[llvm] 7897086 - Do not generate calls to the 128-bit function __multi3() on 32-bit ARM
Renato Golin via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 11 03:46:23 PDT 2021
Author: Koutheir Attouchi
Date: 2021-06-11T11:45:21+01:00
New Revision: 789708617d2023dbb343c65120556b2e6a97044d
URL: https://github.com/llvm/llvm-project/commit/789708617d2023dbb343c65120556b2e6a97044d
DIFF: https://github.com/llvm/llvm-project/commit/789708617d2023dbb343c65120556b2e6a97044d.diff
LOG: Do not generate calls to the 128-bit function __multi3() on 32-bit ARM
Re-applying this patch after bots failures. Should be fine now.
The function __multi3() is undefined on 32-bit ARM, so a call to it should
never be emitted. Instead, plain instructions need to be generated to
perform 128-bit multiplications.
Differential Revision: https://reviews.llvm.org/D103906
Added:
Modified:
llvm/lib/Target/ARM/ARMISelLowering.cpp
llvm/test/CodeGen/ARM/umulo-128-legalisation-lowering.ll
llvm/test/CodeGen/Thumb/pr35836_2.ll
llvm/test/CodeGen/Thumb/umulo-128-legalisation-lowering.ll
llvm/test/CodeGen/Thumb2/umulo-128-legalisation-lowering.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 52b18e92661c0..81c0565f4813f 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -544,6 +544,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setLibcallName(RTLIB::SHL_I128, nullptr);
setLibcallName(RTLIB::SRL_I128, nullptr);
setLibcallName(RTLIB::SRA_I128, nullptr);
+ setLibcallName(RTLIB::MUL_I128, nullptr);
// RTLIB
if (Subtarget->isAAPCS_ABI() &&
diff --git a/llvm/test/CodeGen/ARM/umulo-128-legalisation-lowering.ll b/llvm/test/CodeGen/ARM/umulo-128-legalisation-lowering.ll
index c237a396bf914..d488599a42b40 100644
--- a/llvm/test/CodeGen/ARM/umulo-128-legalisation-lowering.ll
+++ b/llvm/test/CodeGen/ARM/umulo-128-legalisation-lowering.ll
@@ -7,190 +7,208 @@ define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
; ARMV6: @ %bb.0: @ %start
; ARMV6-NEXT: push {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; ARMV6-NEXT: sub sp, sp, #28
-; ARMV6-NEXT: mov r9, #0
-; ARMV6-NEXT: mov r11, r0
+; ARMV6-NEXT: ldr r7, [sp, #72]
+; ARMV6-NEXT: mov r6, r0
+; ARMV6-NEXT: str r0, [sp, #8] @ 4-byte Spill
+; ARMV6-NEXT: ldr r4, [sp, #84]
+; ARMV6-NEXT: umull r1, r0, r2, r7
+; ARMV6-NEXT: mov lr, r7
+; ARMV6-NEXT: umull r5, r10, r4, r2
+; ARMV6-NEXT: str r1, [r6]
+; ARMV6-NEXT: ldr r6, [sp, #80]
+; ARMV6-NEXT: umull r1, r7, r3, r6
+; ARMV6-NEXT: str r7, [sp, #12] @ 4-byte Spill
+; ARMV6-NEXT: add r1, r5, r1
+; ARMV6-NEXT: umull r7, r5, r6, r2
+; ARMV6-NEXT: mov r6, lr
+; ARMV6-NEXT: str r7, [sp, #16] @ 4-byte Spill
+; ARMV6-NEXT: mov r7, #0
+; ARMV6-NEXT: adds r1, r5, r1
+; ARMV6-NEXT: str r1, [sp, #4] @ 4-byte Spill
+; ARMV6-NEXT: adc r1, r7, #0
+; ARMV6-NEXT: str r1, [sp, #24] @ 4-byte Spill
+; ARMV6-NEXT: ldr r1, [sp, #64]
; ARMV6-NEXT: ldr r7, [sp, #76]
-; ARMV6-NEXT: mov r5, r3
-; ARMV6-NEXT: ldr r10, [sp, #72]
-; ARMV6-NEXT: mov r1, r3
-; ARMV6-NEXT: mov r6, r2
-; ARMV6-NEXT: mov r0, r2
+; ARMV6-NEXT: ldr r5, [sp, #64]
+; ARMV6-NEXT: umull r12, r9, r7, r1
+; ARMV6-NEXT: ldr r1, [sp, #68]
+; ARMV6-NEXT: umull r11, r8, r1, lr
+; ARMV6-NEXT: add r12, r11, r12
+; ARMV6-NEXT: umull r11, lr, r5, lr
+; ARMV6-NEXT: mov r5, r6
+; ARMV6-NEXT: mov r6, #0
+; ARMV6-NEXT: adds r12, lr, r12
+; ARMV6-NEXT: umull r2, lr, r2, r7
+; ARMV6-NEXT: adc r6, r6, #0
+; ARMV6-NEXT: str r6, [sp, #20] @ 4-byte Spill
+; ARMV6-NEXT: ldr r6, [sp, #16] @ 4-byte Reload
+; ARMV6-NEXT: adds r11, r11, r6
+; ARMV6-NEXT: ldr r6, [sp, #4] @ 4-byte Reload
+; ARMV6-NEXT: adc r6, r12, r6
+; ARMV6-NEXT: mov r12, #0
+; ARMV6-NEXT: umlal r0, r12, r3, r5
+; ARMV6-NEXT: ldr r5, [sp, #8] @ 4-byte Reload
+; ARMV6-NEXT: str r6, [sp, #16] @ 4-byte Spill
+; ARMV6-NEXT: ldr r6, [sp, #64]
+; ARMV6-NEXT: adds r0, r2, r0
+; ARMV6-NEXT: str r0, [r5, #4]
+; ARMV6-NEXT: adcs r0, r12, lr
; ARMV6-NEXT: mov r2, #0
-; ARMV6-NEXT: mov r3, #0
-; ARMV6-NEXT: str r9, [sp, #12]
-; ARMV6-NEXT: str r9, [sp, #8]
-; ARMV6-NEXT: str r7, [sp, #4]
-; ARMV6-NEXT: str r10, [sp]
-; ARMV6-NEXT: bl __multi3
-; ARMV6-NEXT: str r3, [sp, #20] @ 4-byte Spill
-; ARMV6-NEXT: str r2, [sp, #16] @ 4-byte Spill
-; ARMV6-NEXT: stm r11, {r0, r1}
-; ARMV6-NEXT: ldr r0, [sp, #84]
-; ARMV6-NEXT: ldr r3, [sp, #80]
-; ARMV6-NEXT: ldr r8, [sp, #64]
-; ARMV6-NEXT: umull r4, r0, r0, r6
-; ARMV6-NEXT: umull r2, r1, r5, r3
-; ARMV6-NEXT: add r2, r4, r2
-; ARMV6-NEXT: umull lr, r4, r3, r6
-; ARMV6-NEXT: umull r3, r6, r7, r8
-; ARMV6-NEXT: adds r12, r4, r2
-; ARMV6-NEXT: adc r2, r9, #0
-; ARMV6-NEXT: str r2, [sp, #24] @ 4-byte Spill
-; ARMV6-NEXT: ldr r2, [sp, #68]
-; ARMV6-NEXT: umull r4, r2, r2, r10
-; ARMV6-NEXT: add r3, r4, r3
-; ARMV6-NEXT: umull r4, r10, r8, r10
-; ARMV6-NEXT: adds r3, r10, r3
-; ARMV6-NEXT: adc r10, r9, #0
-; ARMV6-NEXT: adds r4, r4, lr
-; ARMV6-NEXT: adc r12, r3, r12
-; ARMV6-NEXT: ldr r3, [sp, #16] @ 4-byte Reload
-; ARMV6-NEXT: adds r4, r3, r4
-; ARMV6-NEXT: str r4, [r11, #8]
-; ARMV6-NEXT: ldr r4, [sp, #20] @ 4-byte Reload
-; ARMV6-NEXT: adcs r3, r4, r12
-; ARMV6-NEXT: str r3, [r11, #12]
-; ARMV6-NEXT: ldr r3, [sp, #84]
-; ARMV6-NEXT: adc r12, r9, #0
-; ARMV6-NEXT: cmp r5, #0
-; ARMV6-NEXT: movne r5, #1
-; ARMV6-NEXT: cmp r3, #0
-; ARMV6-NEXT: mov r4, r3
-; ARMV6-NEXT: movne r4, #1
-; ARMV6-NEXT: cmp r0, #0
-; ARMV6-NEXT: movne r0, #1
+; ARMV6-NEXT: adc r2, r2, #0
+; ARMV6-NEXT: orrs lr, r6, r1
+; ARMV6-NEXT: ldr r6, [sp, #80]
+; ARMV6-NEXT: movne lr, #1
+; ARMV6-NEXT: umlal r0, r2, r3, r7
+; ARMV6-NEXT: orrs r12, r6, r4
+; ARMV6-NEXT: movne r12, #1
+; ARMV6-NEXT: cmp r9, #0
+; ARMV6-NEXT: ldr r6, [sp, #12] @ 4-byte Reload
+; ARMV6-NEXT: movne r9, #1
+; ARMV6-NEXT: cmp r8, #0
+; ARMV6-NEXT: movne r8, #1
+; ARMV6-NEXT: cmp r6, #0
+; ARMV6-NEXT: movne r6, #1
+; ARMV6-NEXT: cmp r10, #0
+; ARMV6-NEXT: movne r10, #1
; ARMV6-NEXT: cmp r1, #0
-; ARMV6-NEXT: and r5, r4, r5
; ARMV6-NEXT: movne r1, #1
-; ARMV6-NEXT: orr r0, r5, r0
-; ARMV6-NEXT: ldr r5, [sp, #68]
-; ARMV6-NEXT: orr r0, r0, r1
-; ARMV6-NEXT: ldr r1, [sp, #24] @ 4-byte Reload
; ARMV6-NEXT: cmp r7, #0
-; ARMV6-NEXT: orr r0, r0, r1
; ARMV6-NEXT: movne r7, #1
-; ARMV6-NEXT: cmp r5, #0
-; ARMV6-NEXT: mov r1, r5
-; ARMV6-NEXT: movne r1, #1
-; ARMV6-NEXT: cmp r2, #0
-; ARMV6-NEXT: movne r2, #1
+; ARMV6-NEXT: cmp r4, #0
+; ARMV6-NEXT: movne r4, #1
+; ARMV6-NEXT: cmp r3, #0
+; ARMV6-NEXT: movne r3, #1
+; ARMV6-NEXT: adds r0, r0, r11
+; ARMV6-NEXT: str r0, [r5, #8]
; ARMV6-NEXT: and r1, r1, r7
+; ARMV6-NEXT: ldr r0, [sp, #16] @ 4-byte Reload
+; ARMV6-NEXT: orr r1, r1, r8
+; ARMV6-NEXT: orr r1, r1, r9
+; ARMV6-NEXT: adcs r0, r2, r0
+; ARMV6-NEXT: str r0, [r5, #12]
+; ARMV6-NEXT: and r0, r4, r3
+; ARMV6-NEXT: ldr r2, [sp, #24] @ 4-byte Reload
+; ARMV6-NEXT: orr r0, r0, r10
+; ARMV6-NEXT: orr r0, r0, r6
+; ARMV6-NEXT: orr r0, r0, r2
+; ARMV6-NEXT: ldr r2, [sp, #20] @ 4-byte Reload
; ARMV6-NEXT: orr r1, r1, r2
-; ARMV6-NEXT: ldr r2, [sp, #80]
-; ARMV6-NEXT: cmp r6, #0
-; ARMV6-NEXT: movne r6, #1
-; ARMV6-NEXT: orrs r2, r2, r3
-; ARMV6-NEXT: orr r1, r1, r6
-; ARMV6-NEXT: movne r2, #1
-; ARMV6-NEXT: orrs r7, r8, r5
-; ARMV6-NEXT: orr r1, r1, r10
-; ARMV6-NEXT: movne r7, #1
-; ARMV6-NEXT: and r2, r7, r2
+; ARMV6-NEXT: and r2, lr, r12
; ARMV6-NEXT: orr r1, r2, r1
; ARMV6-NEXT: orr r0, r1, r0
-; ARMV6-NEXT: orr r0, r0, r12
+; ARMV6-NEXT: mov r1, #0
+; ARMV6-NEXT: adc r1, r1, #0
+; ARMV6-NEXT: orr r0, r0, r1
; ARMV6-NEXT: and r0, r0, #1
-; ARMV6-NEXT: strb r0, [r11, #16]
+; ARMV6-NEXT: strb r0, [r5, #16]
; ARMV6-NEXT: add sp, sp, #28
; ARMV6-NEXT: pop {r4, r5, r6, r7, r8, r9, r10, r11, pc}
;
; ARMV7-LABEL: muloti_test:
; ARMV7: @ %bb.0: @ %start
; ARMV7-NEXT: push {r4, r5, r6, r7, r8, r9, r10, r11, lr}
-; ARMV7-NEXT: sub sp, sp, #44
-; ARMV7-NEXT: str r0, [sp, #40] @ 4-byte Spill
+; ARMV7-NEXT: sub sp, sp, #36
+; ARMV7-NEXT: ldr r5, [sp, #84]
+; ARMV7-NEXT: mov r8, r0
+; ARMV7-NEXT: ldr r1, [sp, #72]
+; ARMV7-NEXT: ldr r10, [sp, #80]
+; ARMV7-NEXT: ldr r9, [sp, #76]
+; ARMV7-NEXT: umull r4, lr, r5, r1
+; ARMV7-NEXT: umull r0, r7, r2, r10
+; ARMV7-NEXT: str r4, [sp, #24] @ 4-byte Spill
+; ARMV7-NEXT: ldr r4, [sp, #88]
+; ARMV7-NEXT: umull r1, r6, r1, r10
+; ARMV7-NEXT: str r0, [sp, #32] @ 4-byte Spill
+; ARMV7-NEXT: umull r11, r0, r2, r5
+; ARMV7-NEXT: str r6, [sp, #20] @ 4-byte Spill
+; ARMV7-NEXT: str r1, [sp, #28] @ 4-byte Spill
+; ARMV7-NEXT: umull r6, r12, r3, r4
+; ARMV7-NEXT: ldr r1, [sp, #92]
+; ARMV7-NEXT: str r0, [sp, #8] @ 4-byte Spill
; ARMV7-NEXT: mov r0, #0
-; ARMV7-NEXT: ldr r8, [sp, #88]
-; ARMV7-NEXT: mov r5, r3
-; ARMV7-NEXT: ldr r7, [sp, #92]
-; ARMV7-NEXT: mov r1, r3
-; ARMV7-NEXT: mov r6, r2
-; ARMV7-NEXT: str r0, [sp, #8]
-; ARMV7-NEXT: str r0, [sp, #12]
-; ARMV7-NEXT: mov r0, r2
-; ARMV7-NEXT: mov r2, #0
-; ARMV7-NEXT: mov r3, #0
-; ARMV7-NEXT: str r8, [sp]
-; ARMV7-NEXT: str r7, [sp, #4]
-; ARMV7-NEXT: bl __multi3
-; ARMV7-NEXT: str r1, [sp, #28] @ 4-byte Spill
-; ARMV7-NEXT: ldr r1, [sp, #80]
-; ARMV7-NEXT: str r2, [sp, #24] @ 4-byte Spill
-; ARMV7-NEXT: str r3, [sp, #20] @ 4-byte Spill
-; ARMV7-NEXT: umull r2, r9, r7, r1
-; ARMV7-NEXT: str r0, [sp, #32] @ 4-byte Spill
-; ARMV7-NEXT: ldr r4, [sp, #84]
-; ARMV7-NEXT: ldr r0, [sp, #96]
-; ARMV7-NEXT: umull r1, r3, r1, r8
-; ARMV7-NEXT: umull r12, r10, r4, r8
-; ARMV7-NEXT: str r1, [sp, #16] @ 4-byte Spill
-; ARMV7-NEXT: umull lr, r1, r5, r0
-; ARMV7-NEXT: add r2, r12, r2
-; ARMV7-NEXT: umull r11, r8, r0, r6
-; ARMV7-NEXT: ldr r0, [sp, #100]
-; ARMV7-NEXT: adds r2, r3, r2
-; ARMV7-NEXT: mov r12, #0
-; ARMV7-NEXT: umull r6, r0, r0, r6
-; ARMV7-NEXT: adc r3, r12, #0
-; ARMV7-NEXT: str r3, [sp, #36] @ 4-byte Spill
-; ARMV7-NEXT: add r3, r6, lr
-; ARMV7-NEXT: ldr r6, [sp, #16] @ 4-byte Reload
-; ARMV7-NEXT: adds r3, r8, r3
-; ARMV7-NEXT: adc lr, r12, #0
-; ARMV7-NEXT: adds r6, r6, r11
-; ARMV7-NEXT: adc r2, r2, r3
-; ARMV7-NEXT: ldr r3, [sp, #24] @ 4-byte Reload
-; ARMV7-NEXT: mov r12, #0
-; ARMV7-NEXT: adds r3, r3, r6
-; ARMV7-NEXT: ldr r6, [sp, #20] @ 4-byte Reload
-; ARMV7-NEXT: adcs r8, r6, r2
-; ARMV7-NEXT: ldr r6, [sp, #40] @ 4-byte Reload
-; ARMV7-NEXT: ldr r2, [sp, #32] @ 4-byte Reload
-; ARMV7-NEXT: str r2, [r6]
-; ARMV7-NEXT: ldr r2, [sp, #28] @ 4-byte Reload
-; ARMV7-NEXT: stmib r6, {r2, r3, r8}
-; ARMV7-NEXT: adc r8, r12, #0
-; ARMV7-NEXT: cmp r5, #0
-; ARMV7-NEXT: ldr r2, [sp, #100]
-; ARMV7-NEXT: movwne r5, #1
-; ARMV7-NEXT: cmp r2, #0
-; ARMV7-NEXT: mov r3, r2
+; ARMV7-NEXT: umlal r7, r0, r3, r10
+; ARMV7-NEXT: str r6, [sp, #16] @ 4-byte Spill
+; ARMV7-NEXT: umull r6, r1, r1, r2
+; ARMV7-NEXT: umull r2, r4, r4, r2
+; ARMV7-NEXT: str r6, [sp, #4] @ 4-byte Spill
+; ARMV7-NEXT: str r2, [sp, #12] @ 4-byte Spill
+; ARMV7-NEXT: adds r2, r11, r7
+; ARMV7-NEXT: ldr r7, [sp, #8] @ 4-byte Reload
+; ARMV7-NEXT: mov r11, #0
+; ARMV7-NEXT: str r4, [sp] @ 4-byte Spill
+; ARMV7-NEXT: umull r6, r4, r9, r10
+; ARMV7-NEXT: adcs r9, r0, r7
+; ARMV7-NEXT: ldr r0, [sp, #32] @ 4-byte Reload
+; ARMV7-NEXT: adc r10, r11, #0
+; ARMV7-NEXT: stm r8, {r0, r2}
+; ARMV7-NEXT: ldr r0, [sp, #24] @ 4-byte Reload
+; ARMV7-NEXT: umlal r9, r10, r3, r5
+; ARMV7-NEXT: ldr r2, [sp, #20] @ 4-byte Reload
+; ARMV7-NEXT: add r0, r6, r0
+; ARMV7-NEXT: adds r2, r2, r0
+; ARMV7-NEXT: ldr r6, [sp, #4] @ 4-byte Reload
+; ARMV7-NEXT: adc r0, r11, #0
+; ARMV7-NEXT: str r0, [sp, #32] @ 4-byte Spill
+; ARMV7-NEXT: ldr r0, [sp, #16] @ 4-byte Reload
+; ARMV7-NEXT: ldr r7, [sp, #28] @ 4-byte Reload
+; ARMV7-NEXT: add r0, r6, r0
+; ARMV7-NEXT: ldr r6, [sp] @ 4-byte Reload
+; ARMV7-NEXT: adds r0, r6, r0
+; ARMV7-NEXT: ldr r6, [sp, #12] @ 4-byte Reload
+; ARMV7-NEXT: adc r11, r11, #0
+; ARMV7-NEXT: adds r7, r7, r6
+; ARMV7-NEXT: ldr r6, [sp, #92]
+; ARMV7-NEXT: adc r0, r2, r0
+; ARMV7-NEXT: str r0, [sp, #28] @ 4-byte Spill
+; ARMV7-NEXT: ldr r0, [sp, #92]
+; ARMV7-NEXT: cmp r3, #0
; ARMV7-NEXT: movwne r3, #1
+; ARMV7-NEXT: ldr r2, [sp, #76]
; ARMV7-NEXT: cmp r0, #0
; ARMV7-NEXT: movwne r0, #1
; ARMV7-NEXT: cmp r1, #0
-; ARMV7-NEXT: and r3, r3, r5
; ARMV7-NEXT: movwne r1, #1
-; ARMV7-NEXT: orr r0, r3, r0
-; ARMV7-NEXT: cmp r7, #0
+; ARMV7-NEXT: cmp r12, #0
+; ARMV7-NEXT: and r0, r0, r3
+; ARMV7-NEXT: movwne r12, #1
+; ARMV7-NEXT: cmp r5, #0
; ARMV7-NEXT: orr r0, r0, r1
-; ARMV7-NEXT: ldr r1, [sp, #80]
-; ARMV7-NEXT: movwne r7, #1
+; ARMV7-NEXT: movwne r5, #1
+; ARMV7-NEXT: cmp r2, #0
+; ARMV7-NEXT: mov r1, r2
+; ARMV7-NEXT: mov r3, r2
+; ARMV7-NEXT: movwne r1, #1
; ARMV7-NEXT: cmp r4, #0
-; ARMV7-NEXT: orr r1, r1, r4
+; ARMV7-NEXT: ldr r2, [sp, #72]
; ARMV7-NEXT: movwne r4, #1
-; ARMV7-NEXT: cmp r10, #0
-; ARMV7-NEXT: and r3, r4, r7
-; ARMV7-NEXT: movwne r10, #1
-; ARMV7-NEXT: cmp r9, #0
-; ARMV7-NEXT: orr r3, r3, r10
-; ARMV7-NEXT: ldr r7, [sp, #36] @ 4-byte Reload
-; ARMV7-NEXT: movwne r9, #1
-; ARMV7-NEXT: orr r3, r3, r9
-; ARMV7-NEXT: orr r3, r3, r7
-; ARMV7-NEXT: ldr r7, [sp, #96]
-; ARMV7-NEXT: orr r0, r0, lr
-; ARMV7-NEXT: orrs r7, r7, r2
-; ARMV7-NEXT: movwne r7, #1
-; ARMV7-NEXT: cmp r1, #0
-; ARMV7-NEXT: movwne r1, #1
-; ARMV7-NEXT: and r1, r1, r7
-; ARMV7-NEXT: orr r1, r1, r3
+; ARMV7-NEXT: cmp lr, #0
+; ARMV7-NEXT: and r1, r1, r5
+; ARMV7-NEXT: movwne lr, #1
+; ARMV7-NEXT: orrs r2, r2, r3
+; ARMV7-NEXT: ldr r3, [sp, #88]
+; ARMV7-NEXT: movwne r2, #1
+; ARMV7-NEXT: orr r1, r1, r4
+; ARMV7-NEXT: orr r0, r0, r12
+; ARMV7-NEXT: orrs r3, r3, r6
+; ARMV7-NEXT: orr r1, r1, lr
+; ARMV7-NEXT: movwne r3, #1
+; ARMV7-NEXT: adds r7, r9, r7
+; ARMV7-NEXT: str r7, [r8, #8]
+; ARMV7-NEXT: and r2, r2, r3
+; ARMV7-NEXT: ldr r7, [sp, #28] @ 4-byte Reload
+; ARMV7-NEXT: orr r0, r0, r11
+; ARMV7-NEXT: adcs r7, r10, r7
+; ARMV7-NEXT: str r7, [r8, #12]
+; ARMV7-NEXT: ldr r7, [sp, #32] @ 4-byte Reload
+; ARMV7-NEXT: orr r1, r1, r7
+; ARMV7-NEXT: orr r1, r2, r1
; ARMV7-NEXT: orr r0, r1, r0
-; ARMV7-NEXT: orr r0, r0, r8
+; ARMV7-NEXT: mov r1, #0
+; ARMV7-NEXT: adc r1, r1, #0
+; ARMV7-NEXT: orr r0, r0, r1
; ARMV7-NEXT: and r0, r0, #1
-; ARMV7-NEXT: strb r0, [r6, #16]
-; ARMV7-NEXT: add sp, sp, #44
+; ARMV7-NEXT: strb r0, [r8, #16]
+; ARMV7-NEXT: add sp, sp, #36
; ARMV7-NEXT: pop {r4, r5, r6, r7, r8, r9, r10, r11, pc}
start:
%0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2
diff --git a/llvm/test/CodeGen/Thumb/pr35836_2.ll b/llvm/test/CodeGen/Thumb/pr35836_2.ll
index 26e27293dc784..3738f0c684958 100644
--- a/llvm/test/CodeGen/Thumb/pr35836_2.ll
+++ b/llvm/test/CodeGen/Thumb/pr35836_2.ll
@@ -36,21 +36,20 @@ entry:
%mul = mul i128 %add18, %add
ret i128 %mul
}
-; CHECK: adds r4, r2, r7
-; CHECK: mov r4, r1
-; CHECK: adcs r4, r6
-; CHECK: ldr r4, [sp, #20] @ 4-byte Reload
-; CHECK: adcs r5, r4
-; CHECK: ldr r4, [sp, #24] @ 4-byte Reload
-; CHECK: adcs r3, r4
-; CHECK: adds r4, r2, r7
-; CHECK: adcs r1, r6
-; CHECK: str r4, [sp]
-; CHECK: str r1, [sp, #4]
-; CHECK: ldr r2, [r0, #16]
-; CHECK: ldr r6, [r0, #24]
-; CHECK: adcs r6, r2
-; CHECK: str r6, [sp, #8]
-; CHECK: ldr r2, [r0, #20]
-; CHECK: ldr r0, [r0, #28]
-; CHECK: adcs r0, r2
+; CHECK: adds r5, r1, r7
+; CHECK: mov r5, r4
+; CHECK: adcs r5, r6
+; CHECK: ldr r5, [sp, #12] @ 4-byte Reload
+; CHECK: adcs r2, r5
+; CHECK: ldr r5, [sp, #16] @ 4-byte Reload
+; CHECK: adcs r3, r5
+; CHECK: adds r5, r1, r7
+; CHECK: adcs r4, r6
+; CHECK: ldr r1, [r0, #20]
+; CHECK: str r1, [sp, #16] @ 4-byte Spill
+; CHECK: ldr r6, [r0, #28]
+; CHECK: ldr r1, [r0, #16]
+; CHECK: ldr r7, [r0, #24]
+; CHECK: adcs r7, r1
+; CHECK: ldr r0, [sp, #16] @ 4-byte Reload
+; CHECK: adcs r6, r0
diff --git a/llvm/test/CodeGen/Thumb/umulo-128-legalisation-lowering.ll b/llvm/test/CodeGen/Thumb/umulo-128-legalisation-lowering.ll
index 8b966b536c944..9b5fa1c2bc811 100644
--- a/llvm/test/CodeGen/Thumb/umulo-128-legalisation-lowering.ll
+++ b/llvm/test/CodeGen/Thumb/umulo-128-legalisation-lowering.ll
@@ -6,140 +6,197 @@ define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
; THUMBV6: @ %bb.0: @ %start
; THUMBV6-NEXT: .save {r4, r5, r6, r7, lr}
; THUMBV6-NEXT: push {r4, r5, r6, r7, lr}
-; THUMBV6-NEXT: .pad #68
-; THUMBV6-NEXT: sub sp, #68
-; THUMBV6-NEXT: mov r4, r3
-; THUMBV6-NEXT: str r2, [sp, #56] @ 4-byte Spill
-; THUMBV6-NEXT: mov r6, r0
+; THUMBV6-NEXT: .pad #60
+; THUMBV6-NEXT: sub sp, #60
+; THUMBV6-NEXT: mov r6, r3
+; THUMBV6-NEXT: mov r1, r2
+; THUMBV6-NEXT: str r2, [sp, #52] @ 4-byte Spill
+; THUMBV6-NEXT: mov r4, r0
+; THUMBV6-NEXT: str r0, [sp, #40] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r2, [sp, #88]
+; THUMBV6-NEXT: str r2, [sp, #48] @ 4-byte Spill
; THUMBV6-NEXT: movs r5, #0
-; THUMBV6-NEXT: str r5, [sp, #12]
-; THUMBV6-NEXT: str r5, [sp, #8]
-; THUMBV6-NEXT: ldr r0, [sp, #100]
-; THUMBV6-NEXT: str r0, [sp, #28] @ 4-byte Spill
-; THUMBV6-NEXT: str r0, [sp, #4]
-; THUMBV6-NEXT: ldr r0, [sp, #96]
-; THUMBV6-NEXT: str r0, [sp, #64] @ 4-byte Spill
-; THUMBV6-NEXT: str r0, [sp]
-; THUMBV6-NEXT: mov r0, r2
-; THUMBV6-NEXT: mov r1, r3
-; THUMBV6-NEXT: mov r2, r5
+; THUMBV6-NEXT: mov r0, r1
+; THUMBV6-NEXT: mov r1, r5
; THUMBV6-NEXT: mov r3, r5
-; THUMBV6-NEXT: bl __multi3
-; THUMBV6-NEXT: str r2, [sp, #48] @ 4-byte Spill
-; THUMBV6-NEXT: str r3, [sp, #52] @ 4-byte Spill
-; THUMBV6-NEXT: str r6, [sp, #44] @ 4-byte Spill
-; THUMBV6-NEXT: stm r6!, {r0, r1}
-; THUMBV6-NEXT: ldr r2, [sp, #104]
-; THUMBV6-NEXT: str r2, [sp, #60] @ 4-byte Spill
-; THUMBV6-NEXT: mov r0, r4
+; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: str r1, [sp, #28] @ 4-byte Spill
+; THUMBV6-NEXT: str r0, [r4]
+; THUMBV6-NEXT: ldr r2, [sp, #96]
+; THUMBV6-NEXT: str r2, [sp, #36] @ 4-byte Spill
+; THUMBV6-NEXT: mov r4, r6
+; THUMBV6-NEXT: str r6, [sp, #56] @ 4-byte Spill
+; THUMBV6-NEXT: mov r0, r6
; THUMBV6-NEXT: mov r1, r5
; THUMBV6-NEXT: mov r3, r5
; THUMBV6-NEXT: bl __aeabi_lmul
-; THUMBV6-NEXT: str r0, [sp, #36] @ 4-byte Spill
+; THUMBV6-NEXT: str r0, [sp, #44] @ 4-byte Spill
; THUMBV6-NEXT: mov r7, r1
; THUMBV6-NEXT: subs r0, r1, #1
; THUMBV6-NEXT: sbcs r7, r0
-; THUMBV6-NEXT: ldr r6, [sp, #108]
-; THUMBV6-NEXT: mov r0, r6
+; THUMBV6-NEXT: ldr r0, [sp, #100]
+; THUMBV6-NEXT: str r0, [sp, #32] @ 4-byte Spill
; THUMBV6-NEXT: mov r1, r5
-; THUMBV6-NEXT: ldr r2, [sp, #56] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r6, [sp, #52] @ 4-byte Reload
+; THUMBV6-NEXT: mov r2, r6
; THUMBV6-NEXT: mov r3, r5
; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: str r0, [sp, #24] @ 4-byte Spill
; THUMBV6-NEXT: subs r2, r1, #1
; THUMBV6-NEXT: sbcs r1, r2
; THUMBV6-NEXT: subs r2, r4, #1
+; THUMBV6-NEXT: mov r3, r4
+; THUMBV6-NEXT: sbcs r3, r2
+; THUMBV6-NEXT: ldr r4, [sp, #32] @ 4-byte Reload
+; THUMBV6-NEXT: subs r2, r4, #1
; THUMBV6-NEXT: sbcs r4, r2
-; THUMBV6-NEXT: str r6, [sp, #40] @ 4-byte Spill
-; THUMBV6-NEXT: subs r2, r6, #1
-; THUMBV6-NEXT: sbcs r6, r2
-; THUMBV6-NEXT: ands r6, r4
-; THUMBV6-NEXT: orrs r6, r1
-; THUMBV6-NEXT: orrs r6, r7
-; THUMBV6-NEXT: ldr r1, [sp, #36] @ 4-byte Reload
-; THUMBV6-NEXT: adds r4, r0, r1
-; THUMBV6-NEXT: ldr r0, [sp, #60] @ 4-byte Reload
+; THUMBV6-NEXT: ands r4, r3
+; THUMBV6-NEXT: orrs r4, r1
+; THUMBV6-NEXT: orrs r4, r7
+; THUMBV6-NEXT: ldr r0, [sp, #44] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r1, [sp, #24] @ 4-byte Reload
+; THUMBV6-NEXT: adds r7, r1, r0
+; THUMBV6-NEXT: ldr r0, [sp, #36] @ 4-byte Reload
; THUMBV6-NEXT: mov r1, r5
-; THUMBV6-NEXT: ldr r2, [sp, #56] @ 4-byte Reload
+; THUMBV6-NEXT: mov r2, r6
; THUMBV6-NEXT: mov r3, r5
; THUMBV6-NEXT: bl __aeabi_lmul
-; THUMBV6-NEXT: str r0, [sp, #36] @ 4-byte Spill
-; THUMBV6-NEXT: adds r0, r1, r4
-; THUMBV6-NEXT: str r0, [sp, #32] @ 4-byte Spill
+; THUMBV6-NEXT: str r0, [sp, #24] @ 4-byte Spill
+; THUMBV6-NEXT: adds r0, r1, r7
+; THUMBV6-NEXT: str r0, [sp, #20] @ 4-byte Spill
; THUMBV6-NEXT: mov r0, r5
; THUMBV6-NEXT: adcs r0, r5
-; THUMBV6-NEXT: orrs r0, r6
-; THUMBV6-NEXT: str r0, [sp, #24] @ 4-byte Spill
-; THUMBV6-NEXT: ldr r4, [sp, #88]
-; THUMBV6-NEXT: ldr r7, [sp, #28] @ 4-byte Reload
-; THUMBV6-NEXT: mov r0, r7
+; THUMBV6-NEXT: orrs r0, r4
+; THUMBV6-NEXT: str r0, [sp, #16] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r0, [sp, #92]
+; THUMBV6-NEXT: str r0, [sp, #44] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r7, [sp, #80]
; THUMBV6-NEXT: mov r1, r5
-; THUMBV6-NEXT: mov r2, r4
+; THUMBV6-NEXT: mov r2, r7
; THUMBV6-NEXT: mov r3, r5
; THUMBV6-NEXT: bl __aeabi_lmul
-; THUMBV6-NEXT: str r0, [sp, #20] @ 4-byte Spill
-; THUMBV6-NEXT: mov r6, r1
+; THUMBV6-NEXT: str r0, [sp, #12] @ 4-byte Spill
+; THUMBV6-NEXT: mov r4, r1
; THUMBV6-NEXT: subs r0, r1, #1
-; THUMBV6-NEXT: sbcs r6, r0
-; THUMBV6-NEXT: ldr r0, [sp, #92]
-; THUMBV6-NEXT: str r0, [sp, #56] @ 4-byte Spill
+; THUMBV6-NEXT: sbcs r4, r0
+; THUMBV6-NEXT: ldr r6, [sp, #84]
+; THUMBV6-NEXT: mov r0, r6
; THUMBV6-NEXT: mov r1, r5
-; THUMBV6-NEXT: ldr r2, [sp, #64] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r2, [sp, #48] @ 4-byte Reload
; THUMBV6-NEXT: mov r3, r5
; THUMBV6-NEXT: bl __aeabi_lmul
-; THUMBV6-NEXT: str r0, [sp, #16] @ 4-byte Spill
+; THUMBV6-NEXT: str r0, [sp, #4] @ 4-byte Spill
; THUMBV6-NEXT: subs r2, r1, #1
; THUMBV6-NEXT: sbcs r1, r2
-; THUMBV6-NEXT: subs r2, r7, #1
-; THUMBV6-NEXT: sbcs r7, r2
-; THUMBV6-NEXT: mov r3, r7
-; THUMBV6-NEXT: ldr r7, [sp, #56] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r3, [sp, #44] @ 4-byte Reload
+; THUMBV6-NEXT: subs r2, r3, #1
+; THUMBV6-NEXT: sbcs r3, r2
+; THUMBV6-NEXT: str r6, [sp, #8] @ 4-byte Spill
+; THUMBV6-NEXT: subs r2, r6, #1
+; THUMBV6-NEXT: sbcs r6, r2
+; THUMBV6-NEXT: ands r6, r3
+; THUMBV6-NEXT: orrs r6, r1
+; THUMBV6-NEXT: orrs r6, r4
+; THUMBV6-NEXT: ldr r0, [sp, #12] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r1, [sp, #4] @ 4-byte Reload
+; THUMBV6-NEXT: adds r0, r1, r0
+; THUMBV6-NEXT: str r0, [sp, #4] @ 4-byte Spill
+; THUMBV6-NEXT: mov r0, r7
+; THUMBV6-NEXT: mov r1, r5
+; THUMBV6-NEXT: ldr r4, [sp, #48] @ 4-byte Reload
+; THUMBV6-NEXT: mov r2, r4
+; THUMBV6-NEXT: mov r3, r5
+; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: str r0, [sp, #12] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r0, [sp, #4] @ 4-byte Reload
+; THUMBV6-NEXT: adds r0, r1, r0
+; THUMBV6-NEXT: mov r1, r5
+; THUMBV6-NEXT: adcs r1, r5
+; THUMBV6-NEXT: orrs r1, r6
+; THUMBV6-NEXT: ldr r3, [sp, #36] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r2, [sp, #32] @ 4-byte Reload
+; THUMBV6-NEXT: orrs r3, r2
+; THUMBV6-NEXT: subs r2, r3, #1
+; THUMBV6-NEXT: sbcs r3, r2
+; THUMBV6-NEXT: ldr r2, [sp, #8] @ 4-byte Reload
+; THUMBV6-NEXT: orrs r7, r2
; THUMBV6-NEXT: subs r2, r7, #1
; THUMBV6-NEXT: sbcs r7, r2
; THUMBV6-NEXT: ands r7, r3
; THUMBV6-NEXT: orrs r7, r1
-; THUMBV6-NEXT: orrs r7, r6
-; THUMBV6-NEXT: ldr r0, [sp, #20] @ 4-byte Reload
; THUMBV6-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
-; THUMBV6-NEXT: adds r6, r1, r0
-; THUMBV6-NEXT: mov r0, r4
+; THUMBV6-NEXT: orrs r7, r1
+; THUMBV6-NEXT: ldr r1, [sp, #24] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r2, [sp, #12] @ 4-byte Reload
+; THUMBV6-NEXT: adds r1, r2, r1
+; THUMBV6-NEXT: str r1, [sp, #32] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r1, [sp, #20] @ 4-byte Reload
+; THUMBV6-NEXT: adcs r0, r1
+; THUMBV6-NEXT: str r0, [sp, #36] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r0, [sp, #56] @ 4-byte Reload
; THUMBV6-NEXT: mov r1, r5
-; THUMBV6-NEXT: ldr r2, [sp, #64] @ 4-byte Reload
+; THUMBV6-NEXT: mov r2, r4
+; THUMBV6-NEXT: mov r3, r5
+; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: mov r4, r1
+; THUMBV6-NEXT: ldr r1, [sp, #28] @ 4-byte Reload
+; THUMBV6-NEXT: adds r6, r0, r1
+; THUMBV6-NEXT: adcs r4, r5
+; THUMBV6-NEXT: ldr r0, [sp, #52] @ 4-byte Reload
+; THUMBV6-NEXT: mov r1, r5
+; THUMBV6-NEXT: ldr r2, [sp, #44] @ 4-byte Reload
+; THUMBV6-NEXT: mov r3, r5
+; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: adds r0, r0, r6
+; THUMBV6-NEXT: ldr r2, [sp, #40] @ 4-byte Reload
+; THUMBV6-NEXT: str r0, [r2, #4]
+; THUMBV6-NEXT: adcs r1, r5
+; THUMBV6-NEXT: adds r0, r4, r1
+; THUMBV6-NEXT: str r0, [sp, #28] @ 4-byte Spill
+; THUMBV6-NEXT: mov r6, r5
+; THUMBV6-NEXT: adcs r6, r5
+; THUMBV6-NEXT: ldr r0, [sp, #56] @ 4-byte Reload
+; THUMBV6-NEXT: mov r1, r5
+; THUMBV6-NEXT: ldr r4, [sp, #44] @ 4-byte Reload
+; THUMBV6-NEXT: mov r2, r4
; THUMBV6-NEXT: mov r3, r5
; THUMBV6-NEXT: bl __aeabi_lmul
-; THUMBV6-NEXT: adds r1, r1, r6
+; THUMBV6-NEXT: ldr r2, [sp, #28] @ 4-byte Reload
+; THUMBV6-NEXT: adds r0, r0, r2
+; THUMBV6-NEXT: str r0, [sp, #28] @ 4-byte Spill
+; THUMBV6-NEXT: adcs r1, r6
+; THUMBV6-NEXT: str r1, [sp, #24] @ 4-byte Spill
+; THUMBV6-NEXT: ldr r0, [sp, #48] @ 4-byte Reload
+; THUMBV6-NEXT: mov r1, r4
; THUMBV6-NEXT: mov r2, r5
-; THUMBV6-NEXT: adcs r2, r5
-; THUMBV6-NEXT: orrs r2, r7
-; THUMBV6-NEXT: ldr r6, [sp, #60] @ 4-byte Reload
-; THUMBV6-NEXT: ldr r3, [sp, #40] @ 4-byte Reload
-; THUMBV6-NEXT: orrs r6, r3
-; THUMBV6-NEXT: subs r3, r6, #1
-; THUMBV6-NEXT: sbcs r6, r3
-; THUMBV6-NEXT: ldr r3, [sp, #56] @ 4-byte Reload
-; THUMBV6-NEXT: orrs r4, r3
-; THUMBV6-NEXT: subs r3, r4, #1
-; THUMBV6-NEXT: sbcs r4, r3
-; THUMBV6-NEXT: ands r4, r6
-; THUMBV6-NEXT: orrs r4, r2
+; THUMBV6-NEXT: mov r3, r5
+; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: mov r6, r0
+; THUMBV6-NEXT: mov r4, r1
+; THUMBV6-NEXT: ldr r0, [sp, #52] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r1, [sp, #56] @ 4-byte Reload
+; THUMBV6-NEXT: mov r2, r5
+; THUMBV6-NEXT: mov r3, r5
+; THUMBV6-NEXT: bl __aeabi_lmul
+; THUMBV6-NEXT: adds r0, r0, r6
+; THUMBV6-NEXT: adcs r1, r4
+; THUMBV6-NEXT: ldr r2, [sp, #28] @ 4-byte Reload
+; THUMBV6-NEXT: adds r0, r2, r0
; THUMBV6-NEXT: ldr r2, [sp, #24] @ 4-byte Reload
-; THUMBV6-NEXT: orrs r4, r2
-; THUMBV6-NEXT: ldr r2, [sp, #36] @ 4-byte Reload
-; THUMBV6-NEXT: adds r0, r0, r2
-; THUMBV6-NEXT: ldr r2, [sp, #32] @ 4-byte Reload
; THUMBV6-NEXT: adcs r1, r2
-; THUMBV6-NEXT: ldr r2, [sp, #48] @ 4-byte Reload
-; THUMBV6-NEXT: adds r0, r2, r0
-; THUMBV6-NEXT: ldr r2, [sp, #44] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r2, [sp, #32] @ 4-byte Reload
+; THUMBV6-NEXT: adds r0, r0, r2
+; THUMBV6-NEXT: ldr r2, [sp, #40] @ 4-byte Reload
; THUMBV6-NEXT: str r0, [r2, #8]
-; THUMBV6-NEXT: ldr r0, [sp, #52] @ 4-byte Reload
+; THUMBV6-NEXT: ldr r0, [sp, #36] @ 4-byte Reload
; THUMBV6-NEXT: adcs r1, r0
; THUMBV6-NEXT: str r1, [r2, #12]
; THUMBV6-NEXT: adcs r5, r5
-; THUMBV6-NEXT: orrs r5, r4
+; THUMBV6-NEXT: orrs r5, r7
; THUMBV6-NEXT: movs r0, #1
; THUMBV6-NEXT: ands r0, r5
; THUMBV6-NEXT: strb r0, [r2, #16]
-; THUMBV6-NEXT: add sp, #68
+; THUMBV6-NEXT: add sp, #60
; THUMBV6-NEXT: pop {r4, r5, r6, r7, pc}
start:
%0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2
diff --git a/llvm/test/CodeGen/Thumb2/umulo-128-legalisation-lowering.ll b/llvm/test/CodeGen/Thumb2/umulo-128-legalisation-lowering.ll
index f57c9226179b5..cff16c300e703 100644
--- a/llvm/test/CodeGen/Thumb2/umulo-128-legalisation-lowering.ll
+++ b/llvm/test/CodeGen/Thumb2/umulo-128-legalisation-lowering.ll
@@ -8,100 +8,121 @@ define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
; THUMBV7-NEXT: push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; THUMBV7-NEXT: .pad #44
; THUMBV7-NEXT: sub sp, #44
+; THUMBV7-NEXT: ldr.w lr, [sp, #88]
+; THUMBV7-NEXT: mov r11, r0
+; THUMBV7-NEXT: ldr r4, [sp, #96]
+; THUMBV7-NEXT: ldr.w r12, [sp, #80]
+; THUMBV7-NEXT: umull r1, r5, r2, lr
+; THUMBV7-NEXT: umull r7, r6, r3, r4
+; THUMBV7-NEXT: str r1, [sp, #40] @ 4-byte Spill
+; THUMBV7-NEXT: ldr r1, [sp, #100]
+; THUMBV7-NEXT: umull r4, r0, r4, r2
+; THUMBV7-NEXT: str r7, [sp, #32] @ 4-byte Spill
+; THUMBV7-NEXT: umull r7, r1, r1, r2
+; THUMBV7-NEXT: str r4, [sp, #24] @ 4-byte Spill
+; THUMBV7-NEXT: str r0, [sp, #12] @ 4-byte Spill
+; THUMBV7-NEXT: ldr r0, [sp, #84]
+; THUMBV7-NEXT: str r7, [sp, #20] @ 4-byte Spill
+; THUMBV7-NEXT: ldr r7, [sp, #92]
+; THUMBV7-NEXT: umull r10, r8, r0, lr
+; THUMBV7-NEXT: umull r4, r9, r7, r12
+; THUMBV7-NEXT: str r4, [sp, #8] @ 4-byte Spill
+; THUMBV7-NEXT: umull r4, r0, r12, lr
+; THUMBV7-NEXT: mov.w r12, #0
+; THUMBV7-NEXT: umlal r5, r12, r3, lr
+; THUMBV7-NEXT: str r4, [sp, #16] @ 4-byte Spill
+; THUMBV7-NEXT: str r0, [sp, #4] @ 4-byte Spill
+; THUMBV7-NEXT: umull r4, r2, r2, r7
+; THUMBV7-NEXT: ldr r0, [sp, #40] @ 4-byte Reload
+; THUMBV7-NEXT: str r4, [sp, #28] @ 4-byte Spill
+; THUMBV7-NEXT: str r2, [sp, #36] @ 4-byte Spill
+; THUMBV7-NEXT: str.w r0, [r11]
+; THUMBV7-NEXT: ldr r0, [sp, #32] @ 4-byte Reload
+; THUMBV7-NEXT: ldr r2, [sp, #20] @ 4-byte Reload
+; THUMBV7-NEXT: add r2, r0
+; THUMBV7-NEXT: ldr r0, [sp, #12] @ 4-byte Reload
+; THUMBV7-NEXT: adds.w lr, r0, r2
+; THUMBV7-NEXT: mov.w r2, #0
+; THUMBV7-NEXT: adc r0, r2, #0
+; THUMBV7-NEXT: str r0, [sp, #32] @ 4-byte Spill
+; THUMBV7-NEXT: ldr r0, [sp, #8] @ 4-byte Reload
+; THUMBV7-NEXT: add.w r4, r10, r0
+; THUMBV7-NEXT: ldr r0, [sp, #4] @ 4-byte Reload
+; THUMBV7-NEXT: adds r4, r4, r0
+; THUMBV7-NEXT: adc r0, r2, #0
; THUMBV7-NEXT: str r0, [sp, #40] @ 4-byte Spill
-; THUMBV7-NEXT: movs r0, #0
-; THUMBV7-NEXT: ldrd r4, r7, [sp, #88]
-; THUMBV7-NEXT: mov r5, r3
-; THUMBV7-NEXT: strd r0, r0, [sp, #8]
-; THUMBV7-NEXT: mov r1, r3
-; THUMBV7-NEXT: mov r6, r2
-; THUMBV7-NEXT: mov r0, r2
-; THUMBV7-NEXT: movs r2, #0
-; THUMBV7-NEXT: movs r3, #0
-; THUMBV7-NEXT: strd r4, r7, [sp]
-; THUMBV7-NEXT: bl __multi3
-; THUMBV7-NEXT: strd r1, r0, [sp, #32] @ 8-byte Folded Spill
-; THUMBV7-NEXT: strd r3, r2, [sp, #24] @ 8-byte Folded Spill
-; THUMBV7-NEXT: ldrd r2, r0, [sp, #96]
-; THUMBV7-NEXT: ldr.w r9, [sp, #80]
-; THUMBV7-NEXT: umull lr, r0, r0, r6
-; THUMBV7-NEXT: ldr.w r11, [sp, #84]
-; THUMBV7-NEXT: umull r3, r1, r5, r2
-; THUMBV7-NEXT: umull r2, r12, r2, r6
-; THUMBV7-NEXT: add r3, lr
-; THUMBV7-NEXT: umull r8, r10, r7, r9
-; THUMBV7-NEXT: str r2, [sp, #20] @ 4-byte Spill
-; THUMBV7-NEXT: adds.w lr, r12, r3
-; THUMBV7-NEXT: umull r6, r9, r9, r4
-; THUMBV7-NEXT: mov.w r3, #0
-; THUMBV7-NEXT: adc r12, r3, #0
-; THUMBV7-NEXT: umull r2, r4, r11, r4
-; THUMBV7-NEXT: add r2, r8
-; THUMBV7-NEXT: mov.w r8, #0
-; THUMBV7-NEXT: adds.w r2, r2, r9
-; THUMBV7-NEXT: adc r9, r3, #0
-; THUMBV7-NEXT: ldr r3, [sp, #20] @ 4-byte Reload
-; THUMBV7-NEXT: adds r3, r3, r6
-; THUMBV7-NEXT: ldr r6, [sp, #28] @ 4-byte Reload
-; THUMBV7-NEXT: adc.w r2, r2, lr
-; THUMBV7-NEXT: adds r3, r3, r6
-; THUMBV7-NEXT: ldr r6, [sp, #24] @ 4-byte Reload
-; THUMBV7-NEXT: adcs r2, r6
-; THUMBV7-NEXT: ldrd r6, lr, [sp, #36] @ 8-byte Folded Reload
-; THUMBV7-NEXT: str.w r6, [lr]
-; THUMBV7-NEXT: adc r8, r8, #0
-; THUMBV7-NEXT: ldr r6, [sp, #32] @ 4-byte Reload
-; THUMBV7-NEXT: cmp r5, #0
-; THUMBV7-NEXT: strd r6, r3, [lr, #4]
-; THUMBV7-NEXT: str.w r2, [lr, #12]
+; THUMBV7-NEXT: ldr r0, [sp, #24] @ 4-byte Reload
+; THUMBV7-NEXT: ldr r2, [sp, #16] @ 4-byte Reload
+; THUMBV7-NEXT: adds.w r10, r2, r0
+; THUMBV7-NEXT: mov r2, r3
+; THUMBV7-NEXT: adc.w r0, r4, lr
+; THUMBV7-NEXT: ldr.w lr, [sp, #100]
+; THUMBV7-NEXT: cmp r1, #0
+; THUMBV7-NEXT: str r0, [sp, #24] @ 4-byte Spill
; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne r5, #1
-; THUMBV7-NEXT: ldr r2, [sp, #100]
-; THUMBV7-NEXT: cmp r2, #0
-; THUMBV7-NEXT: mov r3, r2
+; THUMBV7-NEXT: movne r1, #1
+; THUMBV7-NEXT: cmp r3, #0
+; THUMBV7-NEXT: mov r0, lr
; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne r3, #1
-; THUMBV7-NEXT: cmp r0, #0
+; THUMBV7-NEXT: movne r2, #1
+; THUMBV7-NEXT: cmp.w lr, #0
; THUMBV7-NEXT: it ne
; THUMBV7-NEXT: movne r0, #1
-; THUMBV7-NEXT: cmp r1, #0
-; THUMBV7-NEXT: and.w r3, r3, r5
+; THUMBV7-NEXT: ldr r4, [sp, #28] @ 4-byte Reload
+; THUMBV7-NEXT: ands r0, r2
+; THUMBV7-NEXT: orrs r1, r0
+; THUMBV7-NEXT: adds r5, r5, r4
+; THUMBV7-NEXT: str.w r5, [r11, #4]
+; THUMBV7-NEXT: ldr r0, [sp, #36] @ 4-byte Reload
+; THUMBV7-NEXT: mov.w r5, #0
+; THUMBV7-NEXT: adcs.w r0, r0, r12
+; THUMBV7-NEXT: adc r2, r5, #0
+; THUMBV7-NEXT: cmp r6, #0
; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne r1, #1
-; THUMBV7-NEXT: orrs r0, r3
+; THUMBV7-NEXT: movne r6, #1
+; THUMBV7-NEXT: orrs r1, r6
+; THUMBV7-NEXT: ldr r6, [sp, #84]
+; THUMBV7-NEXT: umlal r0, r2, r3, r7
+; THUMBV7-NEXT: ldr r3, [sp, #32] @ 4-byte Reload
; THUMBV7-NEXT: cmp r7, #0
-; THUMBV7-NEXT: orr.w r0, r0, r1
; THUMBV7-NEXT: it ne
; THUMBV7-NEXT: movne r7, #1
-; THUMBV7-NEXT: cmp.w r11, #0
-; THUMBV7-NEXT: mov r1, r11
-; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne r1, #1
-; THUMBV7-NEXT: cmp r4, #0
-; THUMBV7-NEXT: ldr r3, [sp, #96]
+; THUMBV7-NEXT: orrs r1, r3
+; THUMBV7-NEXT: mov r3, r6
+; THUMBV7-NEXT: cmp r6, #0
; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne r4, #1
-; THUMBV7-NEXT: cmp.w r10, #0
-; THUMBV7-NEXT: and.w r1, r1, r7
+; THUMBV7-NEXT: movne r3, #1
+; THUMBV7-NEXT: cmp.w r8, #0
+; THUMBV7-NEXT: and.w r3, r3, r7
+; THUMBV7-NEXT: ldr r7, [sp, #80]
; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne.w r10, #1
-; THUMBV7-NEXT: orrs r3, r2
-; THUMBV7-NEXT: ldr r2, [sp, #80]
-; THUMBV7-NEXT: orr.w r1, r1, r4
-; THUMBV7-NEXT: orr.w r1, r1, r10
+; THUMBV7-NEXT: movne.w r8, #1
+; THUMBV7-NEXT: cmp.w r9, #0
; THUMBV7-NEXT: it ne
-; THUMBV7-NEXT: movne r3, #1
-; THUMBV7-NEXT: orrs.w r7, r2, r11
-; THUMBV7-NEXT: orr.w r1, r1, r9
+; THUMBV7-NEXT: movne.w r9, #1
+; THUMBV7-NEXT: orrs r7, r6
+; THUMBV7-NEXT: ldr r6, [sp, #96]
; THUMBV7-NEXT: it ne
; THUMBV7-NEXT: movne r7, #1
-; THUMBV7-NEXT: ands r3, r7
-; THUMBV7-NEXT: orr.w r0, r0, r12
-; THUMBV7-NEXT: orrs r1, r3
+; THUMBV7-NEXT: orr.w r3, r3, r8
+; THUMBV7-NEXT: orrs.w r6, r6, lr
+; THUMBV7-NEXT: orr.w r3, r3, r9
+; THUMBV7-NEXT: it ne
+; THUMBV7-NEXT: movne r6, #1
+; THUMBV7-NEXT: adds.w r0, r0, r10
+; THUMBV7-NEXT: str.w r0, [r11, #8]
+; THUMBV7-NEXT: ldr r0, [sp, #24] @ 4-byte Reload
+; THUMBV7-NEXT: adcs r0, r2
+; THUMBV7-NEXT: str.w r0, [r11, #12]
+; THUMBV7-NEXT: ldr r0, [sp, #40] @ 4-byte Reload
+; THUMBV7-NEXT: and.w r2, r7, r6
+; THUMBV7-NEXT: orr.w r0, r0, r3
+; THUMBV7-NEXT: orr.w r0, r0, r2
+; THUMBV7-NEXT: orr.w r0, r0, r1
+; THUMBV7-NEXT: adc r1, r5, #0
; THUMBV7-NEXT: orrs r0, r1
-; THUMBV7-NEXT: orr.w r0, r0, r8
; THUMBV7-NEXT: and r0, r0, #1
-; THUMBV7-NEXT: strb.w r0, [lr, #16]
+; THUMBV7-NEXT: strb.w r0, [r11, #16]
; THUMBV7-NEXT: add sp, #44
; THUMBV7-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
start:
More information about the llvm-commits
mailing list