Partially revert 92e18ffd803365c64910760ba20278f875d93681

llvm/lib/Target/ARM/ARMISelLowering.cpp

@@ -1204,8 +1204,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
     setOperationAction(ISD::ROTR, VT, Expand);
   }
   setOperationAction(ISD::CTTZ,  MVT::i32, Custom);
-  setOperationAction(ISD::CTPOP, MVT::i32, LibCall);
-  setOperationAction(ISD::CTPOP, MVT::i64, LibCall);
+  setOperationAction(ISD::CTPOP, MVT::i32, Expand);
   if (!Subtarget->hasV5TOps() || Subtarget->isThumb1Only()) {
     setOperationAction(ISD::CTLZ, MVT::i32, Expand);
     setOperationAction(ISD::CTLZ_ZERO_UNDEF, MVT::i32, LibCall);

llvm/test/CodeGen/ARM/popcnt.ll

@@ -324,19 +324,73 @@ define i32 @ctpop16(i16 %x) nounwind readnone {
 define i32 @ctpop32(i32 %x) nounwind readnone {
 ; CHECK-LABEL: ctpop32:
 ; CHECK:       @ %bb.0:
-; CHECK-NEXT:    b __popcountsi2
+; CHECK-NEXT:    ldr r1, .LCPI22_0
+; CHECK-NEXT:    ldr r2, .LCPI22_3
+; CHECK-NEXT:    and r1, r1, r0, lsr #1
+; CHECK-NEXT:    ldr r12, .LCPI22_1
+; CHECK-NEXT:    sub r0, r0, r1
+; CHECK-NEXT:    ldr r3, .LCPI22_2
+; CHECK-NEXT:    and r1, r0, r2
+; CHECK-NEXT:    and r0, r2, r0, lsr #2
+; CHECK-NEXT:    add r0, r1, r0
+; CHECK-NEXT:    add r0, r0, r0, lsr #4
+; CHECK-NEXT:    and r0, r0, r12
+; CHECK-NEXT:    mul r1, r0, r3
+; CHECK-NEXT:    lsr r0, r1, #24
+; CHECK-NEXT:    mov pc, lr
+; CHECK-NEXT:    .p2align 2
+; CHECK-NEXT:  @ %bb.1:
+; CHECK-NEXT:  .LCPI22_0:
+; CHECK-NEXT:    .long 1431655765 @ 0x55555555
+; CHECK-NEXT:  .LCPI22_1:
+; CHECK-NEXT:    .long 252645135 @ 0xf0f0f0f
+; CHECK-NEXT:  .LCPI22_2:
+; CHECK-NEXT:    .long 16843009 @ 0x1010101
+; CHECK-NEXT:  .LCPI22_3:
+; CHECK-NEXT:    .long 858993459 @ 0x33333333
   %count = tail call i32 @llvm.ctpop.i32(i32 %x)
   ret i32 %count
 }
 
 define i32 @ctpop64(i64 %x) nounwind readnone {
 ; CHECK-LABEL: ctpop64:
 ; CHECK:       @ %bb.0:
-; CHECK-NEXT:    .save {r11, lr}
-; CHECK-NEXT:    push {r11, lr}
-; CHECK-NEXT:    bl __popcountdi2
-; CHECK-NEXT:    pop {r11, lr}
+; CHECK-NEXT:    .save {r4, lr}
+; CHECK-NEXT:    push {r4, lr}
+; CHECK-NEXT:    ldr r2, .LCPI23_0
+; CHECK-NEXT:    ldr r3, .LCPI23_3
+; CHECK-NEXT:    and r4, r2, r0, lsr #1
+; CHECK-NEXT:    and r2, r2, r1, lsr #1
+; CHECK-NEXT:    sub r0, r0, r4
+; CHECK-NEXT:    sub r1, r1, r2
+; CHECK-NEXT:    and r4, r0, r3
+; CHECK-NEXT:    and r2, r1, r3
+; CHECK-NEXT:    and r0, r3, r0, lsr #2
+; CHECK-NEXT:    and r1, r3, r1, lsr #2
+; CHECK-NEXT:    add r0, r4, r0
+; CHECK-NEXT:    ldr lr, .LCPI23_1
+; CHECK-NEXT:    add r1, r2, r1
+; CHECK-NEXT:    ldr r12, .LCPI23_2
+; CHECK-NEXT:    add r0, r0, r0, lsr #4
+; CHECK-NEXT:    and r0, r0, lr
+; CHECK-NEXT:    add r1, r1, r1, lsr #4
+; CHECK-NEXT:    mul r2, r0, r12
+; CHECK-NEXT:    and r0, r1, lr
+; CHECK-NEXT:    mul r1, r0, r12
+; CHECK-NEXT:    lsr r0, r2, #24
+; CHECK-NEXT:    add r0, r0, r1, lsr #24
+; CHECK-NEXT:    pop {r4, lr}
 ; CHECK-NEXT:    mov pc, lr
+; CHECK-NEXT:    .p2align 2
+; CHECK-NEXT:  @ %bb.1:
+; CHECK-NEXT:  .LCPI23_0:
+; CHECK-NEXT:    .long 1431655765 @ 0x55555555
+; CHECK-NEXT:  .LCPI23_1:
+; CHECK-NEXT:    .long 252645135 @ 0xf0f0f0f
+; CHECK-NEXT:  .LCPI23_2:
+; CHECK-NEXT:    .long 16843009 @ 0x1010101
+; CHECK-NEXT:  .LCPI23_3:
+; CHECK-NEXT:    .long 858993459 @ 0x33333333
   %count = tail call i64 @llvm.ctpop.i64(i64 %x)
   %conv = trunc i64 %count to i32
   ret i32 %conv

llvm/test/CodeGen/Thumb2/mve-ctpop.ll

@@ -1,24 +1,62 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; NOTE: Assertions have been autoenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK
 
 define arm_aapcs_vfpcc <2 x i64> @ctpop_2i64_t(<2 x i64> %src){
 ; CHECK-LABEL: ctpop_2i64_t:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r4, r5, r7, lr}
 ; CHECK-NEXT:    push {r4, r5, r7, lr}
-; CHECK-NEXT:    .vsave {d8, d9}
-; CHECK-NEXT:    vpush {d8, d9}
-; CHECK-NEXT:    vmov q4, q0
-; CHECK-NEXT:    vmov r0, r1, d9
-; CHECK-NEXT:    bl __popcountdi2
-; CHECK-NEXT:    mov r4, r0
-; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    vmov r0, r1, d8
-; CHECK-NEXT:    bl __popcountdi2
-; CHECK-NEXT:    vmov q0[2], q0[0], r0, r4
-; CHECK-NEXT:    vmov q0[3], q0[1], r1, r5
-; CHECK-NEXT:    vpop {d8, d9}
+; CHECK-NEXT:    vmov r1, r2, d1
+; CHECK-NEXT:    mov.w lr, #1431655765
+; CHECK-NEXT:    vmov r3, r4, d0
+; CHECK-NEXT:    mov.w r12, #858993459
+; CHECK-NEXT:    vldr s1, .LCPI0_0
+; CHECK-NEXT:    vmov.f32 s3, s1
+; CHECK-NEXT:    and.w r0, lr, r2, lsr #1
+; CHECK-NEXT:    subs r0, r2, r0
+; CHECK-NEXT:    and.w r2, r12, r0, lsr #2
+; CHECK-NEXT:    bic r0, r0, #-858993460
+; CHECK-NEXT:    add r0, r2
+; CHECK-NEXT:    and.w r2, lr, r1, lsr #1
+; CHECK-NEXT:    subs r1, r1, r2
+; CHECK-NEXT:    add.w r0, r0, r0, lsr #4
+; CHECK-NEXT:    and.w r2, r12, r1, lsr #2
+; CHECK-NEXT:    bic r1, r1, #-858993460
+; CHECK-NEXT:    add r1, r2
+; CHECK-NEXT:    and.w r2, lr, r3, lsr #1
+; CHECK-NEXT:    subs r2, r3, r2
+; CHECK-NEXT:    bic r5, r0, #-252645136
+; CHECK-NEXT:    add.w r1, r1, r1, lsr #4
+; CHECK-NEXT:    mov.w r0, #16843009
+; CHECK-NEXT:    and.w r3, r12, r2, lsr #2
+; CHECK-NEXT:    bic r2, r2, #-858993460
+; CHECK-NEXT:    add r2, r3
+; CHECK-NEXT:    and.w r3, lr, r4, lsr #1
+; CHECK-NEXT:    subs r3, r4, r3
+; CHECK-NEXT:    bic r1, r1, #-252645136
+; CHECK-NEXT:    add.w r2, r2, r2, lsr #4
+; CHECK-NEXT:    muls r5, r0, r5
+; CHECK-NEXT:    and.w r4, r12, r3, lsr #2
+; CHECK-NEXT:    bic r3, r3, #-858993460
+; CHECK-NEXT:    bic r2, r2, #-252645136
+; CHECK-NEXT:    add r3, r4
+; CHECK-NEXT:    muls r1, r0, r1
+; CHECK-NEXT:    add.w r3, r3, r3, lsr #4
+; CHECK-NEXT:    muls r2, r0, r2
+; CHECK-NEXT:    bic r3, r3, #-252645136
+; CHECK-NEXT:    muls r0, r3, r0
+; CHECK-NEXT:    lsrs r1, r1, #24
+; CHECK-NEXT:    add.w r1, r1, r5, lsr #24
+; CHECK-NEXT:    lsrs r2, r2, #24
+; CHECK-NEXT:    vmov s2, r1
+; CHECK-NEXT:    add.w r0, r2, r0, lsr #24
+; CHECK-NEXT:    vmov s0, r0
 ; CHECK-NEXT:    pop {r4, r5, r7, pc}
+; CHECK-NEXT:    .p2align 2
+; CHECK-NEXT:  @ %bb.1:
+; CHECK-NEXT:  .LCPI0_0:
+; CHECK-NEXT:    .long 0x00000000 @ float 0
 entry:
   %0 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %src)
   ret <2 x i64> %0