mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
ba36647456
There's an existing optimization for x != C, but somehow it was missing a special case for 0. While I'm here, also cleaned up the code/comments a bit: the second value produced by the MERGE_VALUES was actually dead, since a CMOV only produces one result. Differential Revision: https://reviews.llvm.org/D59616 llvm-svn: 357437
160 lines
5.9 KiB
LLVM
160 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=thumb-eabi -mattr=+v6 | FileCheck %s --check-prefixes=THUMBV6
|
|
|
|
define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
|
|
; THUMBV6-LABEL: muloti_test:
|
|
; 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: 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 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: mov r1, r5
|
|
; THUMBV6-NEXT: mov r3, r5
|
|
; THUMBV6-NEXT: bl __aeabi_lmul
|
|
; THUMBV6-NEXT: str r0, [sp, #36] @ 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: mov r1, r5
|
|
; THUMBV6-NEXT: ldr r2, [sp, #56] @ 4-byte Reload
|
|
; THUMBV6-NEXT: mov r3, r5
|
|
; THUMBV6-NEXT: bl __aeabi_lmul
|
|
; THUMBV6-NEXT: subs r2, r1, #1
|
|
; THUMBV6-NEXT: sbcs r1, r2
|
|
; 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: mov r1, r5
|
|
; THUMBV6-NEXT: ldr r2, [sp, #56] @ 4-byte Reload
|
|
; 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: 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: mov r1, r5
|
|
; THUMBV6-NEXT: mov r2, r4
|
|
; 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: 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: mov r1, r5
|
|
; THUMBV6-NEXT: ldr r2, [sp, #64] @ 4-byte Reload
|
|
; THUMBV6-NEXT: mov r3, r5
|
|
; THUMBV6-NEXT: bl __aeabi_lmul
|
|
; THUMBV6-NEXT: str r0, [sp, #16] @ 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: 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: mov r1, r5
|
|
; THUMBV6-NEXT: ldr r2, [sp, #64] @ 4-byte Reload
|
|
; THUMBV6-NEXT: mov r3, r5
|
|
; THUMBV6-NEXT: bl __aeabi_lmul
|
|
; THUMBV6-NEXT: adds r1, r1, r6
|
|
; 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: 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: str r0, [r2, #8]
|
|
; THUMBV6-NEXT: ldr r0, [sp, #52] @ 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: movs r0, #1
|
|
; THUMBV6-NEXT: ands r0, r5
|
|
; THUMBV6-NEXT: strb r0, [r2, #16]
|
|
; THUMBV6-NEXT: add sp, #68
|
|
; THUMBV6-NEXT: pop {r4, r5, r6, r7, pc}
|
|
start:
|
|
%0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2
|
|
%1 = extractvalue { i128, i1 } %0, 0
|
|
%2 = extractvalue { i128, i1 } %0, 1
|
|
%3 = zext i1 %2 to i8
|
|
%4 = insertvalue { i128, i8 } undef, i128 %1, 0
|
|
%5 = insertvalue { i128, i8 } %4, i8 %3, 1
|
|
ret { i128, i8 } %5
|
|
}
|
|
|
|
; Function Attrs: nounwind readnone speculatable
|
|
declare { i128, i1 } @llvm.umul.with.overflow.i128(i128, i128) #1
|
|
|
|
attributes #0 = { nounwind readnone uwtable }
|
|
attributes #1 = { nounwind readnone speculatable }
|
|
attributes #2 = { nounwind }
|