg115 = load i8**, i8*** %CT		; <i8**> [#uses=1]
+	%cast235 = getelementptr i8*, i8** %reg115, i64 %cann-indvar-idxcast		; <i8**> [#uses=1]
+	%reg117 = load i8*, i8** %cast235		; <i8*> [#uses=1]
 	%reg236 = call i32 @puts( i8* %reg117 )		; <i32> [#uses=0]
 	%cond239 = icmp slt i32 %add1-indvar, %argc		; <i1> [#uses=1]
 	br i1 %cond239, label %bb2, label %bb3
diff --git a/test/ExecutionEngine/OrcJIT/2003-01-04-ArgumentBug.ll b/test/ExecutionEngine/OrcMCJIT/2003-01-04-ArgumentBug.ll
index 67425a9..2061329 100644
--- a/test/ExecutionEngine/OrcJIT/2003-01-04-ArgumentBug.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-01-04-ArgumentBug.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @foo(i32 %X, i32 %Y, double %A) {
 	%cond212 = fcmp une double %A, 1.000000e+00		; <i1> [#uses=1]
diff --git a/test/ExecutionEngine/OrcJIT/2003-01-04-LoopTest.ll b/test/ExecutionEngine/OrcMCJIT/2003-01-04-LoopTest.ll
index cf805ea..a298172 100644
--- a/test/ExecutionEngine/OrcJIT/2003-01-04-LoopTest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-01-04-LoopTest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 	call i32 @mylog( i32 4 )		; <i32>:1 [#uses=0]
diff --git a/test/ExecutionEngine/OrcJIT/2003-01-04-PhiTest.ll b/test/ExecutionEngine/OrcMCJIT/2003-01-04-PhiTest.ll
index b8b8519..a24e188 100644
--- a/test/ExecutionEngine/OrcJIT/2003-01-04-PhiTest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-01-04-PhiTest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 ; <label>:0
diff --git a/test/ExecutionEngine/OrcJIT/2003-01-09-SARTest.ll b/test/ExecutionEngine/OrcMCJIT/2003-01-09-SARTest.ll
index 85b0031..8f79ff2 100644
--- a/test/ExecutionEngine/OrcJIT/2003-01-09-SARTest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-01-09-SARTest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; We were accidentally inverting the signedness of right shifts.  Whoops.
 
diff --git a/test/ExecutionEngine/OrcJIT/2003-01-10-FUCOM.ll b/test/ExecutionEngine/OrcMCJIT/2003-01-10-FUCOM.ll
index 66b21c9..7e2ce66 100644
--- a/test/ExecutionEngine/OrcJIT/2003-01-10-FUCOM.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-01-10-FUCOM.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 	%X = fadd double 0.000000e+00, 1.000000e+00		; <double> [#uses=1]
diff --git a/test/ExecutionEngine/OrcJIT/2003-01-15-AlignmentTest.ll b/test/ExecutionEngine/OrcMCJIT/2003-01-15-AlignmentTest.ll
index 1f27c1f..38d5f83 100644
--- a/test/ExecutionEngine/OrcJIT/2003-01-15-AlignmentTest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-01-15-AlignmentTest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @bar(i8* %X) {
         ; pointer should be 4 byte aligned!
diff --git a/test/ExecutionEngine/OrcJIT/2003-05-06-LivenessClobber.ll b/test/ExecutionEngine/OrcMCJIT/2003-05-06-LivenessClobber.ll
index 576ef7c..82bf97d 100644
--- a/test/ExecutionEngine/OrcJIT/2003-05-06-LivenessClobber.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-05-06-LivenessClobber.ll
@@ -1,11 +1,11 @@
 ; This testcase should return with an exit code of 1.
 ;
-; RUN: not %lli %s
+; RUN: not %lli -jit-kind=orc-mcjit %s
 
 @test = global i64 0		; <i64*> [#uses=1]
 
 define internal i64 @test.upgrd.1() {
-	%tmp.0 = load i64* @test		; <i64> [#uses=1]
+	%tmp.0 = load i64, i64* @test		; <i64> [#uses=1]
 	%tmp.1 = add i64 %tmp.0, 1		; <i64> [#uses=1]
 	ret i64 %tmp.1
 }
diff --git a/test/ExecutionEngine/OrcMCJIT/2003-05-07-ArgumentTest.ll b/test/ExecutionEngine/OrcMCJIT/2003-05-07-ArgumentTest.ll
new file mode 100644
index 0000000..43e9ec9
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/2003-05-07-ArgumentTest.ll
@@ -0,0 +1,11 @@
+; RUN: %lli -jit-kind=orc-mcjit %s test
+
+declare i32 @puts(i8*)
+
+define i32 @main(i32 %argc.1, i8** %argv.1) {
+	%tmp.5 = getelementptr i8*, i8** %argv.1, i64 1		; <i8**> [#uses=1]
+	%tmp.6 = load i8*, i8** %tmp.5		; <i8*> [#uses=1]
+	%tmp.0 = call i32 @puts( i8* %tmp.6 )		; <i32> [#uses=0]
+	ret i32 0
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/2003-05-11-PHIRegAllocBug.ll b/test/ExecutionEngine/OrcMCJIT/2003-05-11-PHIRegAllocBug.ll
index 68402d9..47988b9 100644
--- a/test/ExecutionEngine/OrcJIT/2003-05-11-PHIRegAllocBug.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-05-11-PHIRegAllocBug.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 entry:
diff --git a/test/ExecutionEngine/OrcJIT/2003-06-04-bzip2-bug.ll b/test/ExecutionEngine/OrcMCJIT/2003-06-04-bzip2-bug.ll
index 0907993..942b836 100644
--- a/test/ExecutionEngine/OrcJIT/2003-06-04-bzip2-bug.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-06-04-bzip2-bug.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; Testcase distilled from 256.bzip2.
 
diff --git a/test/ExecutionEngine/OrcJIT/2003-06-05-PHIBug.ll b/test/ExecutionEngine/OrcMCJIT/2003-06-05-PHIBug.ll
index 2eb497b..07bcbbd 100644
--- a/test/ExecutionEngine/OrcJIT/2003-06-05-PHIBug.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-06-05-PHIBug.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; Testcase distilled from 256.bzip2.
 
diff --git a/test/ExecutionEngine/OrcJIT/2003-08-15-AllocaAssertion.ll b/test/ExecutionEngine/OrcMCJIT/2003-08-15-AllocaAssertion.ll
index 290d5a2..43c26b7 100644
--- a/test/ExecutionEngine/OrcJIT/2003-08-15-AllocaAssertion.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-08-15-AllocaAssertion.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; This testcase failed to work because two variable sized allocas confused the
 ; local register allocator.
diff --git a/test/ExecutionEngine/OrcJIT/2003-08-21-EnvironmentTest.ll b/test/ExecutionEngine/OrcMCJIT/2003-08-21-EnvironmentTest.ll
index f73f10e..88dd46e 100644
--- a/test/ExecutionEngine/OrcJIT/2003-08-21-EnvironmentTest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-08-21-EnvironmentTest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ;
 ; Regression Test: EnvironmentTest.ll
@@ -12,7 +12,7 @@
 declare i32 @strlen(i8*)
 
 define i32 @main(i32 %argc.1, i8** %argv.1, i8** %envp.1) {
-	%tmp.2 = load i8** %envp.1		; <i8*> [#uses=1]
+	%tmp.2 = load i8*, i8** %envp.1		; <i8*> [#uses=1]
 	%tmp.3 = call i32 @strlen( i8* %tmp.2 )		; <i32> [#uses=1]
 	%T = icmp eq i32 %tmp.3, 0		; <i1> [#uses=1]
 	%R = zext i1 %T to i32		; <i32> [#uses=1]
diff --git a/test/ExecutionEngine/OrcJIT/2003-08-23-RegisterAllocatePhysReg.ll b/test/ExecutionEngine/OrcMCJIT/2003-08-23-RegisterAllocatePhysReg.ll
index bd26c38..fc3734f 100644
--- a/test/ExecutionEngine/OrcJIT/2003-08-23-RegisterAllocatePhysReg.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-08-23-RegisterAllocatePhysReg.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; This testcase exposes a bug in the local register allocator where it runs out
 ; of registers (due to too many overlapping live ranges), but then attempts to
diff --git a/test/ExecutionEngine/OrcJIT/2003-10-18-PHINode-ConstantExpr-CondCode-Failure.ll b/test/ExecutionEngine/OrcMCJIT/2003-10-18-PHINode-ConstantExpr-CondCode-Failure.ll
index c59ad32..4e38184 100644
--- a/test/ExecutionEngine/OrcJIT/2003-10-18-PHINode-ConstantExpr-CondCode-Failure.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2003-10-18-PHINode-ConstantExpr-CondCode-Failure.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 @A = global i32 0		; <i32*> [#uses=1]
 
diff --git a/test/ExecutionEngine/OrcJIT/2005-12-02-TailCallBug.ll b/test/ExecutionEngine/OrcMCJIT/2005-12-02-TailCallBug.ll
index 7f1d3b0..aff7fce 100644
--- a/test/ExecutionEngine/OrcJIT/2005-12-02-TailCallBug.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2005-12-02-TailCallBug.ll
@@ -1,5 +1,5 @@
 ; PR672
-; RUN: %lli -use-orcmcjit %s
+; RUN: %lli -jit-kind=orc-mcjit %s
 ; XFAIL: mcjit-ia32
 
 define i32 @main() {
diff --git a/test/ExecutionEngine/OrcJIT/2007-12-10-APIntLoadStore.ll b/test/ExecutionEngine/OrcMCJIT/2007-12-10-APIntLoadStore.ll
index efe5d83..5bad45a 100644
--- a/test/ExecutionEngine/OrcJIT/2007-12-10-APIntLoadStore.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2007-12-10-APIntLoadStore.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -force-interpreter %s
+; RUN: %lli -jit-kind=orc-mcjit -force-interpreter %s
 ; PR1836
 
 define i32 @main() {
@@ -9,11 +9,11 @@ entry:
     %"alloca point" = bitcast i32 0 to i32      ; <i32> [#uses=0]
     store i75 999, i75* %x, align 16
     store i32 0, i32* %tmp, align 4
-    %tmp1 = load i32* %tmp, align 4     ; <i32> [#uses=1]
+    %tmp1 = load i32, i32* %tmp, align 4     ; <i32> [#uses=1]
     store i32 %tmp1, i32* %retval, align 4
     br label %return
 
 return:     ; preds = %entry
-    %retval2 = load i32* %retval        ; <i32> [#uses=1]
+    %retval2 = load i32, i32* %retval        ; <i32> [#uses=1]
     ret i32 %retval2
 }
diff --git a/test/ExecutionEngine/OrcJIT/2008-06-05-APInt-OverAShr.ll b/test/ExecutionEngine/OrcMCJIT/2008-06-05-APInt-OverAShr.ll
index 6b27528..9dc3e5b 100644
--- a/test/ExecutionEngine/OrcJIT/2008-06-05-APInt-OverAShr.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2008-06-05-APInt-OverAShr.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -force-interpreter=true %s | FileCheck %s
+; RUN: %lli -jit-kind=orc-mcjit -force-interpreter=true %s | FileCheck %s
 ; CHECK: 1
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32"
@@ -12,15 +12,15 @@ entry:
 	%tmp = alloca i65		; <i65*> [#uses=2]
 	%"alloca point" = bitcast i65 0 to i65		; <i65> [#uses=0]
 	store i65 %x, i65* %x_addr
-	%tmp1 = load i65* %x_addr, align 4		; <i65> [#uses=1]
+	%tmp1 = load i65, i65* %x_addr, align 4		; <i65> [#uses=1]
 	%tmp2 = ashr i65 %tmp1, 65		; <i65> [#uses=1]
 	store i65 %tmp2, i65* %tmp, align 4
-	%tmp3 = load i65* %tmp, align 4		; <i65> [#uses=1]
+	%tmp3 = load i65, i65* %tmp, align 4		; <i65> [#uses=1]
 	store i65 %tmp3, i65* %retval, align 4
 	br label %return
 
 return:		; preds = %entry
-	%retval4 = load i65* %retval		; <i65> [#uses=1]
+	%retval4 = load i65, i65* %retval		; <i65> [#uses=1]
 	ret i65 %retval4
 }
 
@@ -46,14 +46,14 @@ cond_false:		; preds = %entry
 	br label %cond_next
 
 cond_next:		; preds = %cond_false, %cond_true
-	%tmp5 = getelementptr [10 x i8]* @.str, i32 0, i32 0		; <i8*> [#uses=1]
-	%tmp6 = load i32* %iftmp.0, align 4		; <i32> [#uses=1]
+	%tmp5 = getelementptr [10 x i8], [10 x i8]* @.str, i32 0, i32 0		; <i8*> [#uses=1]
+	%tmp6 = load i32, i32* %iftmp.0, align 4		; <i32> [#uses=1]
 	%tmp7 = call i32 (i8*, ...)* @printf( i8* noalias  %tmp5, i32 %tmp6 ) nounwind 		; <i32> [#uses=0]
 	br label %return
 
 return:		; preds = %cond_next
     store i32 0, i32* %retval, align 4
-	%retval8 = load i32* %retval		; <i32> [#uses=1]
+	%retval8 = load i32, i32* %retval		; <i32> [#uses=1]
 	ret i32 %retval8
 }
 
diff --git a/test/ExecutionEngine/OrcJIT/2013-04-04-RelocAddend.ll b/test/ExecutionEngine/OrcMCJIT/2013-04-04-RelocAddend.ll
index 199e948..94ccf95 100644
--- a/test/ExecutionEngine/OrcJIT/2013-04-04-RelocAddend.ll
+++ b/test/ExecutionEngine/OrcMCJIT/2013-04-04-RelocAddend.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s
+; RUN: %lli -jit-kind=orc-mcjit %s
 ;
 ; Verify relocations to global symbols with addend work correctly.
 ;
@@ -14,12 +14,12 @@
 ; 
 
 @test = global [2 x i32] [i32 -1, i32 0], align 4
-@p = global i32* getelementptr inbounds ([2 x i32]* @test, i64 0, i64 1), align 8
+@p = global i32* getelementptr inbounds ([2 x i32], [2 x i32]* @test, i64 0, i64 1), align 8
 
 define i32 @main() {
 entry:
-  %0 = load i32** @p, align 8
-  %1 = load i32* %0, align 4
+  %0 = load i32*, i32** @p, align 8
+  %1 = load i32, i32* %0, align 4
   ret i32 %1
 }
 
diff --git a/test/ExecutionEngine/OrcJIT/Inputs/cross-module-b.ll b/test/ExecutionEngine/OrcMCJIT/Inputs/cross-module-b.ll
index 6870117..6870117 100644
--- a/test/ExecutionEngine/OrcJIT/Inputs/cross-module-b.ll
+++ b/test/ExecutionEngine/OrcMCJIT/Inputs/cross-module-b.ll
diff --git a/test/ExecutionEngine/OrcJIT/Inputs/multi-module-b.ll b/test/ExecutionEngine/OrcMCJIT/Inputs/multi-module-b.ll
index 103b601..103b601 100644
--- a/test/ExecutionEngine/OrcJIT/Inputs/multi-module-b.ll
+++ b/test/ExecutionEngine/OrcMCJIT/Inputs/multi-module-b.ll
diff --git a/test/ExecutionEngine/OrcJIT/Inputs/multi-module-c.ll b/test/ExecutionEngine/OrcMCJIT/Inputs/multi-module-c.ll
index b39306b..b39306b 100644
--- a/test/ExecutionEngine/OrcJIT/Inputs/multi-module-c.ll
+++ b/test/ExecutionEngine/OrcMCJIT/Inputs/multi-module-c.ll
diff --git a/test/ExecutionEngine/OrcJIT/Inputs/multi-module-eh-b.ll b/test/ExecutionEngine/OrcMCJIT/Inputs/multi-module-eh-b.ll
index d7dbb03..d7dbb03 100644
--- a/test/ExecutionEngine/OrcJIT/Inputs/multi-module-eh-b.ll
+++ b/test/ExecutionEngine/OrcMCJIT/Inputs/multi-module-eh-b.ll
diff --git a/test/ExecutionEngine/OrcJIT/cross-module-a.ll b/test/ExecutionEngine/OrcMCJIT/cross-module-a.ll
index 14a73f5..451b266 100644
--- a/test/ExecutionEngine/OrcJIT/cross-module-a.ll
+++ b/test/ExecutionEngine/OrcMCJIT/cross-module-a.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -extra-module=%p/Inputs/cross-module-b.ll %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/cross-module-b.ll %s > /dev/null
 
 declare i32 @FB()
 
diff --git a/test/ExecutionEngine/OrcJIT/cross-module-sm-pic-a.ll b/test/ExecutionEngine/OrcMCJIT/cross-module-sm-pic-a.ll
index 50ad1c0..4f5afd0 100644
--- a/test/ExecutionEngine/OrcJIT/cross-module-sm-pic-a.ll
+++ b/test/ExecutionEngine/OrcMCJIT/cross-module-sm-pic-a.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -extra-module=%p/Inputs/cross-module-b.ll -relocation-model=pic -code-model=small %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/cross-module-b.ll -relocation-model=pic -code-model=small %s > /dev/null
 ; XFAIL: mips, i686, i386
 
 declare i32 @FB()
diff --git a/test/ExecutionEngine/OrcJIT/eh-lg-pic.ll b/test/ExecutionEngine/OrcMCJIT/eh-lg-pic.ll
index e5fa22c..32b53c4 100644
--- a/test/ExecutionEngine/OrcJIT/eh-lg-pic.ll
+++ b/test/ExecutionEngine/OrcMCJIT/eh-lg-pic.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -relocation-model=pic -code-model=large %s
+; RUN: %lli -jit-kind=orc-mcjit -relocation-model=pic -code-model=large %s
 ; XFAIL: cygwin, win32, mingw, mips, i686, i386, aarch64, arm, asan, msan
 declare i8* @__cxa_allocate_exception(i64)
 declare void @__cxa_throw(i8*, i8*, i8*)
diff --git a/test/ExecutionEngine/OrcJIT/eh-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/eh-sm-pic.ll
index f22cea9..a54795e 100644
--- a/test/ExecutionEngine/OrcJIT/eh-sm-pic.ll
+++ b/test/ExecutionEngine/OrcMCJIT/eh-sm-pic.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -relocation-model=pic -code-model=small %s
+; RUN: %lli -jit-kind=orc-mcjit -relocation-model=pic -code-model=small %s
 ; XFAIL: cygwin, win32, mingw, mips, i686, i386, darwin, aarch64, arm, asan, msan
 declare i8* @__cxa_allocate_exception(i64)
 declare void @__cxa_throw(i8*, i8*, i8*)
diff --git a/test/ExecutionEngine/OrcJIT/eh.ll b/test/ExecutionEngine/OrcMCJIT/eh.ll
index 130146b..2de6a51 100644
--- a/test/ExecutionEngine/OrcJIT/eh.ll
+++ b/test/ExecutionEngine/OrcMCJIT/eh.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s
+; RUN: %lli -jit-kind=orc-mcjit %s
 ; XFAIL: arm, cygwin, win32, mingw, asan, msan
 declare i8* @__cxa_allocate_exception(i64)
 declare void @__cxa_throw(i8*, i8*, i8*)
diff --git a/test/ExecutionEngine/OrcJIT/fpbitcast.ll b/test/ExecutionEngine/OrcMCJIT/fpbitcast.ll
index 0e39f88..767b580 100644
--- a/test/ExecutionEngine/OrcJIT/fpbitcast.ll
+++ b/test/ExecutionEngine/OrcMCJIT/fpbitcast.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -force-interpreter=true %s | FileCheck %s
+; RUN: %lli -jit-kind=orc-mcjit -force-interpreter=true %s | FileCheck %s
 ; CHECK: 40091eb8
 
 define i32 @test(double %x) {
@@ -12,7 +12,7 @@ entry:
 define i32 @main()
 {
        %res = call i32 @test(double 3.14)
-       %ptr = getelementptr [4 x i8]* @format, i32 0, i32 0
+       %ptr = getelementptr [4 x i8], [4 x i8]* @format, i32 0, i32 0
        call i32 (i8*,...)* @printf(i8* %ptr, i32 %res)
        ret i32 0
 }
diff --git a/test/ExecutionEngine/OrcMCJIT/hello-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/hello-sm-pic.ll
new file mode 100644
index 0000000..59b47af
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/hello-sm-pic.ll
@@ -0,0 +1,12 @@
+; RUN: %lli -jit-kind=orc-mcjit -relocation-model=pic -code-model=small %s > /dev/null
+; XFAIL: mips, i686, i386, darwin, aarch64, arm
+
+@.LC0 = internal global [12 x i8] c"Hello World\00"		; <[12 x i8]*> [#uses=1]
+
+declare i32 @puts(i8*)
+
+define i32 @main() {
+	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8], [12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
+	ret i32 0
+}
+
diff --git a/test/ExecutionEngine/OrcMCJIT/hello.ll b/test/ExecutionEngine/OrcMCJIT/hello.ll
new file mode 100644
index 0000000..08413c2
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/hello.ll
@@ -0,0 +1,11 @@
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
+
+@.LC0 = internal global [12 x i8] c"Hello World\00"		; <[12 x i8]*> [#uses=1]
+
+declare i32 @puts(i8*)
+
+define i32 @main() {
+	%reg210 = call i32 @puts( i8* getelementptr ([12 x i8], [12 x i8]* @.LC0, i64 0, i64 0) )		; <i32> [#uses=0]
+	ret i32 0
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/hello2.ll b/test/ExecutionEngine/OrcMCJIT/hello2.ll
index 9e7cf5b..8f071cd 100644
--- a/test/ExecutionEngine/OrcJIT/hello2.ll
+++ b/test/ExecutionEngine/OrcMCJIT/hello2.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 @X = global i32 7		; <i32*> [#uses=0]
 @msg = internal global [13 x i8] c"Hello World\0A\00"		; <[13 x i8]*> [#uses=1]
diff --git a/test/ExecutionEngine/OrcJIT/lit.local.cfg b/test/ExecutionEngine/OrcMCJIT/lit.local.cfg
index f981403..f981403 100644
--- a/test/ExecutionEngine/OrcJIT/lit.local.cfg
+++ b/test/ExecutionEngine/OrcMCJIT/lit.local.cfg
diff --git a/test/ExecutionEngine/OrcJIT/load-object-a.ll b/test/ExecutionEngine/OrcMCJIT/load-object-a.ll
index 080bf6c..abd470d 100644
--- a/test/ExecutionEngine/OrcJIT/load-object-a.ll
+++ b/test/ExecutionEngine/OrcMCJIT/load-object-a.ll
@@ -1,20 +1,20 @@
 ; This first line will generate the .o files for the next run line
 ; RUN: rm -rf %t.cachedir %t.cachedir2 %t.cachedir3
 ; RUN: mkdir -p %t.cachedir %t.cachedir2 %t.cachedir3
-; RUN: %lli -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -enable-cache-manager -object-cache-dir=%t.cachedir %s
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -enable-cache-manager -object-cache-dir=%t.cachedir %s
 
 ; Collect generated objects.
 ; RUN: find %t.cachedir -type f -name 'multi-module-?.o' -exec mv -v '{}' %t.cachedir2 ';'
 
 ; This line tests MCJIT object loading
-; RUN: %lli -extra-object=%t.cachedir2/multi-module-b.o -extra-object=%t.cachedir2/multi-module-c.o %s
+; RUN: %lli -jit-kind=orc-mcjit -extra-object=%t.cachedir2/multi-module-b.o -extra-object=%t.cachedir2/multi-module-c.o %s
 
 ; These lines put the object files into an archive
 ; RUN: llvm-ar r %t.cachedir3/load-object.a %t.cachedir2/multi-module-b.o
 ; RUN: llvm-ar r %t.cachedir3/load-object.a %t.cachedir2/multi-module-c.o
 
 ; This line test MCJIT archive loading
-; RUN: %lli -extra-archive=%t.cachedir3/load-object.a %s
+; RUN: %lli -jit-kind=orc-mcjit -extra-archive=%t.cachedir3/load-object.a %s
 
 declare i32 @FB()
 
diff --git a/test/ExecutionEngine/OrcMCJIT/multi-module-a.ll b/test/ExecutionEngine/OrcMCJIT/multi-module-a.ll
new file mode 100644
index 0000000..d622efc
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/multi-module-a.ll
@@ -0,0 +1,9 @@
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll %s > /dev/null
+
+declare i32 @FB()
+
+define i32 @main() {
+  %r = call i32 @FB( )   ; <i32> [#uses=1]
+  ret i32 %r
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/multi-module-eh-a.ll b/test/ExecutionEngine/OrcMCJIT/multi-module-eh-a.ll
index 6117e4c..f77cb44 100644
--- a/test/ExecutionEngine/OrcJIT/multi-module-eh-a.ll
+++ b/test/ExecutionEngine/OrcMCJIT/multi-module-eh-a.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -extra-module=%p/Inputs/multi-module-eh-b.ll %s
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/multi-module-eh-b.ll %s
 ; XFAIL: arm, cygwin, win32, mingw, asan, msan
 declare i8* @__cxa_allocate_exception(i64)
 declare void @__cxa_throw(i8*, i8*, i8*)
diff --git a/test/ExecutionEngine/OrcMCJIT/multi-module-sm-pic-a.ll b/test/ExecutionEngine/OrcMCJIT/multi-module-sm-pic-a.ll
new file mode 100644
index 0000000..80b8e16
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/multi-module-sm-pic-a.ll
@@ -0,0 +1,10 @@
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -relocation-model=pic -code-model=small %s > /dev/null
+; XFAIL: mips, i686, i386
+
+declare i32 @FB()
+
+define i32 @main() {
+  %r = call i32 @FB( )   ; <i32> [#uses=1]
+  ret i32 %r
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/non-extern-addend.ll b/test/ExecutionEngine/OrcMCJIT/non-extern-addend.ll
index d768e2b..bb2f7e4 100644
--- a/test/ExecutionEngine/OrcJIT/non-extern-addend.ll
+++ b/test/ExecutionEngine/OrcMCJIT/non-extern-addend.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @foo(i32 %x, i32 %y, double %d) {
 entry:
diff --git a/test/ExecutionEngine/OrcJIT/pr13727.ll b/test/ExecutionEngine/OrcMCJIT/pr13727.ll
index 9c4f10b..a48c573 100644
--- a/test/ExecutionEngine/OrcJIT/pr13727.ll
+++ b/test/ExecutionEngine/OrcMCJIT/pr13727.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -O0 -disable-lazy-compilation=false %s
+; RUN: %lli -jit-kind=orc-mcjit -O0 -disable-lazy-compilation=false %s
 
 ; The intention of this test is to verify that symbols mapped to COMMON in ELF
 ; work as expected.
@@ -31,20 +31,20 @@ entry:
   %retval = alloca i32, align 4
   %i = alloca i32, align 4
   store i32 0, i32* %retval
-  %0 = load i32* @zero_int, align 4
+  %0 = load i32, i32* @zero_int, align 4
   %add = add nsw i32 %0, 5
   %idxprom = sext i32 %add to i64
-  %arrayidx = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom
+  %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom
   store i32 40, i32* %arrayidx, align 4
-  %1 = load double* @zero_double, align 8
+  %1 = load double, double* @zero_double, align 8
   %cmp = fcmp olt double %1, 1.100000e+00
   br i1 %cmp, label %if.then, label %if.end
 
 if.then:                                          ; preds = %entry
-  %2 = load i32* @zero_int, align 4
+  %2 = load i32, i32* @zero_int, align 4
   %add1 = add nsw i32 %2, 2
   %idxprom2 = sext i32 %add1 to i64
-  %arrayidx3 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
+  %arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
   store i32 70, i32* %arrayidx3, align 4
   br label %if.end
 
@@ -53,35 +53,35 @@ if.end:                                           ; preds = %if.then, %entry
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %if.end
-  %3 = load i32* %i, align 4
+  %3 = load i32, i32* %i, align 4
   %cmp4 = icmp slt i32 %3, 10
   br i1 %cmp4, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %sub = sub nsw i32 %4, 1
   %idxprom5 = sext i32 %sub to i64
-  %arrayidx6 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
-  %5 = load i32* %arrayidx6, align 4
-  %6 = load i32* %i, align 4
+  %arrayidx6 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
+  %5 = load i32, i32* %arrayidx6, align 4
+  %6 = load i32, i32* %i, align 4
   %idxprom7 = sext i32 %6 to i64
-  %arrayidx8 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
-  %7 = load i32* %arrayidx8, align 4
+  %arrayidx8 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
+  %7 = load i32, i32* %arrayidx8, align 4
   %add9 = add nsw i32 %5, %7
-  %8 = load i32* %i, align 4
+  %8 = load i32, i32* %i, align 4
   %idxprom10 = sext i32 %8 to i64
-  %arrayidx11 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
+  %arrayidx11 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
   store i32 %add9, i32* %arrayidx11, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %inc = add nsw i32 %9, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %10 = load i32* getelementptr inbounds ([10 x i32]* @zero_arr, i32 0, i64 9), align 4
+  %10 = load i32, i32* getelementptr inbounds ([10 x i32], [10 x i32]* @zero_arr, i32 0, i64 9), align 4
   %cmp12 = icmp eq i32 %10, 110
   %cond = select i1 %cmp12, i32 0, i32 -1
   ret i32 %cond
diff --git a/test/ExecutionEngine/OrcJIT/remote/Inputs/cross-module-b.ll b/test/ExecutionEngine/OrcMCJIT/remote/Inputs/cross-module-b.ll
index bc13b1d..bc13b1d 100644
--- a/test/ExecutionEngine/OrcJIT/remote/Inputs/cross-module-b.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/Inputs/cross-module-b.ll
diff --git a/test/ExecutionEngine/OrcJIT/remote/Inputs/multi-module-b.ll b/test/ExecutionEngine/OrcMCJIT/remote/Inputs/multi-module-b.ll
index 0b8d5eb..0b8d5eb 100644
--- a/test/ExecutionEngine/OrcJIT/remote/Inputs/multi-module-b.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/Inputs/multi-module-b.ll
diff --git a/test/ExecutionEngine/OrcJIT/remote/Inputs/multi-module-c.ll b/test/ExecutionEngine/OrcMCJIT/remote/Inputs/multi-module-c.ll
index 98350a8..98350a8 100644
--- a/test/ExecutionEngine/OrcJIT/remote/Inputs/multi-module-c.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/Inputs/multi-module-c.ll
diff --git a/test/ExecutionEngine/OrcMCJIT/remote/cross-module-a.ll b/test/ExecutionEngine/OrcMCJIT/remote/cross-module-a.ll
new file mode 100644
index 0000000..16553eb
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/remote/cross-module-a.ll
@@ -0,0 +1,12 @@
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/cross-module-b.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
+
+declare i32 @FB()
+
+define i32 @FA() nounwind {
+  ret i32 0
+}
+
+define i32 @main() nounwind {
+  %r = call i32 @FB( )   ; <i32> [#uses=1]
+  ret i32 %r
+}
diff --git a/test/ExecutionEngine/OrcMCJIT/remote/cross-module-sm-pic-a.ll b/test/ExecutionEngine/OrcMCJIT/remote/cross-module-sm-pic-a.ll
new file mode 100644
index 0000000..c897904
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/remote/cross-module-sm-pic-a.ll
@@ -0,0 +1,14 @@
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/cross-module-b.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext -relocation-model=pic -code-model=small %s > /dev/null
+; XFAIL: mips, i686, i386, arm
+
+declare i32 @FB()
+
+define i32 @FA() {
+  ret i32 0
+}
+
+define i32 @main() {
+  %r = call i32 @FB( )   ; <i32> [#uses=1]
+  ret i32 %r
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/remote/lit.local.cfg b/test/ExecutionEngine/OrcMCJIT/remote/lit.local.cfg
index 625d82d..625d82d 100644
--- a/test/ExecutionEngine/OrcJIT/remote/lit.local.cfg
+++ b/test/ExecutionEngine/OrcMCJIT/remote/lit.local.cfg
diff --git a/test/ExecutionEngine/OrcMCJIT/remote/multi-module-a.ll b/test/ExecutionEngine/OrcMCJIT/remote/multi-module-a.ll
new file mode 100644
index 0000000..aa34348
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/remote/multi-module-a.ll
@@ -0,0 +1,9 @@
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
+
+declare i32 @FB()
+
+define i32 @main() nounwind {
+  %r = call i32 @FB( )   ; <i32> [#uses=1]
+  ret i32 %r
+}
+
diff --git a/test/ExecutionEngine/OrcMCJIT/remote/multi-module-sm-pic-a.ll b/test/ExecutionEngine/OrcMCJIT/remote/multi-module-sm-pic-a.ll
new file mode 100644
index 0000000..41812d2
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/remote/multi-module-sm-pic-a.ll
@@ -0,0 +1,10 @@
+; RUN: %lli -jit-kind=orc-mcjit -extra-module=%p/Inputs/multi-module-b.ll -extra-module=%p/Inputs/multi-module-c.ll -disable-lazy-compilation=true -remote-mcjit -mcjit-remote-process=lli-child-target%exeext -relocation-model=pic -code-model=small %s > /dev/null
+; XFAIL: mips, i686, i386, arm
+
+declare i32 @FB()
+
+define i32 @main() {
+  %r = call i32 @FB( )   ; <i32> [#uses=1]
+  ret i32 %r
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/remote/simpletest-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/simpletest-remote.ll
index 30b4dd8..45e11fc 100644
--- a/test/ExecutionEngine/OrcJIT/remote/simpletest-remote.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/simpletest-remote.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
 
 define i32 @bar() nounwind {
 	ret i32 0
diff --git a/test/ExecutionEngine/OrcJIT/remote/stubs-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/stubs-remote.ll
index da4ddc6..aeff011 100644
--- a/test/ExecutionEngine/OrcJIT/remote/stubs-remote.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/stubs-remote.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -remote-mcjit -disable-lazy-compilation=false -mcjit-remote-process=lli-child-target%exeext %s
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -disable-lazy-compilation=false -mcjit-remote-process=lli-child-target%exeext %s
 ; XFAIL: *
 ; This test should fail until remote symbol resolution is supported.
 
@@ -21,14 +21,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/OrcJIT/remote/stubs-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/remote/stubs-sm-pic.ll
index f6a1607..a67edba 100644
--- a/test/ExecutionEngine/OrcJIT/remote/stubs-sm-pic.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/stubs-sm-pic.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -remote-mcjit -disable-lazy-compilation=false -relocation-model=pic -code-model=small %s
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -disable-lazy-compilation=false -relocation-model=pic -code-model=small %s
 ; XFAIL: *
 ; This function should fail until remote symbol resolution is supported.
 
@@ -21,14 +21,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-common-symbols-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-common-symbols-remote.ll
index 0f58710..7e4dc05 100644
--- a/test/ExecutionEngine/OrcJIT/remote/test-common-symbols-remote.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-common-symbols-remote.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -remote-mcjit -O0 -disable-lazy-compilation=false -mcjit-remote-process=lli-child-target%exeext %s
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -O0 -disable-lazy-compilation=false -mcjit-remote-process=lli-child-target%exeext %s
 
 ; The intention of this test is to verify that symbols mapped to COMMON in ELF
 ; work as expected.
@@ -31,20 +31,20 @@ entry:
   %retval = alloca i32, align 4
   %i = alloca i32, align 4
   store i32 0, i32* %retval
-  %0 = load i32* @zero_int, align 4
+  %0 = load i32, i32* @zero_int, align 4
   %add = add nsw i32 %0, 5
   %idxprom = sext i32 %add to i64
-  %arrayidx = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom
+  %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom
   store i32 40, i32* %arrayidx, align 4
-  %1 = load double* @zero_double, align 8
+  %1 = load double, double* @zero_double, align 8
   %cmp = fcmp olt double %1, 1.000000e+00
   br i1 %cmp, label %if.then, label %if.end
 
 if.then:                                          ; preds = %entry
-  %2 = load i32* @zero_int, align 4
+  %2 = load i32, i32* @zero_int, align 4
   %add1 = add nsw i32 %2, 2
   %idxprom2 = sext i32 %add1 to i64
-  %arrayidx3 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
+  %arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
   store i32 70, i32* %arrayidx3, align 4
   br label %if.end
 
@@ -53,35 +53,35 @@ if.end:                                           ; preds = %if.then, %entry
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %if.end
-  %3 = load i32* %i, align 4
+  %3 = load i32, i32* %i, align 4
   %cmp4 = icmp slt i32 %3, 10
   br i1 %cmp4, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %sub = sub nsw i32 %4, 1
   %idxprom5 = sext i32 %sub to i64
-  %arrayidx6 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
-  %5 = load i32* %arrayidx6, align 4
-  %6 = load i32* %i, align 4
+  %arrayidx6 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
+  %5 = load i32, i32* %arrayidx6, align 4
+  %6 = load i32, i32* %i, align 4
   %idxprom7 = sext i32 %6 to i64
-  %arrayidx8 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
-  %7 = load i32* %arrayidx8, align 4
+  %arrayidx8 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
+  %7 = load i32, i32* %arrayidx8, align 4
   %add9 = add nsw i32 %5, %7
-  %8 = load i32* %i, align 4
+  %8 = load i32, i32* %i, align 4
   %idxprom10 = sext i32 %8 to i64
-  %arrayidx11 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
+  %arrayidx11 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
   store i32 %add9, i32* %arrayidx11, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %inc = add nsw i32 %9, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %10 = load i32* getelementptr inbounds ([10 x i32]* @zero_arr, i32 0, i64 9), align 4
+  %10 = load i32, i32* getelementptr inbounds ([10 x i32], [10 x i32]* @zero_arr, i32 0, i64 9), align 4
   %cmp12 = icmp eq i32 %10, 110
   %cond = select i1 %cmp12, i32 0, i32 -1
   ret i32 %cond
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-data-align-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-data-align-remote.ll
index 435c21a..95c9b82 100644
--- a/test/ExecutionEngine/OrcJIT/remote/test-data-align-remote.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-data-align-remote.ll
@@ -1,4 +1,4 @@
-; RUN:  %lli -remote-mcjit -O0 -mcjit-remote-process=lli-child-target%exeext %s
+; RUN:  %lli -jit-kind=orc-mcjit -remote-mcjit -O0 -mcjit-remote-process=lli-child-target%exeext %s
 
 ; Check that a variable is always aligned as specified.
 
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-fp-no-external-funcs-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-fp-no-external-funcs-remote.ll
index 9d11415..2867103 100644
--- a/test/ExecutionEngine/OrcJIT/remote/test-fp-no-external-funcs-remote.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-fp-no-external-funcs-remote.ll
@@ -1,7 +1,7 @@
-; RUN: %lli -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
 
 define double @test(double* %DP, double %Arg) nounwind {
-	%D = load double* %DP		; <double> [#uses=1]
+	%D = load double, double* %DP		; <double> [#uses=1]
 	%V = fadd double %D, 1.000000e+00		; <double> [#uses=2]
 	%W = fsub double %V, %V		; <double> [#uses=3]
 	%X = fmul double %W, %W		; <double> [#uses=2]
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-global-init-nonzero-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-global-init-nonzero-remote.ll
index 40b514f..5dabb8f 100644
--- a/test/ExecutionEngine/OrcJIT/remote/test-global-init-nonzero-remote.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-global-init-nonzero-remote.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -mcjit-remote-process=lli-child-target%exeext %s > /dev/null
 
 @count = global i32 1, align 4
 
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/OrcJIT/remote/test-global-init-nonzero-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-global-init-nonzero-sm-pic.ll
index 5119b72..ec9e1ae 100644
--- a/test/ExecutionEngine/OrcJIT/remote/test-global-init-nonzero-sm-pic.ll
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-global-init-nonzero-sm-pic.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -remote-mcjit -relocation-model=pic -code-model=small %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -relocation-model=pic -code-model=small %s > /dev/null
 ; XFAIL: mips, aarch64, arm, i686, i386
 
 @count = global i32 1, align 4
@@ -12,24 +12,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/OrcMCJIT/remote/test-ptr-reloc-remote.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-ptr-reloc-remote.ll
new file mode 100644
index 0000000..aa07db9
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-ptr-reloc-remote.ll
@@ -0,0 +1,15 @@
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -O0 -mcjit-remote-process=lli-child-target%exeext %s
+
+@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
+@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
+
+define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
+entry:
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
+  %cmp = icmp eq i8* %0, %1
+  %. = zext i1 %cmp to i32
+  ret i32 %.
+}
diff --git a/test/ExecutionEngine/OrcMCJIT/remote/test-ptr-reloc-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/remote/test-ptr-reloc-sm-pic.ll
new file mode 100644
index 0000000..61321ac
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/remote/test-ptr-reloc-sm-pic.ll
@@ -0,0 +1,17 @@
+; RUN: %lli -jit-kind=orc-mcjit -remote-mcjit -O0 -relocation-model=pic -code-model=small %s
+; XFAIL: mips, aarch64, arm, i686, i386
+
+@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
+@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
+
+define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
+entry:
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
+  %cmp = icmp eq i8* %0, %1
+  %. = zext i1 %cmp to i32
+  ret i32 %.
+}
+
diff --git a/test/ExecutionEngine/OrcMCJIT/simplesttest.ll b/test/ExecutionEngine/OrcMCJIT/simplesttest.ll
new file mode 100644
index 0000000..4a47131
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/simplesttest.ll
@@ -0,0 +1,6 @@
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
+
+define i32 @main() {
+	ret i32 0
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/simpletest.ll b/test/ExecutionEngine/OrcMCJIT/simpletest.ll
index e99f615..be1148b 100644
--- a/test/ExecutionEngine/OrcJIT/simpletest.ll
+++ b/test/ExecutionEngine/OrcMCJIT/simpletest.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @bar() {
 	ret i32 0
diff --git a/test/ExecutionEngine/OrcJIT/stubs-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/stubs-sm-pic.ll
index 28f8a76..f354a0d 100644
--- a/test/ExecutionEngine/OrcJIT/stubs-sm-pic.ll
+++ b/test/ExecutionEngine/OrcMCJIT/stubs-sm-pic.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -disable-lazy-compilation=false -relocation-model=pic -code-model=small %s
+; RUN: %lli -jit-kind=orc-mcjit -disable-lazy-compilation=false -relocation-model=pic -code-model=small %s
 ; XFAIL: mips, i686, i386, aarch64, arm
 
 define i32 @main() nounwind {
@@ -20,14 +20,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/OrcJIT/stubs.ll b/test/ExecutionEngine/OrcMCJIT/stubs.ll
index ec3c458..c096f5f 100644
--- a/test/ExecutionEngine/OrcJIT/stubs.ll
+++ b/test/ExecutionEngine/OrcMCJIT/stubs.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -disable-lazy-compilation=false %s
+; RUN: %lli -jit-kind=orc-mcjit -disable-lazy-compilation=false %s
 
 define i32 @main() nounwind {
 entry:
@@ -19,14 +19,14 @@ entry:
 pass_block:
 	ret void
 fail_block:
-	call i32 @puts(i8* getelementptr([46 x i8]* @lcaic_failure, i32 0, i32 0))
+	call i32 @puts(i8* getelementptr([46 x i8], [46 x i8]* @lcaic_failure, i32 0, i32 0))
 	call void @exit(i32 1)
 	unreachable
 }
 
 define i1 @test() nounwind {
 entry:
-	%tmp = load i1 ()** @funcPtr
+	%tmp = load i1 ()*, i1 ()** @funcPtr
 	%eq = icmp eq i1 ()* %tmp, @test
 	ret i1 %eq
 }
diff --git a/test/ExecutionEngine/OrcJIT/test-arith.ll b/test/ExecutionEngine/OrcMCJIT/test-arith.ll
index b662567..c4331bf 100644
--- a/test/ExecutionEngine/OrcJIT/test-arith.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-arith.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 	%A = add i8 0, 12		; <i8> [#uses=1]
diff --git a/test/ExecutionEngine/OrcJIT/test-branch.ll b/test/ExecutionEngine/OrcMCJIT/test-branch.ll
index b66cfaf..b3ef86a 100644
--- a/test/ExecutionEngine/OrcJIT/test-branch.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-branch.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; test unconditional branch
 define i32 @main() {
diff --git a/test/ExecutionEngine/OrcJIT/test-call-no-external-funcs.ll b/test/ExecutionEngine/OrcMCJIT/test-call-no-external-funcs.ll
index c536efe..78c6a1b 100644
--- a/test/ExecutionEngine/OrcJIT/test-call-no-external-funcs.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-call-no-external-funcs.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @_Z14func_exit_codev() nounwind uwtable {
 entry:
diff --git a/test/ExecutionEngine/OrcJIT/test-call.ll b/test/ExecutionEngine/OrcMCJIT/test-call.ll
index 8f50bdc..5345856 100644
--- a/test/ExecutionEngine/OrcJIT/test-call.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-call.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 declare void @exit(i32)
 
diff --git a/test/ExecutionEngine/OrcJIT/test-cast.ll b/test/ExecutionEngine/OrcMCJIT/test-cast.ll
index 4efd760..f1a521f 100644
--- a/test/ExecutionEngine/OrcJIT/test-cast.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-cast.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @foo() {
 	ret i32 0
diff --git a/test/ExecutionEngine/OrcJIT/test-common-symbols-alignment.ll b/test/ExecutionEngine/OrcMCJIT/test-common-symbols-alignment.ll
index 35349e3..cfbd276 100644
--- a/test/ExecutionEngine/OrcJIT/test-common-symbols-alignment.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-common-symbols-alignment.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -O0 %s
+; RUN: %lli -jit-kind=orc-mcjit -O0 %s
 
 ; This test checks that common symbols have been allocated addresses honouring
 ; the alignment requirement.
@@ -13,7 +13,7 @@ entry:
     %ptr = alloca i32, align 4
     store i32 0, i32* %retval
     store i32 ptrtoint (i32* @CS3 to i32), i32* %ptr, align 4
-    %0 = load i32* %ptr, align 4
+    %0 = load i32, i32* %ptr, align 4
     %and = and i32 %0, 15
     %tobool = icmp ne i32 %and, 0
     br i1 %tobool, label %if.then, label %if.else
@@ -27,6 +27,6 @@ if.else:                                          ; preds = %entry
     br label %return
 
 return:                                           ; preds = %if.else, %if.then
-    %1 = load i32* %retval
+    %1 = load i32, i32* %retval
     ret i32 %1
 }
diff --git a/test/ExecutionEngine/OrcJIT/test-common-symbols.ll b/test/ExecutionEngine/OrcMCJIT/test-common-symbols.ll
index 7129e14..db3c047 100644
--- a/test/ExecutionEngine/OrcJIT/test-common-symbols.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-common-symbols.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -O0 -disable-lazy-compilation=false %s
+; RUN: %lli -jit-kind=orc-mcjit -O0 -disable-lazy-compilation=false %s
 
 ; The intention of this test is to verify that symbols mapped to COMMON in ELF
 ; work as expected.
@@ -31,20 +31,20 @@ entry:
   %retval = alloca i32, align 4
   %i = alloca i32, align 4
   store i32 0, i32* %retval
-  %0 = load i32* @zero_int, align 4
+  %0 = load i32, i32* @zero_int, align 4
   %add = add nsw i32 %0, 5
   %idxprom = sext i32 %add to i64
-  %arrayidx = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom
+  %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom
   store i32 40, i32* %arrayidx, align 4
-  %1 = load double* @zero_double, align 8
+  %1 = load double, double* @zero_double, align 8
   %cmp = fcmp olt double %1, 1.000000e+00
   br i1 %cmp, label %if.then, label %if.end
 
 if.then:                                          ; preds = %entry
-  %2 = load i32* @zero_int, align 4
+  %2 = load i32, i32* @zero_int, align 4
   %add1 = add nsw i32 %2, 2
   %idxprom2 = sext i32 %add1 to i64
-  %arrayidx3 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
+  %arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom2
   store i32 70, i32* %arrayidx3, align 4
   br label %if.end
 
@@ -53,35 +53,35 @@ if.end:                                           ; preds = %if.then, %entry
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %if.end
-  %3 = load i32* %i, align 4
+  %3 = load i32, i32* %i, align 4
   %cmp4 = icmp slt i32 %3, 10
   br i1 %cmp4, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %sub = sub nsw i32 %4, 1
   %idxprom5 = sext i32 %sub to i64
-  %arrayidx6 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
-  %5 = load i32* %arrayidx6, align 4
-  %6 = load i32* %i, align 4
+  %arrayidx6 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom5
+  %5 = load i32, i32* %arrayidx6, align 4
+  %6 = load i32, i32* %i, align 4
   %idxprom7 = sext i32 %6 to i64
-  %arrayidx8 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
-  %7 = load i32* %arrayidx8, align 4
+  %arrayidx8 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom7
+  %7 = load i32, i32* %arrayidx8, align 4
   %add9 = add nsw i32 %5, %7
-  %8 = load i32* %i, align 4
+  %8 = load i32, i32* %i, align 4
   %idxprom10 = sext i32 %8 to i64
-  %arrayidx11 = getelementptr inbounds [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
+  %arrayidx11 = getelementptr inbounds [10 x i32], [10 x i32]* @zero_arr, i32 0, i64 %idxprom10
   store i32 %add9, i32* %arrayidx11, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %inc = add nsw i32 %9, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %10 = load i32* getelementptr inbounds ([10 x i32]* @zero_arr, i32 0, i64 9), align 4
+  %10 = load i32, i32* getelementptr inbounds ([10 x i32], [10 x i32]* @zero_arr, i32 0, i64 9), align 4
   %cmp12 = icmp eq i32 %10, 110
   %cond = select i1 %cmp12, i32 0, i32 -1
   ret i32 %cond
diff --git a/test/ExecutionEngine/OrcJIT/test-constantexpr.ll b/test/ExecutionEngine/OrcMCJIT/test-constantexpr.ll
index 380848c..9a147c2 100644
--- a/test/ExecutionEngine/OrcJIT/test-constantexpr.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-constantexpr.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; This tests to make sure that we can evaluate weird constant expressions
 
diff --git a/test/ExecutionEngine/OrcJIT/test-data-align.ll b/test/ExecutionEngine/OrcMCJIT/test-data-align.ll
index f76dda9..f0deb56 100644
--- a/test/ExecutionEngine/OrcJIT/test-data-align.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-data-align.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -O0 %s
+; RUN: %lli -jit-kind=orc-mcjit -O0 %s
 
 ; Check that a variable is always aligned as specified.
 
diff --git a/test/ExecutionEngine/OrcJIT/test-fp-no-external-funcs.ll b/test/ExecutionEngine/OrcMCJIT/test-fp-no-external-funcs.ll
index cf8db4c..2baadcd 100644
--- a/test/ExecutionEngine/OrcJIT/test-fp-no-external-funcs.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-fp-no-external-funcs.ll
@@ -1,7 +1,7 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define double @test(double* %DP, double %Arg) {
-	%D = load double* %DP		; <double> [#uses=1]
+	%D = load double, double* %DP		; <double> [#uses=1]
 	%V = fadd double %D, 1.000000e+00		; <double> [#uses=2]
 	%W = fsub double %V, %V		; <double> [#uses=3]
 	%X = fmul double %W, %W		; <double> [#uses=2]
diff --git a/test/ExecutionEngine/OrcJIT/test-fp.ll b/test/ExecutionEngine/OrcMCJIT/test-fp.ll
index 77a4c7e..6d56e69 100644
--- a/test/ExecutionEngine/OrcJIT/test-fp.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-fp.ll
@@ -1,7 +1,7 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define double @test(double* %DP, double %Arg) {
-	%D = load double* %DP		; <double> [#uses=1]
+	%D = load double, double* %DP		; <double> [#uses=1]
 	%V = fadd double %D, 1.000000e+00		; <double> [#uses=2]
 	%W = fsub double %V, %V		; <double> [#uses=3]
 	%X = fmul double %W, %W		; <double> [#uses=2]
diff --git a/test/ExecutionEngine/OrcJIT/test-global-ctors.ll b/test/ExecutionEngine/OrcMCJIT/test-global-ctors.ll
index bb00af6..d66efc2 100644
--- a/test/ExecutionEngine/OrcJIT/test-global-ctors.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-global-ctors.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 ; XFAIL: darwin
 @var = global i32 1, align 4
 @llvm.global_ctors = appending global [1 x { i32, void ()* }] [{ i32, void ()* } { i32 65535, void ()* @ctor_func }]
@@ -6,7 +6,7 @@
 
 define i32 @main() nounwind {
 entry:
-  %0 = load i32* @var, align 4
+  %0 = load i32, i32* @var, align 4
   ret i32 %0
 }
 
diff --git a/test/ExecutionEngine/OrcJIT/test-global-init-nonzero-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/test-global-init-nonzero-sm-pic.ll
index c8ef597..7f66aec 100644
--- a/test/ExecutionEngine/OrcJIT/test-global-init-nonzero-sm-pic.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-global-init-nonzero-sm-pic.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit -relocation-model=pic -code-model=small %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit -relocation-model=pic -code-model=small %s > /dev/null
 ; XFAIL: mips, aarch64, arm, i686, i386
 
 @count = global i32 1, align 4
@@ -12,24 +12,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/OrcJIT/test-global-init-nonzero.ll b/test/ExecutionEngine/OrcMCJIT/test-global-init-nonzero.ll
index 46b721d..f8d43bf 100644
--- a/test/ExecutionEngine/OrcJIT/test-global-init-nonzero.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-global-init-nonzero.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 @count = global i32 1, align 4
 
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 49
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/OrcJIT/test-global.ll b/test/ExecutionEngine/OrcMCJIT/test-global.ll
index 5ece354..3e42cae 100644
--- a/test/ExecutionEngine/OrcJIT/test-global.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-global.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 @count = global i32 0, align 4
 
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 50
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* @count, align 4
+  %1 = load i32, i32* @count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* @count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* @count, align 4
+  %3 = load i32, i32* @count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/OrcJIT/test-loadstore.ll b/test/ExecutionEngine/OrcMCJIT/test-loadstore.ll
index 24ddd7a..d95d61a 100644
--- a/test/ExecutionEngine/OrcJIT/test-loadstore.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-loadstore.ll
@@ -1,13 +1,13 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define void @test(i8* %P, i16* %P.upgrd.1, i32* %P.upgrd.2, i64* %P.upgrd.3) {
-	%V = load i8* %P		; <i8> [#uses=1]
+	%V = load i8, i8* %P		; <i8> [#uses=1]
 	store i8 %V, i8* %P
-	%V.upgrd.4 = load i16* %P.upgrd.1		; <i16> [#uses=1]
+	%V.upgrd.4 = load i16, i16* %P.upgrd.1		; <i16> [#uses=1]
 	store i16 %V.upgrd.4, i16* %P.upgrd.1
-	%V.upgrd.5 = load i32* %P.upgrd.2		; <i32> [#uses=1]
+	%V.upgrd.5 = load i32, i32* %P.upgrd.2		; <i32> [#uses=1]
 	store i32 %V.upgrd.5, i32* %P.upgrd.2
-	%V.upgrd.6 = load i64* %P.upgrd.3		; <i64> [#uses=1]
+	%V.upgrd.6 = load i64, i64* %P.upgrd.3		; <i64> [#uses=1]
 	store i64 %V.upgrd.6, i64* %P.upgrd.3
 	ret void
 }
@@ -16,7 +16,7 @@ define i32 @varalloca(i32 %Size) {
         ;; Variable sized alloca
 	%X = alloca i32, i32 %Size		; <i32*> [#uses=2]
 	store i32 %Size, i32* %X
-	%Y = load i32* %X		; <i32> [#uses=1]
+	%Y = load i32, i32* %X		; <i32> [#uses=1]
 	ret i32 %Y
 }
 
diff --git a/test/ExecutionEngine/OrcJIT/test-local.ll b/test/ExecutionEngine/OrcMCJIT/test-local.ll
index b541650..1e63d9f 100644
--- a/test/ExecutionEngine/OrcJIT/test-local.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-local.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() nounwind uwtable {
 entry:
@@ -11,24 +11,24 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 50
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %count, align 4
+  %1 = load i32, i32* %count, align 4
   %inc = add nsw i32 %1, 1
   store i32 %inc, i32* %count, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body
-  %2 = load i32* %i, align 4
+  %2 = load i32, i32* %i, align 4
   %inc1 = add nsw i32 %2, 1
   store i32 %inc1, i32* %i, align 4
   br label %for.cond
 
 for.end:                                          ; preds = %for.cond
-  %3 = load i32* %count, align 4
+  %3 = load i32, i32* %count, align 4
   %sub = sub nsw i32 %3, 50
   ret i32 %sub
 }
diff --git a/test/ExecutionEngine/OrcJIT/test-logical.ll b/test/ExecutionEngine/OrcMCJIT/test-logical.ll
index aa8e5de..9d53ac9 100644
--- a/test/ExecutionEngine/OrcJIT/test-logical.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-logical.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 	%A = and i8 4, 8		; <i8> [#uses=2]
diff --git a/test/ExecutionEngine/OrcJIT/test-loop.ll b/test/ExecutionEngine/OrcMCJIT/test-loop.ll
index 5cb9353..dfb62d3 100644
--- a/test/ExecutionEngine/OrcJIT/test-loop.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-loop.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 ; <label>:0
diff --git a/test/ExecutionEngine/OrcJIT/test-phi.ll b/test/ExecutionEngine/OrcMCJIT/test-phi.ll
index 880a916..70bf8c8 100644
--- a/test/ExecutionEngine/OrcJIT/test-phi.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-phi.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; test phi node
 @Y = global i32 6		; <i32*> [#uses=1]
diff --git a/test/ExecutionEngine/OrcMCJIT/test-ptr-reloc-sm-pic.ll b/test/ExecutionEngine/OrcMCJIT/test-ptr-reloc-sm-pic.ll
new file mode 100644
index 0000000..6e0a425
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/test-ptr-reloc-sm-pic.ll
@@ -0,0 +1,17 @@
+; RUN: %lli -jit-kind=orc-mcjit -O0 -relocation-model=pic -code-model=small %s
+; XFAIL: mips, aarch64, arm, i686, i386
+
+@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
+@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
+
+define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
+entry:
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
+  %cmp = icmp eq i8* %0, %1
+  %. = zext i1 %cmp to i32
+  ret i32 %.
+}
+
diff --git a/test/ExecutionEngine/OrcMCJIT/test-ptr-reloc.ll b/test/ExecutionEngine/OrcMCJIT/test-ptr-reloc.ll
new file mode 100644
index 0000000..a3846aa
--- /dev/null
+++ b/test/ExecutionEngine/OrcMCJIT/test-ptr-reloc.ll
@@ -0,0 +1,16 @@
+; RUN: %lli -jit-kind=orc-mcjit -O0 %s
+
+@.str = private unnamed_addr constant [6 x i8] c"data1\00", align 1
+@ptr = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i32 0, i32 0), align 4
+@.str1 = private unnamed_addr constant [6 x i8] c"data2\00", align 1
+@ptr2 = global i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str1, i32 0, i32 0), align 4
+
+define i32 @main(i32 %argc, i8** nocapture %argv) nounwind readonly {
+entry:
+  %0 = load i8*, i8** @ptr, align 4
+  %1 = load i8*, i8** @ptr2, align 4
+  %cmp = icmp eq i8* %0, %1
+  %. = zext i1 %cmp to i32
+  ret i32 %.
+}
+
diff --git a/test/ExecutionEngine/OrcJIT/test-ret.ll b/test/ExecutionEngine/OrcMCJIT/test-ret.ll
index 71ff452..000bea0 100644
--- a/test/ExecutionEngine/OrcJIT/test-ret.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-ret.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 ; test return instructions
 define void @test1() {
diff --git a/test/ExecutionEngine/OrcJIT/test-return.ll b/test/ExecutionEngine/OrcMCJIT/test-return.ll
index 07e74b0..f7a1cdd 100644
--- a/test/ExecutionEngine/OrcJIT/test-return.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-return.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() nounwind uwtable {
 entry:
diff --git a/test/ExecutionEngine/OrcJIT/test-setcond-fp.ll b/test/ExecutionEngine/OrcMCJIT/test-setcond-fp.ll
index d708b90..8514c8d 100644
--- a/test/ExecutionEngine/OrcJIT/test-setcond-fp.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-setcond-fp.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 
 define i32 @main() {
diff --git a/test/ExecutionEngine/OrcJIT/test-setcond-int.ll b/test/ExecutionEngine/OrcMCJIT/test-setcond-int.ll
index b801d97..2f63d0b 100644
--- a/test/ExecutionEngine/OrcJIT/test-setcond-int.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-setcond-int.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 	%int1 = add i32 0, 0		; <i32> [#uses=6]
diff --git a/test/ExecutionEngine/OrcJIT/test-shift.ll b/test/ExecutionEngine/OrcMCJIT/test-shift.ll
index 500987c..2d06421 100644
--- a/test/ExecutionEngine/OrcJIT/test-shift.ll
+++ b/test/ExecutionEngine/OrcMCJIT/test-shift.ll
@@ -1,4 +1,4 @@
-; RUN: %lli -use-orcmcjit %s > /dev/null
+; RUN: %lli -jit-kind=orc-mcjit %s > /dev/null
 
 define i32 @main() {
 	%shamt = add i8 0, 1		; <i8> [#uses=8]
diff --git a/test/ExecutionEngine/RuntimeDyld/X86/COFF_x86_64 b/test/ExecutionEngine/RuntimeDyld/X86/COFF_x86_64
new file mode 100644
index 0000000..7029cf4
--- /dev/null
+++ b/test/ExecutionEngine/RuntimeDyld/X86/COFF_x86_64
@@ -0,0 +1,31 @@
+# RUN: llvm-mc -triple=x86_64-pc-win32 -filetype=obj -o %T/COFF_x86_64.o %s
+# RUN: llvm-rtdyld -triple=x86_64-pc-win32 -verify -check=%s %/T/COFF_x86_64.o
+        	.text
+	.def	 F;
+	.scl	2;
+	.type	32;
+	.endef
+	.globl	__real400921f9f01b866e
+	.section	.rdata,"dr",discard,__real400921f9f01b866e
+	.align	8
+__real400921f9f01b866e:
+	.quad	4614256650576692846     # double 3.1415899999999999
+	.text
+	.globl	F
+        .global inst1
+	.align	16, 0x90
+F:                                      # @F
+.Ltmp0:
+.seh_proc F
+# BB#0:                                 # %entry
+.Ltmp1:
+	.seh_endprologue
+# rtdyld-check: decode_operand(inst1, 4) = __real400921f9f01b866e - next_pc(inst1)
+inst1:
+	movsd	__real400921f9f01b866e(%rip), %xmm0 # xmm0 = mem[0],zero
+	retq
+.Leh_func_end0:
+.Ltmp2:
+	.seh_endproc
+
+
diff --git a/test/ExecutionEngine/fma3-jit.ll b/test/ExecutionEngine/fma3-jit.ll
index 25eaa65..fe62854 100644
--- a/test/ExecutionEngine/fma3-jit.ll
+++ b/test/ExecutionEngine/fma3-jit.ll
@@ -9,7 +9,7 @@ declare i32 @printf(i8*, ...)
 define i32 @main() {
   %fma = tail call double @llvm.fma.f64(double 3.0, double 3.0, double 3.0) nounwind readnone
 
-  %ptr1 = getelementptr [4 x i8]* @msg_double, i32 0, i32 0
+  %ptr1 = getelementptr [4 x i8], [4 x i8]* @msg_double, i32 0, i32 0
   call i32 (i8*,...)* @printf(i8* %ptr1, double %fma)
 
   ret i32 0
diff --git a/test/ExecutionEngine/frem.ll b/test/ExecutionEngine/frem.ll
index ce83d20..2276677 100644
--- a/test/ExecutionEngine/frem.ll
+++ b/test/ExecutionEngine/frem.ll
@@ -11,10 +11,10 @@ declare i32 @printf(i8* nocapture, ...) nounwind
 declare i32 @fflush(i8*) nounwind
 
 define i32 @main() {
-  %flt = load float* @flt
+  %flt = load float, float* @flt
   %float2 = frem float %flt, 5.0
   %double1 = fpext float %float2 to double
-  call i32 (i8*, ...)* @printf(i8* getelementptr ([18 x i8]* @str, i32 0, i64 0), double %double1)
+  call i32 (i8*, ...)* @printf(i8* getelementptr ([18 x i8], [18 x i8]* @str, i32 0, i64 0), double %double1)
   call i32 @fflush(i8* null)
   ret i32 0
 }
diff --git a/test/ExecutionEngine/test-interp-vec-loadstore.ll b/test/ExecutionEngine/test-interp-vec-loadstore.ll
index 665a135..6819724 100644
--- a/test/ExecutionEngine/test-interp-vec-loadstore.ll
+++ b/test/ExecutionEngine/test-interp-vec-loadstore.ll
@@ -35,13 +35,13 @@ define i32 @main() {
   store i32 4, i32* %pint_3
   
   ; load stored scalars
-  %val_int0 = load i32* %pint_0
-  %val_int1 = load i32* %pint_1
-  %val_int2 = load i32* %pint_2
-  %val_int3 = load i32* %pint_3
+  %val_int0 = load i32, i32* %pint_0
+  %val_int1 = load i32, i32* %pint_1
+  %val_int2 = load i32, i32* %pint_2
+  %val_int3 = load i32, i32* %pint_3
 
   ; load stored vector
-  %val0 = load <4 x i32> *%a, align 16
+  %val0 = load <4 x i32> , <4 x i32> *%a, align 16
 
   ; extract integers from the loaded vector
   %res_i32_0 = extractelement <4 x i32> %val0, i32 0
@@ -72,7 +72,7 @@ define i32 @main() {
   ; if TRUE print message
   br i1 %res_i, label %Print_int, label %Double
 Print_int:
-  %ptr0 = getelementptr [17 x i8]* @msg_int, i32 0, i32 0
+  %ptr0 = getelementptr [17 x i8], [17 x i8]* @msg_int, i32 0, i32 0
   call i32 (i8*,...)* @printf(i8* %ptr0)
   br label %Double
 Double:
@@ -84,12 +84,12 @@ Double:
   store double 8.0, double* %pdouble_3
 
   ; load stored vector
-  %val1 = load <4 x double> *%b, align 16
+  %val1 = load <4 x double> , <4 x double> *%b, align 16
   ; load stored scalars
-  %val_double0 = load double* %pdouble_0
-  %val_double1 = load double* %pdouble_1
-  %val_double2 = load double* %pdouble_2
-  %val_double3 = load double* %pdouble_3
+  %val_double0 = load double, double* %pdouble_0
+  %val_double1 = load double, double* %pdouble_1
+  %val_double2 = load double, double* %pdouble_2
+  %val_double3 = load double, double* %pdouble_3
 
   %res_double_0 = extractelement <4 x double> %val1, i32 0
   %res_double_1 = extractelement <4 x double> %val1, i32 1
@@ -116,7 +116,7 @@ Double:
 
   br i1 %res_double, label %Print_double, label %Float
 Print_double:
-  %ptr1 = getelementptr [20 x i8]* @msg_double, i32 0, i32 0
+  %ptr1 = getelementptr [20 x i8], [20 x i8]* @msg_double, i32 0, i32 0
   call i32 (i8*,...)* @printf(i8* %ptr1)
   br label %Float
 Float:
@@ -128,12 +128,12 @@ Float:
   store float 12.0, float* %pfloat_3
 
   ; load stored vector
-  %val2 = load <4 x float> *%c, align 16
+  %val2 = load <4 x float> , <4 x float> *%c, align 16
   ; load stored scalars
-  %val_float0 = load float* %pfloat_0
-  %val_float1 = load float* %pfloat_1
-  %val_float2 = load float* %pfloat_2
-  %val_float3 = load float* %pfloat_3
+  %val_float0 = load float, float* %pfloat_0
+  %val_float1 = load float, float* %pfloat_1
+  %val_float2 = load float, float* %pfloat_2
+  %val_float3 = load float, float* %pfloat_3
 
   %res_float_0 = extractelement <4 x float> %val2, i32 0
   %res_float_1 = extractelement <4 x float> %val2, i32 1
@@ -160,7 +160,7 @@ Float:
 
   br i1 %res_float, label %Print_float, label %Exit
 Print_float:
-  %ptr2 = getelementptr [19 x i8]* @msg_float, i32 0, i32 0
+  %ptr2 = getelementptr [19 x i8], [19 x i8]* @msg_float, i32 0, i32 0
   call i32 (i8*,...)* @printf(i8* %ptr2)
   br label %Exit
 Exit: