[llvm] [InstCombine] Fold @llvm.experimental.get.vector.length when cnt <= max_lanes (PR #169293)

[Luke Lau via llvm-commits]

================
@@ -0,0 +1,80 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt < %s -passes=instcombine,verify -S | FileCheck %s
+
+define i32 @cnt_known_lt() {
+; CHECK-LABEL: define i32 @cnt_known_lt() {
+; CHECK-NEXT:    ret i32 1
+;
+  %x = call i32 @llvm.experimental.get.vector.length(i32 1, i32 2, i1 false)
+  ret i32 %x
+}
+
+define i32 @cnt_not_known_lt() {
+; CHECK-LABEL: define i32 @cnt_not_known_lt() {
+; CHECK-NEXT:    [[X:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 2, i32 1, i1 false)
+; CHECK-NEXT:    ret i32 [[X]]
+;
+  %x = call i32 @llvm.experimental.get.vector.length(i32 2, i32 1, i1 false)
+  ret i32 %x
+}
+
+define i32 @cnt_known_lt_scalable() vscale_range(2, 4) {
+; CHECK-LABEL: define i32 @cnt_known_lt_scalable(
+; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:    ret i32 2
+;
+  %x = call i32 @llvm.experimental.get.vector.length(i32 2, i32 1, i1 true)
+  ret i32 %x
+}
+
+define i32 @cnt_not_known_lt_scalable() {
+; CHECK-LABEL: define i32 @cnt_not_known_lt_scalable() {
+; CHECK-NEXT:    [[X:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 2, i32 1, i1 true)
+; CHECK-NEXT:    ret i32 [[X]]
+;
+  %x = call i32 @llvm.experimental.get.vector.length(i32 2, i32 1, i1 true)
+  ret i32 %x
+}
+
+define i32 @cnt_known_lt_runtime(i32 %x) {
+; CHECK-LABEL: define i32 @cnt_known_lt_runtime(
+; CHECK-SAME: i32 [[X:%.*]]) {
+; CHECK-NEXT:    [[ICMP:%.*]] = icmp ult i32 [[X]], 4
+; CHECK-NEXT:    call void @llvm.assume(i1 [[ICMP]])
+; CHECK-NEXT:    ret i32 [[X]]
+;
+  %icmp = icmp ule i32 %x, 3
+  call void @llvm.assume(i1 %icmp)
+  %y = call i32 @llvm.experimental.get.vector.length(i32 %x, i32 3, i1 false)
+  ret i32 %y
+}
+
+define i32 @cnt_known_lt_runtime_trunc(i64 %x) {
+; CHECK-LABEL: define i32 @cnt_known_lt_runtime_trunc(
+; CHECK-SAME: i64 [[X:%.*]]) {
+; CHECK-NEXT:    [[ICMP:%.*]] = icmp ult i64 [[X]], 4
+; CHECK-NEXT:    call void @llvm.assume(i1 [[ICMP]])
+; CHECK-NEXT:    [[Y:%.*]] = trunc nuw nsw i64 [[X]] to i32
+; CHECK-NEXT:    ret i32 [[Y]]
+;
+  %icmp = icmp ule i64 %x, 3
+  call void @llvm.assume(i1 %icmp)
+  %y = call i32 @llvm.experimental.get.vector.length(i64 %x, i32 3, i1 false)
+  ret i32 %y
+}
+
+; FIXME: We should be able to deduce the constant range from AssumptionCache
----------------
lukel97 wrote:

Btw the reason for using `computeConstantRangeIncludingKnownBits` and not just `computeConstantRange` directly is because for the motivating case I think we need to be able handle a simple PHI recurrence, which only `computeKnownBits` seems to be able to handle at the moment. 

https://github.com/llvm/llvm-project/pull/169293