[LoongArch] Precommit a test for smul with overflow (NFC)

llvm/test/CodeGen/LoongArch/smul-with-overflow.ll

@@ -0,0 +1,118 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch32 < %s | FileCheck %s --check-prefix=LA32
+; RUN: llc --mtriple=loongarch64 < %s | FileCheck %s --check-prefix=LA64
+
+define zeroext i1 @smuloi64(i64 %v1, i64 %v2, ptr %res) {
+; LA32-LABEL: smuloi64:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -16
+; LA32-NEXT:    .cfi_def_cfa_offset 16
+; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 8 # 4-byte Folded Spill
+; LA32-NEXT:    .cfi_offset 1, -4
+; LA32-NEXT:    .cfi_offset 22, -8
+; LA32-NEXT:    move $fp, $a4
+; LA32-NEXT:    st.w $zero, $sp, 4
+; LA32-NEXT:    addi.w $a4, $sp, 4
+; LA32-NEXT:    bl %plt(__mulodi4)
+; LA32-NEXT:    st.w $a1, $fp, 4
+; LA32-NEXT:    st.w $a0, $fp, 0
+; LA32-NEXT:    ld.w $a0, $sp, 4
+; LA32-NEXT:    sltu $a0, $zero, $a0
+; LA32-NEXT:    ld.w $fp, $sp, 8 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 16
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: smuloi64:
+; LA64:       # %bb.0:
+; LA64-NEXT:    mul.d $a3, $a0, $a1
+; LA64-NEXT:    st.d $a3, $a2, 0
+; LA64-NEXT:    mulh.d $a0, $a0, $a1
+; LA64-NEXT:    srai.d $a1, $a3, 63
+; LA64-NEXT:    xor $a0, $a0, $a1
+; LA64-NEXT:    sltu $a0, $zero, $a0
+; LA64-NEXT:    ret
+  %t = call {i64, i1} @llvm.smul.with.overflow.i64(i64 %v1, i64 %v2)
+  %val = extractvalue {i64, i1} %t, 0
+  %obit = extractvalue {i64, i1} %t, 1
+  store i64 %val, ptr %res
+  ret i1 %obit
+}
+
+define zeroext i1 @smuloi128(i128 %v1, i128 %v2, ptr %res) {
+; LA32-LABEL: smuloi128:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -64
+; LA32-NEXT:    .cfi_def_cfa_offset 64
+; LA32-NEXT:    st.w $ra, $sp, 60 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 56 # 4-byte Folded Spill
+; LA32-NEXT:    .cfi_offset 1, -4
+; LA32-NEXT:    .cfi_offset 22, -8
+; LA32-NEXT:    move $fp, $a2
+; LA32-NEXT:    st.w $zero, $sp, 52
+; LA32-NEXT:    ld.w $a2, $a1, 12
+; LA32-NEXT:    st.w $a2, $sp, 12
+; LA32-NEXT:    ld.w $a2, $a1, 8
+; LA32-NEXT:    st.w $a2, $sp, 8
+; LA32-NEXT:    ld.w $a2, $a1, 4
+; LA32-NEXT:    st.w $a2, $sp, 4
+; LA32-NEXT:    ld.w $a1, $a1, 0
+; LA32-NEXT:    st.w $a1, $sp, 0
+; LA32-NEXT:    ld.w $a1, $a0, 12
+; LA32-NEXT:    st.w $a1, $sp, 28
+; LA32-NEXT:    ld.w $a1, $a0, 8
+; LA32-NEXT:    st.w $a1, $sp, 24
+; LA32-NEXT:    ld.w $a1, $a0, 4
+; LA32-NEXT:    st.w $a1, $sp, 20
+; LA32-NEXT:    ld.w $a0, $a0, 0
+; LA32-NEXT:    st.w $a0, $sp, 16
+; LA32-NEXT:    addi.w $a0, $sp, 32
+; LA32-NEXT:    addi.w $a1, $sp, 16
+; LA32-NEXT:    addi.w $a2, $sp, 0
+; LA32-NEXT:    addi.w $a3, $sp, 52
+; LA32-NEXT:    bl %plt(__muloti4)
+; LA32-NEXT:    ld.w $a0, $sp, 44
+; LA32-NEXT:    st.w $a0, $fp, 12
+; LA32-NEXT:    ld.w $a0, $sp, 40
+; LA32-NEXT:    st.w $a0, $fp, 8
+; LA32-NEXT:    ld.w $a0, $sp, 36
+; LA32-NEXT:    st.w $a0, $fp, 4
+; LA32-NEXT:    ld.w $a0, $sp, 32
+; LA32-NEXT:    st.w $a0, $fp, 0
+; LA32-NEXT:    ld.w $a0, $sp, 52
+; LA32-NEXT:    sltu $a0, $zero, $a0
+; LA32-NEXT:    ld.w $fp, $sp, 56 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 60 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 64
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: smuloi128:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -32
+; LA64-NEXT:    .cfi_def_cfa_offset 32
+; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 16 # 8-byte Folded Spill
+; LA64-NEXT:    .cfi_offset 1, -8
+; LA64-NEXT:    .cfi_offset 22, -16
+; LA64-NEXT:    move $fp, $a4
+; LA64-NEXT:    st.d $zero, $sp, 8
+; LA64-NEXT:    addi.d $a4, $sp, 8
+; LA64-NEXT:    bl %plt(__muloti4)
+; LA64-NEXT:    st.d $a1, $fp, 8
+; LA64-NEXT:    st.d $a0, $fp, 0
+; LA64-NEXT:    ld.d $a0, $sp, 8
+; LA64-NEXT:    sltu $a0, $zero, $a0
+; LA64-NEXT:    ld.d $fp, $sp, 16 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 24 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 32
+; LA64-NEXT:    ret
+  %t = call {i128, i1} @llvm.smul.with.overflow.i128(i128 %v1, i128 %v2)
+  %val = extractvalue {i128, i1} %t, 0
+  %obit = extractvalue {i128, i1} %t, 1
+  store i128 %val, ptr %res
+  ret i1 %obit
+}
+
+declare {i64, i1} @llvm.smul.with.overflow.i64(i64, i64) nounwind readnone
+declare {i128, i1} @llvm.smul.with.overflow.i128(i128, i128) nounwind readnone