[llvm] [CVP][LVI] Add support for InsertElementInst in LVI (PR #99368)

[Nikita Popov via llvm-commits]

================
@@ -0,0 +1,76 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=correlated-propagation -S | FileCheck %s
+
+;; Check if ICMP instruction is constant folded or not.
+
+define void @test1(ptr addrspace(1) %out) {
+; CHECK-LABEL: define void @test1(
+; CHECK-SAME: ptr addrspace(1) [[OUT:%.*]]) {
+; CHECK-NEXT:    [[CALL:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x(), !range [[RNG0:![0-9]+]]
+; CHECK-NEXT:    [[UDIV_LHS_TRUNC:%.*]] = trunc i32 [[CALL]] to i16
+; CHECK-NEXT:    [[UDIV1:%.*]] = udiv i16 [[UDIV_LHS_TRUNC]], 5
+; CHECK-NEXT:    [[UDIV_ZEXT:%.*]] = zext i16 [[UDIV1]] to i32
+; CHECK-NEXT:    [[ADD1:%.*]] = add nuw nsw i32 [[UDIV_ZEXT]], 768
+; CHECK-NEXT:    [[ADD2:%.*]] = add nuw nsw i32 [[UDIV_ZEXT]], 896
+; CHECK-NEXT:    [[IE1:%.*]] = insertelement <2 x i32> poison, i32 [[ADD1]], i64 0
+; CHECK-NEXT:    [[IE2:%.*]] = insertelement <2 x i32> [[IE1]], i32 [[ADD2]], i64 1
+; CHECK-NEXT:    [[EI1:%.*]] = extractelement <2 x i1> <i1 true, i1 true>, i64 0
+; CHECK-NEXT:    [[EI2:%.*]] = extractelement <2 x i1> <i1 true, i1 true>, i64 1
+; CHECK-NEXT:    [[ADDUP:%.*]] = add i1 [[EI1]], [[EI2]]
+; CHECK-NEXT:    [[ADDUP_UPCAST:%.*]] = zext i1 [[ADDUP]] to i32
+; CHECK-NEXT:    store i32 [[ADDUP_UPCAST]], ptr addrspace(1) [[OUT]], align 4
+; CHECK-NEXT:    ret void
+;
+  %call = call i32 @llvm.nvvm.read.ptx.sreg.tid.x(), !range !1
+  %udiv = udiv i32 %call, 5
+  %add1 = add i32 %udiv, 768
+  %add2 = add i32 %udiv, 896
+  %ie1 = insertelement <2 x i32> poison, i32 %add1, i64 0
+  %ie2 = insertelement <2 x i32> %ie1, i32 %add2, i64 1
+  %icmp1 = icmp slt <2 x i32> %ie2, <i32 1024, i32 1024>
+  %ei1 = extractelement <2 x i1> %icmp1, i64 0
+  %ei2 = extractelement <2 x i1> %icmp1, i64 1
+  %addUp = add i1 %ei1, %ei2
+  %addUp.upcast = zext i1 %addUp to i32
+  store i32 %addUp.upcast, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+
+;; Check if LVI is able to handle constant vector operands
+;; in InsertElementInst and CVP is able to fold ICMP instruction.
+
+define void @test2(ptr addrspace(1) %out) {
+; CHECK-LABEL: define void @test2(
+; CHECK-SAME: ptr addrspace(1) [[OUT:%.*]]) {
+; CHECK-NEXT:    [[CALL:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x(), !range [[RNG0]]
+; CHECK-NEXT:    [[UDIV_LHS_TRUNC:%.*]] = trunc i32 [[CALL]] to i16
+; CHECK-NEXT:    [[UDIV1:%.*]] = udiv i16 [[UDIV_LHS_TRUNC]], 5
+; CHECK-NEXT:    [[UDIV_ZEXT:%.*]] = zext i16 [[UDIV1]] to i32
+; CHECK-NEXT:    [[ADD2:%.*]] = add nuw nsw i32 [[UDIV_ZEXT]], 896
+; CHECK-NEXT:    [[IE1:%.*]] = insertelement <2 x i32> <i32 poison, i32 1>, i32 [[ADD2]], i64 0
+; CHECK-NEXT:    [[EI1:%.*]] = extractelement <2 x i1> <i1 true, i1 true>, i64 0
+; CHECK-NEXT:    [[EI2:%.*]] = extractelement <2 x i1> <i1 true, i1 true>, i64 1
+; CHECK-NEXT:    [[ADDUP:%.*]] = add i1 [[EI1]], [[EI2]]
+; CHECK-NEXT:    [[ADDUP_UPCAST:%.*]] = zext i1 [[ADDUP]] to i32
+; CHECK-NEXT:    store i32 [[ADDUP_UPCAST]], ptr addrspace(1) [[OUT]], align 4
+; CHECK-NEXT:    ret void
+;
+  %call = call i32 @llvm.nvvm.read.ptx.sreg.tid.x(), !range !1
+  %udiv = udiv i32 %call, 5
+  %add2 = add i32 %udiv, 896
+  %ie1 = insertelement <2 x i32> <i32 poison, i32 1>, i32 %add2, i64 0
+  %icmp1 = icmp slt <2 x i32> %ie1, <i32 1024, i32 1024>
+  %ei1 = extractelement <2 x i1> %icmp1, i64 0
+  %ei2 = extractelement <2 x i1> %icmp1, i64 1
+  %addUp = add i1 %ei1, %ei2
+  %addUp.upcast = zext i1 %addUp to i32
+  store i32 %addUp.upcast, ptr addrspace(1) %out, align 4
+  ret void
+}
----------------
nikic wrote:

Please make these tests more minimal and add them to vectors.ll.

https://github.com/llvm/llvm-project/pull/99368