SINK: Sink instructions to the block that the current block immediately dominates.

[cfang]

Summary

The Nearest common dominator of all users is the lowest point we could possibly sink the instruction
to. While instruction sinking approach is still empirical, performance regressions have been observed
related to register pressure. As a result, we revert to the previous approach to sink the instruction to
the earliest possible block, i.e. the block that current block immediately dominates.

llvm/lib/Transforms/Scalar/Sink.cpp

     Instruction *UseInst = cast<Instruction>(U.getUser());
     BasicBlock *UseBlock = UseInst->getParent();
     if (PHINode *PN = dyn_cast<PHINode>(UseInst)) {
       // PHI nodes use the operand in the predecessor block, not the block with
       // the PHI.
       unsigned Num = PHINode::getIncomingValueNumForOperand(U.getOperandNo());
       UseBlock = PN->getIncomingBlock(Num);
     }
-    if (SuccToSinkTo)
+    if (SuccToSinkTo) {
       SuccToSinkTo = DT.findNearestCommonDominator(SuccToSinkTo, UseBlock);
-    else
+      if (!SuccToSinkTo) // findNearestCommonDominator fails.
+        return false;
+    } else
       SuccToSinkTo = UseBlock;
     // The current basic block needs to dominate the candidate.
     if (!DT.dominates(BB, SuccToSinkTo))
       return false;
   }
 
-  if (SuccToSinkTo) {
-    // The nearest common dominator may be in a parent loop of BB, which may not
-    // be beneficial. Find an ancestor.
-    while (SuccToSinkTo != BB &&
-           !IsAcceptableTarget(Inst, SuccToSinkTo, DT, LI))
-      SuccToSinkTo = DT.getNode(SuccToSinkTo)->getIDom()->getBlock();
-    if (SuccToSinkTo == BB)
-      SuccToSinkTo = nullptr;
+  // No candidate block to sink to.
+  if (!SuccToSinkTo || SuccToSinkTo == BB)
+    return false;
+
+  // Nearest common dominator is the lowest point we may sink the instruction
+  // to. While instruction sinking approach is still empirical, performance
+  // regressions have been observed related to register pressure. As a result,
+  // we try to sink the instruction to the earliest possible block.
+  //
+  // Find the block that BB immediately dominates to sink this instruction to.
+  BasicBlock *CurBB = DT.getNode(SuccToSinkTo)->getIDom()->getBlock();
+  while (CurBB != BB ) {
+    SuccToSinkTo = CurBB;
+    CurBB = DT.getNode(CurBB)->getIDom()->getBlock();
   }
 
-  // If we couldn't find a block to sink to, ignore this instruction.
-  if (!SuccToSinkTo)
+  if (!IsAcceptableTarget(Inst, SuccToSinkTo, DT, LI))
     return false;
 
   LLVM_DEBUG(dbgs() << "Sink" << *Inst << " (";
              Inst->getParent()->printAsOperand(dbgs(), false); dbgs() << " -> ";
              SuccToSinkTo->printAsOperand(dbgs(), false); dbgs() << ")\n");
 
   // Move the instruction.
   Inst->moveBefore(&*SuccToSinkTo->getFirstInsertionPt());

llvm/test/CodeGen/AMDGPU/sdiv64.ll

 ; GCN-IR-NEXT:    s_branch BB0_7
 ; GCN-IR-NEXT:  BB0_5:
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v3, 0
 ; GCN-IR-NEXT:  BB0_6: ; %Flow6
 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
-; GCN-IR-NEXT:  BB0_7: ; %udiv-end
+; GCN-IR-NEXT:  BB0_7: ; %Flow7
 ; GCN-IR-NEXT:    s_xor_b64 s[0:1], s[8:9], s[2:3]
 ; GCN-IR-NEXT:    v_xor_b32_e32 v0, s0, v0
 ; GCN-IR-NEXT:    v_xor_b32_e32 v1, s1, v1
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s1
 ; GCN-IR-NEXT:    v_subrev_i32_e32 v0, vcc, s0, v0
+; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v1, v2, vcc
 ; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
 ; GCN-IR-NEXT:    s_mov_b32 s6, -1
-; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v1, v2, vcc
 ; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %result = sdiv i64 %x, %y
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 define i64 @v_test_sdiv(i64 %x, i64 %y) {

 ; GCN-IR-NEXT:    v_ffbh_u32_e32 v7, v3
 ; GCN-IR-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v3
 ; GCN-IR-NEXT:    v_cndmask_b32_e32 v13, v7, v0, vcc
 ; GCN-IR-NEXT:    v_ffbh_u32_e32 v0, v9
 ; GCN-IR-NEXT:    v_add_i32_e32 v0, vcc, 32, v0
 ; GCN-IR-NEXT:    v_ffbh_u32_e32 v7, v10
 ; GCN-IR-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v10
 ; GCN-IR-NEXT:    v_cndmask_b32_e32 v14, v7, v0, vcc
-; GCN-IR-NEXT:    v_sub_i32_e32 v7, vcc, v13, v14
-; GCN-IR-NEXT:    v_subb_u32_e64 v8, s[4:5], 0, 0, vcc
-; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, 63, v[7:8]
-; GCN-IR-NEXT:    v_cmp_ne_u64_e64 s[4:5], 63, v[7:8]
+; GCN-IR-NEXT:    v_sub_i32_e32 v11, vcc, v13, v14
+; GCN-IR-NEXT:    v_subb_u32_e64 v12, s[4:5], 0, 0, vcc
+; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, 63, v[11:12]
+; GCN-IR-NEXT:    v_cmp_ne_u64_e64 s[4:5], 63, v[11:12]
 ; GCN-IR-NEXT:    s_or_b64 s[6:7], s[6:7], vcc
 ; GCN-IR-NEXT:    s_xor_b64 s[8:9], s[6:7], -1
 ; GCN-IR-NEXT:    v_mov_b32_e32 v18, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v6, v4
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, v5
-; GCN-IR-NEXT:    v_cndmask_b32_e64 v12, v10, 0, s[6:7]
+; GCN-IR-NEXT:    v_cndmask_b32_e64 v7, v10, 0, s[6:7]
 ; GCN-IR-NEXT:    s_and_b64 s[4:5], s[8:9], s[4:5]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v15, v18
 ; GCN-IR-NEXT:    v_cndmask_b32_e64 v0, v9, 0, s[6:7]
 ; GCN-IR-NEXT:    s_and_saveexec_b64 s[6:7], s[4:5]
 ; GCN-IR-NEXT:    s_cbranch_execz BB1_6
 ; GCN-IR-NEXT:  ; %bb.1: ; %udiv-bb1
-; GCN-IR-NEXT:    v_add_i32_e32 v16, vcc, 1, v7
-; GCN-IR-NEXT:    v_addc_u32_e32 v17, vcc, 0, v8, vcc
-; GCN-IR-NEXT:    v_sub_i32_e64 v0, s[4:5], 63, v7
-; GCN-IR-NEXT:    v_cmp_ge_u64_e32 vcc, v[16:17], v[7:8]
+; GCN-IR-NEXT:    v_add_i32_e32 v16, vcc, 1, v11
+; GCN-IR-NEXT:    v_addc_u32_e32 v17, vcc, 0, v12, vcc
+; GCN-IR-NEXT:    v_sub_i32_e64 v0, s[4:5], 63, v11
+; GCN-IR-NEXT:    v_cmp_ge_u64_e32 vcc, v[16:17], v[11:12]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v11, 0
 ; GCN-IR-NEXT:    v_lshl_b64 v[7:8], v[9:10], v0
 ; GCN-IR-NEXT:    s_mov_b64 s[8:9], 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v12, 0
 ; GCN-IR-NEXT:    s_and_saveexec_b64 s[4:5], vcc
 ; GCN-IR-NEXT:    s_xor_b64 s[10:11], exec, s[4:5]
 ; GCN-IR-NEXT:    s_cbranch_execz BB1_5
 ; GCN-IR-NEXT:  ; %bb.2: ; %udiv-preheader

 ; GCN-IR-NEXT:    v_mov_b32_e32 v18, v11
 ; GCN-IR-NEXT:    s_andn2_b64 exec, exec, s[8:9]
 ; GCN-IR-NEXT:    s_cbranch_execnz BB1_3
 ; GCN-IR-NEXT:  ; %bb.4: ; %Flow
 ; GCN-IR-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; GCN-IR-NEXT:  BB1_5: ; %Flow3
 ; GCN-IR-NEXT:    s_or_b64 exec, exec, s[10:11]
 ; GCN-IR-NEXT:    v_lshl_b64 v[2:3], v[7:8], 1
-; GCN-IR-NEXT:    v_or_b32_e32 v12, v12, v3
+; GCN-IR-NEXT:    v_or_b32_e32 v7, v12, v3
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v11, v2
 ; GCN-IR-NEXT:  BB1_6: ; %Flow4
 ; GCN-IR-NEXT:    s_or_b64 exec, exec, s[6:7]
 ; GCN-IR-NEXT:    v_xor_b32_e32 v2, v5, v4
 ; GCN-IR-NEXT:    v_xor_b32_e32 v0, v0, v2
 ; GCN-IR-NEXT:    v_xor_b32_e32 v1, v1, v6
-; GCN-IR-NEXT:    v_xor_b32_e32 v3, v12, v1
+; GCN-IR-NEXT:    v_xor_b32_e32 v3, v7, v1
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, v0, v2
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v3, v1, vcc
 ; GCN-IR-NEXT:    s_setpc_b64 s[30:31]
   %result = sdiv i64 %x, %y
   ret i64 %result
 }
 
 define amdgpu_kernel void @s_test_sdiv24_64(i64 addrspace(1)* %out, i64 %x, i64 %y) {

 ; GCN-IR-NEXT:    s_branch BB9_7
 ; GCN-IR-NEXT:  BB9_5:
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v3, 0
 ; GCN-IR-NEXT:  BB9_6: ; %Flow3
 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
-; GCN-IR-NEXT:  BB9_7: ; %udiv-end
+; GCN-IR-NEXT:  BB9_7: ; %Flow4
 ; GCN-IR-NEXT:    s_xor_b64 s[0:1], s[6:7], s[2:3]
 ; GCN-IR-NEXT:    v_xor_b32_e32 v0, s0, v0
 ; GCN-IR-NEXT:    v_xor_b32_e32 v1, s1, v1
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s1
 ; GCN-IR-NEXT:    v_subrev_i32_e32 v0, vcc, s0, v0
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v1, v2, vcc
 ; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
 ; GCN-IR-NEXT:    s_mov_b32 s6, -1

 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
 ; GCN-IR-NEXT:  BB10_7: ; %udiv-end
 ; GCN-IR-NEXT:    v_xor_b32_e32 v0, s2, v0
 ; GCN-IR-NEXT:    v_xor_b32_e32 v1, s3, v1
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s3
 ; GCN-IR-NEXT:    v_subrev_i32_e32 v0, vcc, s2, v0
+; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v1, v2, vcc
 ; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
 ; GCN-IR-NEXT:    s_mov_b32 s6, -1
-; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v1, v2, vcc
 ; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %result = sdiv i64 24, %x
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 define i64 @v_test_sdiv_k_num_i64(i64 %x) {

llvm/test/CodeGen/AMDGPU/srem64.ll

 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
 ; GCN-IR-NEXT:  BB0_7: ; %udiv-end
 ; GCN-IR-NEXT:    v_mul_lo_u32 v1, s2, v1
 ; GCN-IR-NEXT:    v_mul_hi_u32 v2, s2, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v3, s3, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v0, s2, v0
-; GCN-IR-NEXT:    s_mov_b32 s11, 0xf000
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v2, v1
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v1, v3
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s7
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, s6, v0
-; GCN-IR-NEXT:    s_mov_b32 s10, -1
-; GCN-IR-NEXT:    s_mov_b32 s8, s4
-; GCN-IR-NEXT:    s_mov_b32 s9, s5
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v2, v1, vcc
-; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[8:11], 0
+; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-IR-NEXT:    s_mov_b32 s6, -1
+; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %result = urem i64 %x, %y
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 define i64 @v_test_srem(i64 %x, i64 %y) {
 ; GCN-LABEL: v_test_srem:

 ; GCN-IR-LABEL: s_test_srem33_64:
 ; GCN-IR:       ; %bb.0: ; %_udiv-special-cases
 ; GCN-IR-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
 ; GCN-IR-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0xd
 ; GCN-IR-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-IR-NEXT:    s_ashr_i32 s2, s7, 31
 ; GCN-IR-NEXT:    s_ashr_i64 s[10:11], s[0:1], 31
 ; GCN-IR-NEXT:    s_ashr_i32 s0, s1, 31
-; GCN-IR-NEXT:    s_mov_b32 s1, s0
 ; GCN-IR-NEXT:    s_ashr_i64 s[8:9], s[6:7], 31
 ; GCN-IR-NEXT:    s_mov_b32 s3, s2
+; GCN-IR-NEXT:    s_mov_b32 s1, s0
 ; GCN-IR-NEXT:    s_xor_b64 s[6:7], s[8:9], s[2:3]
-; GCN-IR-NEXT:    s_xor_b64 s[10:11], s[10:11], s[0:1]
-; GCN-IR-NEXT:    s_sub_u32 s8, s6, s2
-; GCN-IR-NEXT:    s_subb_u32 s9, s7, s2
-; GCN-IR-NEXT:    s_sub_u32 s10, s10, s0
-; GCN-IR-NEXT:    s_flbit_i32_b32 s12, s10
-; GCN-IR-NEXT:    s_subb_u32 s11, s11, s0
+; GCN-IR-NEXT:    s_xor_b64 s[8:9], s[10:11], s[0:1]
+; GCN-IR-NEXT:    s_sub_u32 s6, s6, s2
+; GCN-IR-NEXT:    s_subb_u32 s7, s7, s2
+; GCN-IR-NEXT:    s_sub_u32 s8, s8, s0
+; GCN-IR-NEXT:    s_flbit_i32_b32 s12, s8
+; GCN-IR-NEXT:    s_subb_u32 s9, s9, s0
 ; GCN-IR-NEXT:    s_add_i32 s12, s12, 32
-; GCN-IR-NEXT:    s_flbit_i32_b32 s13, s11
+; GCN-IR-NEXT:    s_flbit_i32_b32 s13, s9
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s12
-; GCN-IR-NEXT:    s_flbit_i32_b32 s12, s8
+; GCN-IR-NEXT:    s_flbit_i32_b32 s12, s6
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s13
-; GCN-IR-NEXT:    v_cmp_eq_u32_e64 vcc, s11, 0
+; GCN-IR-NEXT:    v_cmp_eq_u32_e64 vcc, s9, 0
 ; GCN-IR-NEXT:    s_add_i32 s12, s12, 32
-; GCN-IR-NEXT:    s_flbit_i32_b32 s13, s9
+; GCN-IR-NEXT:    s_flbit_i32_b32 s13, s7
 ; GCN-IR-NEXT:    v_cndmask_b32_e32 v2, v0, v1, vcc
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s13
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s12
-; GCN-IR-NEXT:    v_cmp_eq_u32_e64 vcc, s9, 0
+; GCN-IR-NEXT:    v_cmp_eq_u32_e64 vcc, s7, 0
 ; GCN-IR-NEXT:    v_cndmask_b32_e32 v3, v0, v1, vcc
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, v2, v3
 ; GCN-IR-NEXT:    v_subb_u32_e64 v1, s[12:13], 0, 0, vcc
-; GCN-IR-NEXT:    v_cmp_eq_u64_e64 s[0:1], s[10:11], 0
-; GCN-IR-NEXT:    v_cmp_eq_u64_e64 s[6:7], s[8:9], 0
+; GCN-IR-NEXT:    v_cmp_eq_u64_e64 s[0:1], s[8:9], 0
+; GCN-IR-NEXT:    v_cmp_eq_u64_e64 s[10:11], s[6:7], 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, 63, v[0:1]
-; GCN-IR-NEXT:    s_or_b64 s[0:1], s[0:1], s[6:7]
+; GCN-IR-NEXT:    s_or_b64 s[0:1], s[0:1], s[10:11]
 ; GCN-IR-NEXT:    s_or_b64 s[0:1], s[0:1], vcc
 ; GCN-IR-NEXT:    v_cmp_ne_u64_e32 vcc, 63, v[0:1]
-; GCN-IR-NEXT:    s_xor_b64 s[6:7], s[0:1], -1
-; GCN-IR-NEXT:    s_and_b64 s[6:7], s[6:7], vcc
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, s[6:7]
+; GCN-IR-NEXT:    s_xor_b64 s[10:11], s[0:1], -1
+; GCN-IR-NEXT:    s_and_b64 s[10:11], s[10:11], vcc
+; GCN-IR-NEXT:    s_and_b64 vcc, exec, s[10:11]
 ; GCN-IR-NEXT:    s_cbranch_vccz BB8_4
 ; GCN-IR-NEXT:  ; %bb.1: ; %udiv-bb1
 ; GCN-IR-NEXT:    v_add_i32_e32 v4, vcc, 1, v0
 ; GCN-IR-NEXT:    v_addc_u32_e32 v5, vcc, 0, v1, vcc
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e64 s[0:1], v[4:5], v[0:1]
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, 63, v0
-; GCN-IR-NEXT:    v_lshl_b64 v[0:1], s[8:9], v0
+; GCN-IR-NEXT:    v_lshl_b64 v[0:1], s[6:7], v0
 ; GCN-IR-NEXT:    s_andn2_b64 vcc, exec, s[0:1]
 ; GCN-IR-NEXT:    s_cbranch_vccz BB8_5
 ; GCN-IR-NEXT:  ; %bb.2: ; %udiv-preheader
 ; GCN-IR-NEXT:    v_not_b32_e32 v2, v2
-; GCN-IR-NEXT:    s_add_u32 s6, s10, -1
-; GCN-IR-NEXT:    v_lshr_b64 v[6:7], s[8:9], v4
+; GCN-IR-NEXT:    s_add_u32 s10, s8, -1
+; GCN-IR-NEXT:    v_lshr_b64 v[6:7], s[6:7], v4
 ; GCN-IR-NEXT:    v_add_i32_e32 v4, vcc, v2, v3
 ; GCN-IR-NEXT:    v_mov_b32_e32 v8, 0
-; GCN-IR-NEXT:    s_addc_u32 s7, s11, -1
+; GCN-IR-NEXT:    s_addc_u32 s11, s9, -1
 ; GCN-IR-NEXT:    v_addc_u32_e64 v5, s[0:1], -1, 0, vcc
 ; GCN-IR-NEXT:    v_mov_b32_e32 v9, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v3, 0
 ; GCN-IR-NEXT:  BB8_3: ; %udiv-do-while
 ; GCN-IR-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GCN-IR-NEXT:    v_lshl_b64 v[6:7], v[6:7], 1
 ; GCN-IR-NEXT:    v_lshrrev_b32_e32 v2, 31, v1
 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v6, v6, v2
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v8, v0
-; GCN-IR-NEXT:    v_mov_b32_e32 v2, s7
-; GCN-IR-NEXT:    v_sub_i32_e32 v8, vcc, s6, v6
+; GCN-IR-NEXT:    v_mov_b32_e32 v2, s11
+; GCN-IR-NEXT:    v_sub_i32_e32 v8, vcc, s10, v6
 ; GCN-IR-NEXT:    v_subb_u32_e32 v2, vcc, v2, v7, vcc
 ; GCN-IR-NEXT:    v_ashrrev_i32_e32 v8, 31, v2
-; GCN-IR-NEXT:    v_and_b32_e32 v10, s10, v8
+; GCN-IR-NEXT:    v_and_b32_e32 v10, s8, v8
 ; GCN-IR-NEXT:    v_and_b32_e32 v2, 1, v8
-; GCN-IR-NEXT:    v_and_b32_e32 v11, s11, v8
+; GCN-IR-NEXT:    v_and_b32_e32 v11, s9, v8
 ; GCN-IR-NEXT:    v_add_i32_e32 v8, vcc, 1, v4
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v9, v1
 ; GCN-IR-NEXT:    v_addc_u32_e32 v9, vcc, 0, v5, vcc
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, v[8:9], v[4:5]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v4, v8
 ; GCN-IR-NEXT:    v_sub_i32_e64 v6, s[0:1], v6, v10
 ; GCN-IR-NEXT:    v_mov_b32_e32 v5, v9
 ; GCN-IR-NEXT:    v_mov_b32_e32 v9, v3
 ; GCN-IR-NEXT:    v_subb_u32_e64 v7, s[0:1], v7, v11, s[0:1]
 ; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    v_mov_b32_e32 v8, v2
 ; GCN-IR-NEXT:    s_cbranch_vccz BB8_3
 ; GCN-IR-NEXT:    s_branch BB8_6
 ; GCN-IR-NEXT:  BB8_4:
-; GCN-IR-NEXT:    v_mov_b32_e32 v0, s9
+; GCN-IR-NEXT:    v_mov_b32_e32 v0, s7
 ; GCN-IR-NEXT:    v_cndmask_b32_e64 v1, v0, 0, s[0:1]
-; GCN-IR-NEXT:    v_mov_b32_e32 v0, s8
+; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    v_cndmask_b32_e64 v0, v0, 0, s[0:1]
 ; GCN-IR-NEXT:    s_branch BB8_7
 ; GCN-IR-NEXT:  BB8_5:
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v3, 0
 ; GCN-IR-NEXT:  BB8_6: ; %Flow6
 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
 ; GCN-IR-NEXT:  BB8_7: ; %udiv-end
-; GCN-IR-NEXT:    v_mul_lo_u32 v1, s10, v1
-; GCN-IR-NEXT:    v_mul_hi_u32 v2, s10, v0
-; GCN-IR-NEXT:    v_mul_lo_u32 v3, s11, v0
-; GCN-IR-NEXT:    v_mul_lo_u32 v0, s10, v0
-; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-IR-NEXT:    v_mul_lo_u32 v1, s8, v1
+; GCN-IR-NEXT:    v_mul_hi_u32 v2, s8, v0
+; GCN-IR-NEXT:    v_mul_lo_u32 v3, s9, v0
+; GCN-IR-NEXT:    v_mul_lo_u32 v0, s8, v0
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v2, v1
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v1, v3
-; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, s8, v0
-; GCN-IR-NEXT:    v_mov_b32_e32 v2, s9
+; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, s6, v0
+; GCN-IR-NEXT:    v_mov_b32_e32 v2, s7
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v2, v1, vcc
 ; GCN-IR-NEXT:    v_xor_b32_e32 v0, s2, v0
 ; GCN-IR-NEXT:    v_xor_b32_e32 v1, s3, v1
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s3
 ; GCN-IR-NEXT:    v_subrev_i32_e32 v0, vcc, s2, v0
-; GCN-IR-NEXT:    s_mov_b32 s6, -1
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v1, v2, vcc
+; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-IR-NEXT:    s_mov_b32 s6, -1
 ; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %1 = ashr i64 %x, 31
   %2 = ashr i64 %y, 31
   %result = srem i64 %1, %2
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }

 ; GCN-IR-NEXT:    v_mul_lo_u32 v1, s2, v1
 ; GCN-IR-NEXT:    v_mul_hi_u32 v2, s2, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v3, s3, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v0, s2, v0
 ; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v2, v1
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v1, v3
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, 24, v0
-; GCN-IR-NEXT:    s_mov_b32 s6, -1
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, 0, v1, vcc
+; GCN-IR-NEXT:    s_mov_b32 s6, -1
 ; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
-  %result = srem i64 24, %x
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 define i64 @v_test_srem_k_num_i64(i64 %x) {
 ; GCN-LABEL: v_test_srem_k_num_i64:
 ; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)

llvm/test/CodeGen/AMDGPU/urem64.ll

 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
 ; GCN-IR-NEXT:  BB0_7: ; %udiv-end
 ; GCN-IR-NEXT:    v_mul_lo_u32 v1, s2, v1
 ; GCN-IR-NEXT:    v_mul_hi_u32 v2, s2, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v3, s3, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v0, s2, v0
-; GCN-IR-NEXT:    s_mov_b32 s11, 0xf000
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v2, v1
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v1, v3
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s7
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, s6, v0
-; GCN-IR-NEXT:    s_mov_b32 s10, -1
-; GCN-IR-NEXT:    s_mov_b32 s8, s4
-; GCN-IR-NEXT:    s_mov_b32 s9, s5
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v2, v1, vcc
-; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[8:11], 0
+; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-IR-NEXT:    s_mov_b32 s6, -1
+; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %result = urem i64 %x, %y
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 define i64 @v_test_urem_i64(i64 %x, i64 %y) {
 ; GCN-LABEL: v_test_urem_i64:

 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
 ; GCN-IR-NEXT:  BB6_7: ; %udiv-end
 ; GCN-IR-NEXT:    v_mul_lo_u32 v1, s6, v1
 ; GCN-IR-NEXT:    v_mul_hi_u32 v2, s6, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v3, s7, v0
 ; GCN-IR-NEXT:    v_mul_lo_u32 v0, s6, v0
-; GCN-IR-NEXT:    s_mov_b32 s3, 0xf000
+; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v2, v1
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v1, v3
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, 24, v0
-; GCN-IR-NEXT:    s_mov_b32 s2, -1
-; GCN-IR-NEXT:    s_mov_b32 s0, s4
-; GCN-IR-NEXT:    s_mov_b32 s1, s5
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, 0, v1, vcc
-; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[0:3], 0
+; GCN-IR-NEXT:    s_mov_b32 s6, -1
+; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %result = urem i64 24, %x
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 define amdgpu_kernel void @s_test_urem_k_den_i64(i64 addrspace(1)* %out, i64 %x) {
 ; GCN-LABEL: s_test_urem_k_den_i64:

 ; GCN-IR-NEXT:  BB7_6: ; %Flow5
 ; GCN-IR-NEXT:    v_lshl_b64 v[0:1], v[0:1], 1
 ; GCN-IR-NEXT:    v_or_b32_e32 v0, v2, v0
 ; GCN-IR-NEXT:    v_or_b32_e32 v1, v3, v1
 ; GCN-IR-NEXT:  BB7_7: ; %udiv-end
 ; GCN-IR-NEXT:    v_mul_hi_u32 v2, v0, 24
 ; GCN-IR-NEXT:    v_mul_lo_u32 v1, v1, 24
 ; GCN-IR-NEXT:    v_mul_lo_u32 v0, v0, 24
-; GCN-IR-NEXT:    s_mov_b32 s3, 0xf000
-; GCN-IR-NEXT:    s_mov_b32 s2, -1
 ; GCN-IR-NEXT:    v_add_i32_e32 v1, vcc, v2, v1
 ; GCN-IR-NEXT:    v_mov_b32_e32 v2, s7
 ; GCN-IR-NEXT:    v_sub_i32_e32 v0, vcc, s6, v0
-; GCN-IR-NEXT:    s_mov_b32 s0, s4
-; GCN-IR-NEXT:    s_mov_b32 s1, s5
 ; GCN-IR-NEXT:    v_subb_u32_e32 v1, vcc, v2, v1, vcc
-; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[0:3], 0
+; GCN-IR-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-IR-NEXT:    s_mov_b32 s6, -1
+; GCN-IR-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
 ; GCN-IR-NEXT:    s_endpgm
   %result = urem i64 %x, 24
   store i64 %result, i64 addrspace(1)* %out
   ret void
 }
 
 ; FIXME: Constant bus violation
 ; define i64 @v_test_urem_k_num_i64(i64 %x) {