Introduce llvm.load.relative intrinsic.
This intrinsic takes two arguments, ``%ptr`` and ``%offset``. It loads
a 32-bit value from the address ``%ptr + %offset``, adds ``%ptr`` to that
value and returns it. The constant folder specifically recognizes the form of
this intrinsic and the constant initializers it may load from; if a loaded
constant initializer is known to have the form ``i32 trunc(x - %ptr)``,
the intrinsic call is folded to ``x``.
LLVM provides that the calculation of such a constant initializer will
not overflow at link time under the medium code model if ``x`` is an
``unnamed_addr`` function. However, it does not provide this guarantee for
a constant initializer folded into a function body. This intrinsic can be
used to avoid the possibility of overflows when loading from such a constant.
Differential Revision: http://reviews.llvm.org/D18367
llvm-svn: 267223
diff --git a/llvm/test/Transforms/InstSimplify/load-relative-32.ll b/llvm/test/Transforms/InstSimplify/load-relative-32.ll
new file mode 100644
index 0000000..a38de85
--- /dev/null
+++ b/llvm/test/Transforms/InstSimplify/load-relative-32.ll
@@ -0,0 +1,19 @@
+; RUN: opt < %s -instsimplify -S | FileCheck %s
+
+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-n8:16:32"
+target triple = "i386-unknown-linux-gnu"
+
+@a = external global i8
+
+@c1 = constant [3 x i32] [i32 0, i32 0,
+i32 sub (i32 ptrtoint (i8* @a to i32), i32 ptrtoint (i32* getelementptr ([3 x i32], [3 x i32]* @c1, i32 0, i32 2) to i32))
+]
+
+; CHECK: @f1
+define i8* @f1() {
+ ; CHECK: ret i8* @a
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([3 x i32], [3 x i32]* @c1, i32 0, i32 2) to i8*), i32 0)
+ ret i8* %l
+}
+
+declare i8* @llvm.load.relative.i32(i8*, i32)
diff --git a/llvm/test/Transforms/InstSimplify/load-relative.ll b/llvm/test/Transforms/InstSimplify/load-relative.ll
new file mode 100644
index 0000000..3074ede
--- /dev/null
+++ b/llvm/test/Transforms/InstSimplify/load-relative.ll
@@ -0,0 +1,75 @@
+; RUN: opt < %s -instsimplify -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@a = external global i8
+@b = external global i8
+
+@c1 = constant i32 trunc (i64 sub (i64 ptrtoint (i8* @a to i64), i64 ptrtoint (i32* @c1 to i64)) to i32)
+@c2 = constant [7 x i32] [i32 0, i32 0,
+i32 trunc (i64 sub (i64 ptrtoint (i8* @a to i64), i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32),
+i32 trunc (i64 sub (i64 ptrtoint (i8* @b to i64), i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32),
+i32 trunc (i64 add (i64 ptrtoint (i8* @b to i64), i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32),
+i32 trunc (i64 sub (i64 ptrtoint (i8* @b to i64), i64 1) to i32),
+i32 trunc (i64 sub (i64 0, i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32)
+]
+
+; CHECK: @f1
+define i8* @f1() {
+ ; CHECK: ret i8* @a
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* @c1 to i8*), i32 0)
+ ret i8* %l
+}
+
+; CHECK: @f2
+define i8* @f2() {
+ ; CHECK: ret i8* @a
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 0)
+ ret i8* %l
+}
+
+; CHECK: @f3
+define i8* @f3() {
+ ; CHECK: ret i8* @b
+ %l = call i8* @llvm.load.relative.i64(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i64 4)
+ ret i8* %l
+}
+
+; CHECK: @f4
+define i8* @f4() {
+ ; CHECK: ret i8* %
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 1)
+ ret i8* %l
+}
+
+; CHECK: @f5
+define i8* @f5() {
+ ; CHECK: ret i8* %
+ %l = call i8* @llvm.load.relative.i32(i8* zeroinitializer, i32 0)
+ ret i8* %l
+}
+
+; CHECK: @f6
+define i8* @f6() {
+ ; CHECK: ret i8* %
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 8)
+ ret i8* %l
+}
+
+; CHECK: @f7
+define i8* @f7() {
+ ; CHECK: ret i8* %
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 12)
+ ret i8* %l
+}
+
+; CHECK: @f8
+define i8* @f8() {
+ ; CHECK: ret i8* %
+ %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 16)
+ ret i8* %l
+}
+
+declare i8* @llvm.load.relative.i32(i8*, i32)
+declare i8* @llvm.load.relative.i64(i8*, i64)
diff --git a/llvm/test/Transforms/PreISelIntrinsicLowering/load-relative.ll b/llvm/test/Transforms/PreISelIntrinsicLowering/load-relative.ll
new file mode 100644
index 0000000..56bedd9
--- /dev/null
+++ b/llvm/test/Transforms/PreISelIntrinsicLowering/load-relative.ll
@@ -0,0 +1,26 @@
+; RUN: opt -pre-isel-intrinsic-lowering -S -o - %s | FileCheck %s
+
+; CHECK: define i8* @foo32(i8* [[P:%.*]], i32 [[O:%.*]])
+define i8* @foo32(i8* %p, i32 %o) {
+ ; CHECK: [[OP:%.*]] = getelementptr i8, i8* [[P]], i32 [[O]]
+ ; CHECK: [[OPI32:%.*]] = bitcast i8* [[OP]] to i32*
+ ; CHECK: [[OI32:%.*]] = load i32, i32* [[OPI32]], align 4
+ ; CHECK: [[R:%.*]] = getelementptr i8, i8* [[P]], i32 [[OI32]]
+ ; CHECK: ret i8* [[R]]
+ %l = call i8* @llvm.load.relative.i32(i8* %p, i32 %o)
+ ret i8* %l
+}
+
+; CHECK: define i8* @foo64(i8* [[P:%.*]], i64 [[O:%.*]])
+define i8* @foo64(i8* %p, i64 %o) {
+ ; CHECK: [[OP:%.*]] = getelementptr i8, i8* [[P]], i64 [[O]]
+ ; CHECK: [[OPI32:%.*]] = bitcast i8* [[OP]] to i32*
+ ; CHECK: [[OI32:%.*]] = load i32, i32* [[OPI32]], align 4
+ ; CHECK: [[R:%.*]] = getelementptr i8, i8* [[P]], i32 [[OI32]]
+ ; CHECK: ret i8* [[R]]
+ %l = call i8* @llvm.load.relative.i64(i8* %p, i64 %o)
+ ret i8* %l
+}
+
+declare i8* @llvm.load.relative.i32(i8*, i32)
+declare i8* @llvm.load.relative.i64(i8*, i64)