[SelectionDAGBuilder] Set NoUnsignedWrap for inbounds gep and load/store offsets.
In an inbounds getelementptr, when an index produces a constant non-negative
offset to add to the base, the add can be assumed to not have unsigned overflow.
This relies on the assumption that addresses can't occupy more than half the
address space, which isn't possible in C because it wouldn't be possible to
represent the difference between the start of the object and one-past-the-end
in a ptrdiff_t.
Setting the NoUnsignedWrap flag is theoretically useful in general, and is
specifically useful to the WebAssembly backend, since it permits stronger
constant offset folding.
Differential Revision: http://reviews.llvm.org/D15544
llvm-svn: 256890
diff --git a/llvm/test/CodeGen/WebAssembly/offset.ll b/llvm/test/CodeGen/WebAssembly/offset.ll
index 75a0bc9..901801d 100644
--- a/llvm/test/CodeGen/WebAssembly/offset.ll
+++ b/llvm/test/CodeGen/WebAssembly/offset.ll
@@ -17,6 +17,28 @@
ret i32 %t
}
+; With an inbounds gep, we can fold an offset.
+
+; CHECK-LABEL: load_i32_with_folded_gep_offset:
+; CHECK: i32.load $push0=, 24($0){{$}}
+define i32 @load_i32_with_folded_gep_offset(i32* %p) {
+ %s = getelementptr inbounds i32, i32* %p, i32 6
+ %t = load i32, i32* %s
+ ret i32 %t
+}
+
+; We can't fold a negative offset though, even with an inbounds gep.
+
+; CHECK-LABEL: load_i32_with_unfolded_gep_negative_offset:
+; CHECK: i32.const $push0=, -24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i32.load $push2=, 0($pop1){{$}}
+define i32 @load_i32_with_unfolded_gep_negative_offset(i32* %p) {
+ %s = getelementptr inbounds i32, i32* %p, i32 -6
+ %t = load i32, i32* %s
+ ret i32 %t
+}
+
; Without nuw, and even with nsw, we can't fold an offset.
; CHECK-LABEL: load_i32_with_unfolded_offset:
@@ -31,6 +53,18 @@
ret i32 %t
}
+; Without inbounds, we can't fold a gep offset.
+
+; CHECK-LABEL: load_i32_with_unfolded_gep_offset:
+; CHECK: i32.const $push0=, 24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i32.load $push2=, 0($pop1){{$}}
+define i32 @load_i32_with_unfolded_gep_offset(i32* %p) {
+ %s = getelementptr i32, i32* %p, i32 6
+ %t = load i32, i32* %s
+ ret i32 %t
+}
+
; Same as above but with i64.
; CHECK-LABEL: load_i64_with_folded_offset:
@@ -45,6 +79,28 @@
; Same as above but with i64.
+; CHECK-LABEL: load_i64_with_folded_gep_offset:
+; CHECK: i64.load $push0=, 24($0){{$}}
+define i64 @load_i64_with_folded_gep_offset(i64* %p) {
+ %s = getelementptr inbounds i64, i64* %p, i32 3
+ %t = load i64, i64* %s
+ ret i64 %t
+}
+
+; Same as above but with i64.
+
+; CHECK-LABEL: load_i64_with_unfolded_gep_negative_offset:
+; CHECK: i32.const $push0=, -24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i64.load $push2=, 0($pop1){{$}}
+define i64 @load_i64_with_unfolded_gep_negative_offset(i64* %p) {
+ %s = getelementptr inbounds i64, i64* %p, i32 -3
+ %t = load i64, i64* %s
+ ret i64 %t
+}
+
+; Same as above but with i64.
+
; CHECK-LABEL: load_i64_with_unfolded_offset:
; CHECK: i32.const $push0=, 24{{$}}
; CHECK: i32.add $push1=, $0, $pop0{{$}}
@@ -57,6 +113,18 @@
ret i64 %t
}
+; Same as above but with i64.
+
+; CHECK-LABEL: load_i64_with_unfolded_gep_offset:
+; CHECK: i32.const $push0=, 24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i64.load $push2=, 0($pop1){{$}}
+define i64 @load_i64_with_unfolded_gep_offset(i64* %p) {
+ %s = getelementptr i64, i64* %p, i32 3
+ %t = load i64, i64* %s
+ ret i64 %t
+}
+
; Same as above but with store.
; CHECK-LABEL: store_i32_with_folded_offset:
@@ -71,6 +139,28 @@
; Same as above but with store.
+; CHECK-LABEL: store_i32_with_folded_gep_offset:
+; CHECK: i32.store $discard=, 24($0), $pop0{{$}}
+define void @store_i32_with_folded_gep_offset(i32* %p) {
+ %s = getelementptr inbounds i32, i32* %p, i32 6
+ store i32 0, i32* %s
+ ret void
+}
+
+; Same as above but with store.
+
+; CHECK-LABEL: store_i32_with_unfolded_gep_negative_offset:
+; CHECK: i32.const $push0=, -24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i32.store $discard=, 0($pop1), $pop2{{$}}
+define void @store_i32_with_unfolded_gep_negative_offset(i32* %p) {
+ %s = getelementptr inbounds i32, i32* %p, i32 -6
+ store i32 0, i32* %s
+ ret void
+}
+
+; Same as above but with store.
+
; CHECK-LABEL: store_i32_with_unfolded_offset:
; CHECK: i32.const $push0=, 24{{$}}
; CHECK: i32.add $push1=, $0, $pop0{{$}}
@@ -83,6 +173,18 @@
ret void
}
+; Same as above but with store.
+
+; CHECK-LABEL: store_i32_with_unfolded_gep_offset:
+; CHECK: i32.const $push0=, 24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i32.store $discard=, 0($pop1), $pop2{{$}}
+define void @store_i32_with_unfolded_gep_offset(i32* %p) {
+ %s = getelementptr i32, i32* %p, i32 6
+ store i32 0, i32* %s
+ ret void
+}
+
; Same as above but with store with i64.
; CHECK-LABEL: store_i64_with_folded_offset:
@@ -97,6 +199,28 @@
; Same as above but with store with i64.
+; CHECK-LABEL: store_i64_with_folded_gep_offset:
+; CHECK: i64.store $discard=, 24($0), $pop0{{$}}
+define void @store_i64_with_folded_gep_offset(i64* %p) {
+ %s = getelementptr inbounds i64, i64* %p, i32 3
+ store i64 0, i64* %s
+ ret void
+}
+
+; Same as above but with store with i64.
+
+; CHECK-LABEL: store_i64_with_unfolded_gep_negative_offset:
+; CHECK: i32.const $push0=, -24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i64.store $discard=, 0($pop1), $pop2{{$}}
+define void @store_i64_with_unfolded_gep_negative_offset(i64* %p) {
+ %s = getelementptr inbounds i64, i64* %p, i32 -3
+ store i64 0, i64* %s
+ ret void
+}
+
+; Same as above but with store with i64.
+
; CHECK-LABEL: store_i64_with_unfolded_offset:
; CHECK: i32.const $push0=, 24{{$}}
; CHECK: i32.add $push1=, $0, $pop0{{$}}
@@ -109,6 +233,18 @@
ret void
}
+; Same as above but with store with i64.
+
+; CHECK-LABEL: store_i64_with_unfolded_gep_offset:
+; CHECK: i32.const $push0=, 24{{$}}
+; CHECK: i32.add $push1=, $0, $pop0{{$}}
+; CHECK: i64.store $discard=, 0($pop1), $pop2{{$}}
+define void @store_i64_with_unfolded_gep_offset(i64* %p) {
+ %s = getelementptr i64, i64* %p, i32 3
+ store i64 0, i64* %s
+ ret void
+}
+
; When loading from a fixed address, materialize a zero.
; CHECK-LABEL: load_i32_from_numeric_address
@@ -159,6 +295,17 @@
ret i32 %u
}
+; Fold a gep offset into a sign-extending load.
+
+; CHECK-LABEL: load_i8_s_with_folded_gep_offset:
+; CHECK: i32.load8_s $push0=, 24($0){{$}}
+define i32 @load_i8_s_with_folded_gep_offset(i8* %p) {
+ %s = getelementptr inbounds i8, i8* %p, i32 24
+ %t = load i8, i8* %s
+ %u = sext i8 %t to i32
+ ret i32 %u
+}
+
; Fold an offset into a zero-extending load.
; CHECK-LABEL: load_i8_u_with_folded_offset:
@@ -172,6 +319,17 @@
ret i32 %u
}
+; Fold a gep offset into a zero-extending load.
+
+; CHECK-LABEL: load_i8_u_with_folded_gep_offset:
+; CHECK: i32.load8_u $push0=, 24($0){{$}}
+define i32 @load_i8_u_with_folded_gep_offset(i8* %p) {
+ %s = getelementptr inbounds i8, i8* %p, i32 24
+ %t = load i8, i8* %s
+ %u = zext i8 %t to i32
+ ret i32 %u
+}
+
; Fold an offset into a truncating store.
; CHECK-LABEL: store_i8_with_folded_offset:
@@ -183,3 +341,43 @@
store i8 0, i8* %s
ret void
}
+
+; Fold a gep offset into a truncating store.
+
+; CHECK-LABEL: store_i8_with_folded_gep_offset:
+; CHECK: i32.store8 $discard=, 24($0), $pop0{{$}}
+define void @store_i8_with_folded_gep_offset(i8* %p) {
+ %s = getelementptr inbounds i8, i8* %p, i32 24
+ store i8 0, i8* %s
+ ret void
+}
+
+; Fold the offsets when lowering aggregate loads and stores.
+
+; CHECK-LABEL: aggregate_load_store:
+; CHECK: i32.load $2=, 0($0){{$}}
+; CHECK: i32.load $3=, 4($0){{$}}
+; CHECK: i32.load $4=, 8($0){{$}}
+; CHECK: i32.load $push0=, 12($0){{$}}
+; CHECK: i32.store $discard=, 12($1), $pop0{{$}}
+; CHECK: i32.store $discard=, 8($1), $4{{$}}
+; CHECK: i32.store $discard=, 4($1), $3{{$}}
+; CHECK: i32.store $discard=, 0($1), $2{{$}}
+define void @aggregate_load_store({i32,i32,i32,i32}* %p, {i32,i32,i32,i32}* %q) {
+ ; volatile so that things stay in order for the tests above
+ %t = load volatile {i32,i32,i32,i32}, {i32, i32,i32,i32}* %p
+ store volatile {i32,i32,i32,i32} %t, {i32, i32,i32,i32}* %q
+ ret void
+}
+
+; Fold the offsets when lowering aggregate return values.
+
+; CHECK-LABEL: aggregate_return:
+; CHECK: i32.const $push0=, 0{{$}}
+; CHECK: i32.store $push1=, 12($0), $pop0{{$}}
+; CHECK: i32.store $push2=, 8($0), $pop1{{$}}
+; CHECK: i32.store $push3=, 4($0), $pop2{{$}}
+; CHECK: i32.store $discard=, 0($0), $pop3{{$}}
+define {i32,i32,i32,i32} @aggregate_return() {
+ ret {i32,i32,i32,i32} zeroinitializer
+}