maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/ARM/load-combine.ll

693 lines
22 KiB
LLVM
Raw Normal View History

[DAGCombiner] Match load by bytes idiom and fold it into a single load. Attempt #2. The previous patch (https://reviews.llvm.org/rL289538) got reverted because of a bug. Chandler also requested some changes to the algorithm. http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20161212/413479.html This is an updated patch. The key difference is that collectBitProviders (renamed to calculateByteProvider) now collects the origin of one byte, not the whole value. It simplifies the implementation and allows to stop the traversal earlier if we know that the result won't be used. From the original commit: Match a pattern where a wide type scalar value is loaded by several narrow loads and combined by shifts and ors. Fold it into a single load or a load and a bswap if the targets supports it. Assuming little endian target: i8 *a = ... i32 val = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24) => i32 val = *((i32)a) i8 *a = ... i32 val = (a[0] << 24) | (a[1] << 16) | (a[2] << 8) | a[3] => i32 val = BSWAP(*((i32)a)) This optimization was discussed on llvm-dev some time ago in "Load combine pass" thread. We came to the conclusion that we want to do this transformation late in the pipeline because in presence of atomic loads load widening is irreversible transformation and it might hinder other optimizations. Eventually we'd like to support folding patterns like this where the offset has a variable and a constant part: i32 val = a[i] | (a[i + 1] << 8) | (a[i + 2] << 16) | (a[i + 3] << 24) Matching the pattern above is easier at SelectionDAG level since address reassociation has already happened and the fact that the loads are adjacent is clear. Understanding that these loads are adjacent at IR level would have involved looking through geps/zexts/adds while looking at the addresses. The general scheme is to match OR expressions by recursively calculating the origin of individual bytes which constitute the resulting OR value. If all the OR bytes come from memory verify that they are adjacent and match with little or big endian encoding of a wider value. If so and the load of the wider type (and bswap if needed) is allowed by the target generate a load and a bswap if needed. Reviewed By: RKSimon, filcab, chandlerc Differential Revision: https://reviews.llvm.org/D27861 llvm-svn: 293036
2017-01-25 16:53:31 +08:00
; RUN: llc < %s -mtriple=arm-unknown | FileCheck %s
; RUN: llc < %s -mtriple=armv6-unknown | FileCheck %s --check-prefix=CHECK-ARMv6
; i8* p; // p is 1 byte aligned
; (i32) p[0] | ((i32) p[1] << 8) | ((i32) p[2] << 16) | ((i32) p[3] << 24)
define i32 @load_i32_by_i8_unaligned(i32* %arg) {
; CHECK-LABEL: load_i32_by_i8_unaligned:
; CHECK: ldrb{{.*}}r0
; CHECK: ldrb{{.*}}r0
; CHECK: ldrb{{.*}}r0
; CHECK: ldrb{{.*}}r0
; CHECK: orr
; CHECK: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_unaligned:
; CHECK-ARMv6: ldrb{{.*}}r0
; CHECK-ARMv6: ldrb{{.*}}r0
; CHECK-ARMv6: ldrb{{.*}}r0
; CHECK-ARMv6: ldrb{{.*}}r0
; CHECK-ARMv6: orr
; CHECK-ARMv6: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0
Fix a reoccuring typo in load-combine tests %tmp = bitcast i32* %arg to i8* %tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0 - %tmp2 = load i8, i8* %tmp, align 1 + %tmp2 = load i8, i8* %tmp1, align 1 This doesn't change the semantics of the tests but makes use of %tmp1 which was originally intended. llvm-svn: 328642
2018-03-28 01:33:50 +08:00
%tmp2 = load i8, i8* %tmp1, align 1
[DAGCombiner] Match load by bytes idiom and fold it into a single load. Attempt #2. The previous patch (https://reviews.llvm.org/rL289538) got reverted because of a bug. Chandler also requested some changes to the algorithm. http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20161212/413479.html This is an updated patch. The key difference is that collectBitProviders (renamed to calculateByteProvider) now collects the origin of one byte, not the whole value. It simplifies the implementation and allows to stop the traversal earlier if we know that the result won't be used. From the original commit: Match a pattern where a wide type scalar value is loaded by several narrow loads and combined by shifts and ors. Fold it into a single load or a load and a bswap if the targets supports it. Assuming little endian target: i8 *a = ... i32 val = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24) => i32 val = *((i32)a) i8 *a = ... i32 val = (a[0] << 24) | (a[1] << 16) | (a[2] << 8) | a[3] => i32 val = BSWAP(*((i32)a)) This optimization was discussed on llvm-dev some time ago in "Load combine pass" thread. We came to the conclusion that we want to do this transformation late in the pipeline because in presence of atomic loads load widening is irreversible transformation and it might hinder other optimizations. Eventually we'd like to support folding patterns like this where the offset has a variable and a constant part: i32 val = a[i] | (a[i + 1] << 8) | (a[i + 2] << 16) | (a[i + 3] << 24) Matching the pattern above is easier at SelectionDAG level since address reassociation has already happened and the fact that the loads are adjacent is clear. Understanding that these loads are adjacent at IR level would have involved looking through geps/zexts/adds while looking at the addresses. The general scheme is to match OR expressions by recursively calculating the origin of individual bytes which constitute the resulting OR value. If all the OR bytes come from memory verify that they are adjacent and match with little or big endian encoding of a wider value. If so and the load of the wider type (and bswap if needed) is allowed by the target generate a load and a bswap if needed. Reviewed By: RKSimon, filcab, chandlerc Differential Revision: https://reviews.llvm.org/D27861 llvm-svn: 293036
2017-01-25 16:53:31 +08:00
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 2
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 16
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 3
%tmp15 = load i8, i8* %tmp14, align 1
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = shl nuw nsw i32 %tmp16, 24
%tmp18 = or i32 %tmp13, %tmp17
ret i32 %tmp18
}
; i8* p; // p is 4 byte aligned
; (i32) p[0] | ((i32) p[1] << 8) | ((i32) p[2] << 16) | ((i32) p[3] << 24)
define i32 @load_i32_by_i8_aligned(i32* %arg) {
; CHECK-LABEL: load_i32_by_i8_aligned:
; CHECK: ldr r0, [r0]
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_aligned:
; CHECK-ARMv6: ldr r0, [r0]
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0
Fix a reoccuring typo in load-combine tests %tmp = bitcast i32* %arg to i8* %tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0 - %tmp2 = load i8, i8* %tmp, align 1 + %tmp2 = load i8, i8* %tmp1, align 1 This doesn't change the semantics of the tests but makes use of %tmp1 which was originally intended. llvm-svn: 328642
2018-03-28 01:33:50 +08:00
%tmp2 = load i8, i8* %tmp1, align 4
[DAGCombiner] Match load by bytes idiom and fold it into a single load. Attempt #2. The previous patch (https://reviews.llvm.org/rL289538) got reverted because of a bug. Chandler also requested some changes to the algorithm. http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20161212/413479.html This is an updated patch. The key difference is that collectBitProviders (renamed to calculateByteProvider) now collects the origin of one byte, not the whole value. It simplifies the implementation and allows to stop the traversal earlier if we know that the result won't be used. From the original commit: Match a pattern where a wide type scalar value is loaded by several narrow loads and combined by shifts and ors. Fold it into a single load or a load and a bswap if the targets supports it. Assuming little endian target: i8 *a = ... i32 val = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24) => i32 val = *((i32)a) i8 *a = ... i32 val = (a[0] << 24) | (a[1] << 16) | (a[2] << 8) | a[3] => i32 val = BSWAP(*((i32)a)) This optimization was discussed on llvm-dev some time ago in "Load combine pass" thread. We came to the conclusion that we want to do this transformation late in the pipeline because in presence of atomic loads load widening is irreversible transformation and it might hinder other optimizations. Eventually we'd like to support folding patterns like this where the offset has a variable and a constant part: i32 val = a[i] | (a[i + 1] << 8) | (a[i + 2] << 16) | (a[i + 3] << 24) Matching the pattern above is easier at SelectionDAG level since address reassociation has already happened and the fact that the loads are adjacent is clear. Understanding that these loads are adjacent at IR level would have involved looking through geps/zexts/adds while looking at the addresses. The general scheme is to match OR expressions by recursively calculating the origin of individual bytes which constitute the resulting OR value. If all the OR bytes come from memory verify that they are adjacent and match with little or big endian encoding of a wider value. If so and the load of the wider type (and bswap if needed) is allowed by the target generate a load and a bswap if needed. Reviewed By: RKSimon, filcab, chandlerc Differential Revision: https://reviews.llvm.org/D27861 llvm-svn: 293036
2017-01-25 16:53:31 +08:00
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 2
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 16
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 3
%tmp15 = load i8, i8* %tmp14, align 1
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = shl nuw nsw i32 %tmp16, 24
%tmp18 = or i32 %tmp13, %tmp17
ret i32 %tmp18
}
; i8* p; // p is 4 byte aligned
; ((i32) p[0] << 24) | ((i32) p[1] << 16) | ((i32) p[2] << 8) | (i32) p[3]
define i32 @load_i32_by_i8_bswap(i32* %arg) {
; BSWAP is not supported by 32 bit target
; CHECK-LABEL: load_i32_by_i8_bswap:
; CHECK: ldr r0, [r0]
; CHECK: and
; CHECK-NEXT: and
; CHECK-NEXT: orr
; CHECK-NEXT: orr
; CHECK-NEXT: orr
; CHECK: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_bswap:
; CHECK-ARMv6: ldr r0, [r0]
; CHECK-ARMv6-NEXT: rev r0, r0
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = load i8, i8* %tmp, align 4
%tmp2 = zext i8 %tmp1 to i32
%tmp3 = shl nuw nsw i32 %tmp2, 24
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 16
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 2
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 8
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 3
%tmp15 = load i8, i8* %tmp14, align 1
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = or i32 %tmp13, %tmp16
ret i32 %tmp17
}
; i8* p; // p is 8 byte aligned
; (i64) p[0] | ((i64) p[1] << 8) | ((i64) p[2] << 16) | ((i64) p[3] << 24) | ((i64) p[4] << 32) | ((i64) p[5] << 40) | ((i64) p[6] << 48) | ((i64) p[7] << 56)
define i64 @load_i64_by_i8(i64* %arg) {
; CHECK-LABEL: load_i64_by_i8:
; CHECK: ldr r2, [r0]
; CHECK-NEXT: ldr r1, [r0, #4]
; CHECK-NEXT: mov r0, r2
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i64_by_i8:
; CHECK-ARMv6: ldrd r0, r1, [r0]
; CHECK-ARMv6: bx lr
%tmp = bitcast i64* %arg to i8*
%tmp1 = load i8, i8* %tmp, align 8
%tmp2 = zext i8 %tmp1 to i64
%tmp3 = getelementptr inbounds i8, i8* %tmp, i64 1
%tmp4 = load i8, i8* %tmp3, align 1
%tmp5 = zext i8 %tmp4 to i64
%tmp6 = shl nuw nsw i64 %tmp5, 8
%tmp7 = or i64 %tmp6, %tmp2
%tmp8 = getelementptr inbounds i8, i8* %tmp, i64 2
%tmp9 = load i8, i8* %tmp8, align 1
%tmp10 = zext i8 %tmp9 to i64
%tmp11 = shl nuw nsw i64 %tmp10, 16
%tmp12 = or i64 %tmp7, %tmp11
%tmp13 = getelementptr inbounds i8, i8* %tmp, i64 3
%tmp14 = load i8, i8* %tmp13, align 1
%tmp15 = zext i8 %tmp14 to i64
%tmp16 = shl nuw nsw i64 %tmp15, 24
%tmp17 = or i64 %tmp12, %tmp16
%tmp18 = getelementptr inbounds i8, i8* %tmp, i64 4
%tmp19 = load i8, i8* %tmp18, align 1
%tmp20 = zext i8 %tmp19 to i64
%tmp21 = shl nuw nsw i64 %tmp20, 32
%tmp22 = or i64 %tmp17, %tmp21
%tmp23 = getelementptr inbounds i8, i8* %tmp, i64 5
%tmp24 = load i8, i8* %tmp23, align 1
%tmp25 = zext i8 %tmp24 to i64
%tmp26 = shl nuw nsw i64 %tmp25, 40
%tmp27 = or i64 %tmp22, %tmp26
%tmp28 = getelementptr inbounds i8, i8* %tmp, i64 6
%tmp29 = load i8, i8* %tmp28, align 1
%tmp30 = zext i8 %tmp29 to i64
%tmp31 = shl nuw nsw i64 %tmp30, 48
%tmp32 = or i64 %tmp27, %tmp31
%tmp33 = getelementptr inbounds i8, i8* %tmp, i64 7
%tmp34 = load i8, i8* %tmp33, align 1
%tmp35 = zext i8 %tmp34 to i64
%tmp36 = shl nuw i64 %tmp35, 56
%tmp37 = or i64 %tmp32, %tmp36
ret i64 %tmp37
}
; i8* p; // p is 8 byte aligned
; ((i64) p[0] << 56) | ((i64) p[1] << 48) | ((i64) p[2] << 40) | ((i64) p[3] << 32) | ((i64) p[4] << 24) | ((i64) p[5] << 16) | ((i64) p[6] << 8) | (i64) p[7]
define i64 @load_i64_by_i8_bswap(i64* %arg) {
; CHECK-LABEL: load_i64_by_i8_bswap:
; CHECK: ldr{{.*}}r0
; CHECK: ldr{{.*}}r0
; CHECK: and
; CHECK-NEXT: and
; CHECK-NEXT: orr
; CHECK-NEXT: orr
; CHECK-NEXT: and
; CHECK-NEXT: orr
; CHECK-NEXT: and
; CHECK-NEXT: orr
; CHECK-NEXT: orr
; CHECK-NEXT: orr
; CHECK: mov pc, lr
; CHECK-ARMv6-LABEL: load_i64_by_i8_bswap:
; CHECK-ARMv6: ldrd r2, r3, [r0]
; CHECK-ARMv6: rev r0, r3
; CHECK-ARMv6: rev r1, r2
; CHECK-ARMv6: bx lr
%tmp = bitcast i64* %arg to i8*
%tmp1 = load i8, i8* %tmp, align 8
%tmp2 = zext i8 %tmp1 to i64
%tmp3 = shl nuw i64 %tmp2, 56
%tmp4 = getelementptr inbounds i8, i8* %tmp, i64 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i64
%tmp7 = shl nuw nsw i64 %tmp6, 48
%tmp8 = or i64 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i64 2
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i64
%tmp12 = shl nuw nsw i64 %tmp11, 40
%tmp13 = or i64 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i64 3
%tmp15 = load i8, i8* %tmp14, align 1
%tmp16 = zext i8 %tmp15 to i64
%tmp17 = shl nuw nsw i64 %tmp16, 32
%tmp18 = or i64 %tmp13, %tmp17
%tmp19 = getelementptr inbounds i8, i8* %tmp, i64 4
%tmp20 = load i8, i8* %tmp19, align 1
%tmp21 = zext i8 %tmp20 to i64
%tmp22 = shl nuw nsw i64 %tmp21, 24
%tmp23 = or i64 %tmp18, %tmp22
%tmp24 = getelementptr inbounds i8, i8* %tmp, i64 5
%tmp25 = load i8, i8* %tmp24, align 1
%tmp26 = zext i8 %tmp25 to i64
%tmp27 = shl nuw nsw i64 %tmp26, 16
%tmp28 = or i64 %tmp23, %tmp27
%tmp29 = getelementptr inbounds i8, i8* %tmp, i64 6
%tmp30 = load i8, i8* %tmp29, align 1
%tmp31 = zext i8 %tmp30 to i64
%tmp32 = shl nuw nsw i64 %tmp31, 8
%tmp33 = or i64 %tmp28, %tmp32
%tmp34 = getelementptr inbounds i8, i8* %tmp, i64 7
%tmp35 = load i8, i8* %tmp34, align 1
%tmp36 = zext i8 %tmp35 to i64
%tmp37 = or i64 %tmp33, %tmp36
ret i64 %tmp37
}
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; i8* p; // p[1] is 4 byte aligned
; (i32) p[1] | ((i32) p[2] << 8) | ((i32) p[3] << 16) | ((i32) p[4] << 24)
define i32 @load_i32_by_i8_nonzero_offset(i32* %arg) {
; CHECK-LABEL: load_i32_by_i8_nonzero_offset:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK: ldr r0, [r0, #1]
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_nonzero_offset:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK-ARMv6: ldr r0, [r0, #1]
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp2 = load i8, i8* %tmp1, align 4
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 2
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 3
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 16
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 4
%tmp15 = load i8, i8* %tmp14, align 1
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = shl nuw nsw i32 %tmp16, 24
%tmp18 = or i32 %tmp13, %tmp17
ret i32 %tmp18
}
; i8* p; // p[-4] is 4 byte aligned
; (i32) p[-4] | ((i32) p[-3] << 8) | ((i32) p[-2] << 16) | ((i32) p[-1] << 24)
define i32 @load_i32_by_i8_neg_offset(i32* %arg) {
; CHECK-LABEL: load_i32_by_i8_neg_offset:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK: ldr r0, [r0, #-4]
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_neg_offset:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK-ARMv6: ldr r0, [r0, #-4]
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 -4
%tmp2 = load i8, i8* %tmp1, align 4
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 -3
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 -2
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 16
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 -1
%tmp15 = load i8, i8* %tmp14, align 1
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = shl nuw nsw i32 %tmp16, 24
%tmp18 = or i32 %tmp13, %tmp17
ret i32 %tmp18
}
; i8* p; // p[1] is 4 byte aligned
; (i32) p[4] | ((i32) p[3] << 8) | ((i32) p[2] << 16) | ((i32) p[1] << 24)
define i32 @load_i32_by_i8_nonzero_offset_bswap(i32* %arg) {
; CHECK-LABEL: load_i32_by_i8_nonzero_offset_bswap:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK: ldr r0, [r0, #1]
; CHECK-NEXT: mov r1, #65280
; CHECK-NEXT: mov r2, #16711680
; CHECK-NEXT: and r1, r1, r0, lsr #8
; CHECK-NEXT: and r2, r2, r0, lsl #8
; CHECK-NEXT: orr r1, r1, r0, lsr #24
; CHECK-NEXT: orr r0, r2, r0, lsl #24
; CHECK-NEXT: orr r0, r0, r1
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_nonzero_offset_bswap:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK-ARMv6: ldr r0, [r0, #1]
; CHECK-ARMv6-NEXT: rev r0, r0
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 4
%tmp2 = load i8, i8* %tmp1, align 1
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 3
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 2
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 16
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp15 = load i8, i8* %tmp14, align 4
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = shl nuw nsw i32 %tmp16, 24
%tmp18 = or i32 %tmp13, %tmp17
ret i32 %tmp18
}
; i8* p; // p[-4] is 4 byte aligned
; (i32) p[-1] | ((i32) p[-2] << 8) | ((i32) p[-3] << 16) | ((i32) p[-4] << 24)
define i32 @load_i32_by_i8_neg_offset_bswap(i32* %arg) {
; CHECK-LABEL: load_i32_by_i8_neg_offset_bswap:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK: ldr r0, [r0, #-4]
; CHECK-NEXT: mov r1, #65280
; CHECK-NEXT: mov r2, #16711680
; CHECK-NEXT: and r1, r1, r0, lsr #8
; CHECK-NEXT: and r2, r2, r0, lsl #8
; CHECK-NEXT: orr r1, r1, r0, lsr #24
; CHECK-NEXT: orr r0, r2, r0, lsl #24
; CHECK-NEXT: orr r0, r0, r1
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_i8_neg_offset_bswap:
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK-ARMv6: ldr r0, [r0, #-4]
; CHECK-ARMv6-NEXT: rev r0, r0
Add DAGCombiner load combine tests with non-zero offset This is separated from https://reviews.llvm.org/D29394 review. llvm-svn: 294185
2017-02-06 22:15:31 +08:00
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 -1
%tmp2 = load i8, i8* %tmp1, align 1
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 -2
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
%tmp9 = getelementptr inbounds i8, i8* %tmp, i32 -3
%tmp10 = load i8, i8* %tmp9, align 1
%tmp11 = zext i8 %tmp10 to i32
%tmp12 = shl nuw nsw i32 %tmp11, 16
%tmp13 = or i32 %tmp8, %tmp12
%tmp14 = getelementptr inbounds i8, i8* %tmp, i32 -4
%tmp15 = load i8, i8* %tmp14, align 4
%tmp16 = zext i8 %tmp15 to i32
%tmp17 = shl nuw nsw i32 %tmp16, 24
%tmp18 = or i32 %tmp13, %tmp17
ret i32 %tmp18
}
[DAGCombiner] Support bswap as a part of load combine patterns Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29397 llvm-svn: 294201
2017-02-07 01:48:08 +08:00
declare i16 @llvm.bswap.i16(i16)
; i16* p; // p is 4 byte aligned
; (i32) bswap(p[1]) | (i32) bswap(p[0] << 16)
define i32 @load_i32_by_bswap_i16(i32* %arg) {
; CHECK-LABEL: load_i32_by_bswap_i16:
; CHECK: ldr r0, [r0]
; CHECK-NEXT: mov r1, #65280
; CHECK-NEXT: mov r2, #16711680
; CHECK-NEXT: and r1, r1, r0, lsr #8
; CHECK-NEXT: and r2, r2, r0, lsl #8
; CHECK-NEXT: orr r1, r1, r0, lsr #24
; CHECK-NEXT: orr r0, r2, r0, lsl #24
; CHECK-NEXT: orr r0, r0, r1
; CHECK-NEXT: mov pc, lr
; CHECK-ARMv6-LABEL: load_i32_by_bswap_i16:
; CHECK-ARMv6: ldr r0, [r0]
; CHECK-ARMv6-NEXT: rev r0, r0
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i16*
%tmp1 = load i16, i16* %tmp, align 4
%tmp11 = call i16 @llvm.bswap.i16(i16 %tmp1)
%tmp2 = zext i16 %tmp11 to i32
%tmp3 = getelementptr inbounds i16, i16* %tmp, i32 1
%tmp4 = load i16, i16* %tmp3, align 1
%tmp41 = call i16 @llvm.bswap.i16(i16 %tmp4)
%tmp5 = zext i16 %tmp41 to i32
%tmp6 = shl nuw nsw i32 %tmp2, 16
%tmp7 = or i32 %tmp6, %tmp5
ret i32 %tmp7
}
Add DAGCombiner load combine tests for {a|s}ext, {a|z|s}ext load nodes Currently we don't support these nodes, so the tests check the current codegen without load combine. This change makes the review of the change to support these nodes more clear. Separated from https://reviews.llvm.org/D29591 review. llvm-svn: 294305
2017-02-07 22:09:37 +08:00
; i16* p;
; (i32) p[0] | (sext(p[1] << 16) to i32)
define i32 @load_i32_by_sext_i16(i32* %arg) {
; CHECK-LABEL: load_i32_by_sext_i16:
[DAGCombiner] Support {a|s}ext, {a|z|s}ext load nodes in load combine Resubmit r295336 after the bug with non-zero offset patterns on BE targets is fixed (r296336). Support {a|s}ext, {a|z|s}ext load nodes as a part of load combine patters. Reviewed By: filcab Differential Revision: https://reviews.llvm.org/D29591 llvm-svn: 296651
2017-03-02 02:12:29 +08:00
; CHECK: ldr r0, [r0]
Add DAGCombiner load combine tests for {a|s}ext, {a|z|s}ext load nodes Currently we don't support these nodes, so the tests check the current codegen without load combine. This change makes the review of the change to support these nodes more clear. Separated from https://reviews.llvm.org/D29591 review. llvm-svn: 294305
2017-02-07 22:09:37 +08:00
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: load_i32_by_sext_i16:
[DAGCombiner] Support {a|s}ext, {a|z|s}ext load nodes in load combine Resubmit r295336 after the bug with non-zero offset patterns on BE targets is fixed (r296336). Support {a|s}ext, {a|z|s}ext load nodes as a part of load combine patters. Reviewed By: filcab Differential Revision: https://reviews.llvm.org/D29591 llvm-svn: 296651
2017-03-02 02:12:29 +08:00
; CHECK-ARMv6: ldr r0, [r0]
; CHECK-ARMv6-NEXT: bx lr
Add DAGCombiner load combine tests for {a|s}ext, {a|z|s}ext load nodes Currently we don't support these nodes, so the tests check the current codegen without load combine. This change makes the review of the change to support these nodes more clear. Separated from https://reviews.llvm.org/D29591 review. llvm-svn: 294305
2017-02-07 22:09:37 +08:00
%tmp = bitcast i32* %arg to i16*
%tmp1 = load i16, i16* %tmp, align 4
%tmp2 = zext i16 %tmp1 to i32
%tmp3 = getelementptr inbounds i16, i16* %tmp, i32 1
%tmp4 = load i16, i16* %tmp3, align 1
%tmp5 = sext i16 %tmp4 to i32
%tmp6 = shl nuw nsw i32 %tmp5, 16
%tmp7 = or i32 %tmp6, %tmp2
ret i32 %tmp7
}
; i8* arg; i32 i;
; p = arg + 12;
; (i32) p[i] | ((i32) p[i + 1] << 8) | ((i32) p[i + 2] << 16) | ((i32) p[i + 3] << 24)
define i32 @load_i32_by_i8_base_offset_index(i8* %arg, i32 %i) {
; CHECK-LABEL: load_i32_by_i8_base_offset_index:
; CHECK: add r0, r0, r1
; CHECK-NEXT: ldr r0, [r0, #12]
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: load_i32_by_i8_base_offset_index:
; CHECK-ARMv6: add r0, r0, r1
; CHECK-ARMv6-NEXT: ldr r0, [r0, #12]
; CHECK-ARMv6-NEXT: bx lr
%tmp = add nuw nsw i32 %i, 3
%tmp2 = add nuw nsw i32 %i, 2
%tmp3 = add nuw nsw i32 %i, 1
%tmp4 = getelementptr inbounds i8, i8* %arg, i64 12
%tmp5 = zext i32 %i to i64
%tmp6 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp5
%tmp7 = load i8, i8* %tmp6, align 4
%tmp8 = zext i8 %tmp7 to i32
%tmp9 = zext i32 %tmp3 to i64
%tmp10 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp9
%tmp11 = load i8, i8* %tmp10, align 1
%tmp12 = zext i8 %tmp11 to i32
%tmp13 = shl nuw nsw i32 %tmp12, 8
%tmp14 = or i32 %tmp13, %tmp8
%tmp15 = zext i32 %tmp2 to i64
%tmp16 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp15
%tmp17 = load i8, i8* %tmp16, align 1
%tmp18 = zext i8 %tmp17 to i32
%tmp19 = shl nuw nsw i32 %tmp18, 16
%tmp20 = or i32 %tmp14, %tmp19
%tmp21 = zext i32 %tmp to i64
%tmp22 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp21
%tmp23 = load i8, i8* %tmp22, align 1
%tmp24 = zext i8 %tmp23 to i32
%tmp25 = shl nuw i32 %tmp24, 24
%tmp26 = or i32 %tmp20, %tmp25
ret i32 %tmp26
}
; i8* arg; i32 i;
; p = arg + 12;
; (i32) p[i + 1] | ((i32) p[i + 2] << 8) | ((i32) p[i + 3] << 16) | ((i32) p[i + 4] << 24)
define i32 @load_i32_by_i8_base_offset_index_2(i8* %arg, i32 %i) {
; CHECK-LABEL: load_i32_by_i8_base_offset_index_2:
; CHECK: add r0, r0, r1
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK-NEXT: ldr r0, [r0, #13]
Add DAGCombiner load combine tests for {a|s}ext, {a|z|s}ext load nodes Currently we don't support these nodes, so the tests check the current codegen without load combine. This change makes the review of the change to support these nodes more clear. Separated from https://reviews.llvm.org/D29591 review. llvm-svn: 294305
2017-02-07 22:09:37 +08:00
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: load_i32_by_i8_base_offset_index_2:
; CHECK-ARMv6: add r0, r0, r1
[DAGCombiner] Support non-zero offset in load combine Enable folding patterns which load the value from non-zero offset: i8 *a = ... i32 val = a[4] | (a[5] << 8) | (a[6] << 16) | (a[7] << 24) => i32 val = *((i32*)(a+4)) Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D29394 llvm-svn: 294582
2017-02-09 20:06:01 +08:00
; CHECK-ARMv6-NEXT: ldr r0, [r0, #13]
Add DAGCombiner load combine tests for {a|s}ext, {a|z|s}ext load nodes Currently we don't support these nodes, so the tests check the current codegen without load combine. This change makes the review of the change to support these nodes more clear. Separated from https://reviews.llvm.org/D29591 review. llvm-svn: 294305
2017-02-07 22:09:37 +08:00
; CHECK-ARMv6-NEXT: bx lr
%tmp = add nuw nsw i32 %i, 4
%tmp2 = add nuw nsw i32 %i, 3
%tmp3 = add nuw nsw i32 %i, 2
%tmp4 = getelementptr inbounds i8, i8* %arg, i64 12
%tmp5 = add nuw nsw i32 %i, 1
%tmp27 = zext i32 %tmp5 to i64
%tmp28 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp27
%tmp29 = load i8, i8* %tmp28, align 4
%tmp30 = zext i8 %tmp29 to i32
%tmp31 = zext i32 %tmp3 to i64
%tmp32 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp31
%tmp33 = load i8, i8* %tmp32, align 1
%tmp34 = zext i8 %tmp33 to i32
%tmp35 = shl nuw nsw i32 %tmp34, 8
%tmp36 = or i32 %tmp35, %tmp30
%tmp37 = zext i32 %tmp2 to i64
%tmp38 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp37
%tmp39 = load i8, i8* %tmp38, align 1
%tmp40 = zext i8 %tmp39 to i32
%tmp41 = shl nuw nsw i32 %tmp40, 16
%tmp42 = or i32 %tmp36, %tmp41
%tmp43 = zext i32 %tmp to i64
%tmp44 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp43
%tmp45 = load i8, i8* %tmp44, align 1
%tmp46 = zext i8 %tmp45 to i32
%tmp47 = shl nuw i32 %tmp46, 24
%tmp48 = or i32 %tmp42, %tmp47
ret i32 %tmp48
}
Add DAGCombiner load combine tests for partially available values If some of the trailing or leading bytes of a load combine pattern are zeroes we can combine the pattern to a load + zext and shift. Currently we don't support it, so the tests check the current codegen without load combine. This change will make the patch to support this kind of combine a bit more clear. llvm-svn: 294591
2017-02-09 23:13:40 +08:00
; i8* p; // p is 2 byte aligned
; (i32) p[0] | ((i32) p[1] << 8)
define i32 @zext_load_i32_by_i8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8:
; CHECK: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: orr r0, r1, r0, lsl #8
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8:
; CHECK-ARMv6: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: orr r0, r1, r0, lsl #8
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0
%tmp2 = load i8, i8* %tmp1, align 2
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
ret i32 %tmp8
}
; i8* p; // p is 2 byte aligned
; ((i32) p[0] << 8) | ((i32) p[1] << 16)
define i32 @zext_load_i32_by_i8_shl_8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_shl_8:
; CHECK: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: lsl r0, r0, #16
; CHECK-NEXT: orr r0, r0, r1, lsl #8
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_shl_8:
; CHECK-ARMv6: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: lsl r0, r0, #16
; CHECK-ARMv6-NEXT: orr r0, r0, r1, lsl #8
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0
%tmp2 = load i8, i8* %tmp1, align 2
%tmp3 = zext i8 %tmp2 to i32
%tmp30 = shl nuw nsw i32 %tmp3, 8
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 16
%tmp8 = or i32 %tmp7, %tmp30
ret i32 %tmp8
}
; i8* p; // p is 2 byte aligned
; ((i32) p[0] << 16) | ((i32) p[1] << 24)
define i32 @zext_load_i32_by_i8_shl_16(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_shl_16:
; CHECK: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: lsl r0, r0, #24
; CHECK-NEXT: orr r0, r0, r1, lsl #16
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_shl_16:
; CHECK-ARMv6: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: lsl r0, r0, #24
; CHECK-ARMv6-NEXT: orr r0, r0, r1, lsl #16
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0
%tmp2 = load i8, i8* %tmp1, align 2
%tmp3 = zext i8 %tmp2 to i32
%tmp30 = shl nuw nsw i32 %tmp3, 16
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp5 = load i8, i8* %tmp4, align 1
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 24
%tmp8 = or i32 %tmp7, %tmp30
ret i32 %tmp8
}
; i8* p; // p is 2 byte aligned
; (i32) p[1] | ((i32) p[0] << 8)
define i32 @zext_load_i32_by_i8_bswap(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap:
; CHECK: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: orr r0, r0, r1, lsl #8
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-ARMv6: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: orr r0, r0, r1, lsl #8
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp2 = load i8, i8* %tmp1, align 1
%tmp3 = zext i8 %tmp2 to i32
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 0
%tmp5 = load i8, i8* %tmp4, align 2
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 8
%tmp8 = or i32 %tmp7, %tmp3
ret i32 %tmp8
}
; i8* p; // p is 2 byte aligned
; ((i32) p[1] << 8) | ((i32) p[0] << 16)
define i32 @zext_load_i32_by_i8_bswap_shl_8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap_shl_8:
; CHECK: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: lsl r1, r1, #16
; CHECK-NEXT: orr r0, r1, r0, lsl #8
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_bswap_shl_8:
; CHECK-ARMv6: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: lsl r1, r1, #16
; CHECK-ARMv6-NEXT: orr r0, r1, r0, lsl #8
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp2 = load i8, i8* %tmp1, align 1
%tmp3 = zext i8 %tmp2 to i32
%tmp30 = shl nuw nsw i32 %tmp3, 8
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 0
%tmp5 = load i8, i8* %tmp4, align 2
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 16
%tmp8 = or i32 %tmp7, %tmp30
ret i32 %tmp8
}
; i8* p; // p is 2 byte aligned
; ((i32) p[1] << 16) | ((i32) p[0] << 24)
define i32 @zext_load_i32_by_i8_bswap_shl_16(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap_shl_16:
; CHECK: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: lsl r1, r1, #24
; CHECK-NEXT: orr r0, r1, r0, lsl #16
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_bswap_shl_16:
; CHECK-ARMv6: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: lsl r1, r1, #24
; CHECK-ARMv6-NEXT: orr r0, r1, r0, lsl #16
; CHECK-ARMv6-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 1
%tmp2 = load i8, i8* %tmp1, align 1
%tmp3 = zext i8 %tmp2 to i32
%tmp30 = shl nuw nsw i32 %tmp3, 16
%tmp4 = getelementptr inbounds i8, i8* %tmp, i32 0
%tmp5 = load i8, i8* %tmp4, align 2
%tmp6 = zext i8 %tmp5 to i32
%tmp7 = shl nuw nsw i32 %tmp6, 24
%tmp8 = or i32 %tmp7, %tmp30
ret i32 %tmp8
}