shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopUnroll/convergent.controlled.ll
Joel E. Denny 6d44b9082e
[LoopUnroll] Skip remainder loop guard if skip unrolled loop (#156549) 
The original loop (OL) that serves as input to LoopUnroll has basic
blocks that are arranged as follows:

```
OLPreHeader
OLHeader <-.
...        |
OLLatch ---'
OLExit
```

In this depiction, every block has an implicit edge to the next block
below, so any explicit edge indicates a conditional branch.

Given OL and unroll count N, LoopUnroll sometimes creates an unrolled
loop (UL) with a remainder loop (RL) epilogue arranged like this:

```
,-- ULGuard
|   ULPreHeader
|   ULHeader <-.
|   ...        |
|   ULLatch ---'
|   ULExit
`-> RLGuard -----.
    RLPreHeader  |
,-> RLHeader     |
|   ...          |
`-- RLLatch      |
    RLExit       |
    OLExit <-----'
```

Each UL iteration executes N OL iterations, but each RL iteration
executes 1 OL iteration. ULGuard or RLGuard checks whether the first
iteration of UL or RL should execute, respectively. If so, ULLatch or
RLLatch checks whether to execute each subsequent iteration.

Once reached, OL always executes its first iteration but not necessarily
the next N-1 iterations. Thus, ULGuard is always required before the
first UL iteration. However, when control flows from ULGuard directly to
RLGuard, the first OL iteration has yet to execute, so RLGuard is then
redundant before the first RL iteration.

Thus, this patch makes the following changes:
- Adjust ULGuard to branch to RLPreHeader instead of RLGuard, thus
eliminating RLGuard's unnecessary branch instruction for that path.
- Eliminate the creation of RLGuard phi node poison values. Without this
patch, RLGuard has such a phi node for each value that is defined by any
OL iteration and used in OLExit. The poison value is required where
ULGuard is the predecessor. The poison value indicates that control flow
from ULGuard to RLGuard to Exit has no counterpart in OL because the
first OL iteration must execute either in UL or RL.
- Simplify the CFG by not splitting ULExit and RLGuard because, without
the ULGuard predecessor, the single block can now be a dedicated UL
exit.
- To RLPreHeader, add an `llvm.assume` call that asserts the RL trip
count is non-zero. Without this patch, RLPreHeader is reachable only
when RLGuard guarantees that assertion is true. With this patch, RLGuard
guarantees it only when RLGuard is the predecessor, and the OL structure
guarantees it when ULGuard is the predecessor. If RL itself is unrolled
later, this guarantee somehow prevents ScalarEvolution from giving up
when trying to compute a maximum trip count for RL. That maximum trip
count enables the branch instruction in the final unrolled instance of
RLLatch to be eliminated. Without the `llvm.assume` call, some existing
unroll tests start to fail because that instruction is not eliminated.

The original motivation for this patch is to facilitate later patches
that fix LoopUnroll's computation of branch weights so that they
maintain the block frequency of OL's body (see #135812). Specifically,
this patch ensures RLGuard's branch weights do not affect RL's
contribution to the block frequency of OL's body in the case that
ULGuard skips UL.
2025-10-07 10:45:49 -04:00

563 lines
23 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-unroll -unroll-runtime -unroll-allow-partial -S | FileCheck %s
declare void @f() convergent
declare void @g()
; Although this loop contains a convergent instruction, it should be
; fully unrolled.
define i32 @full_unroll() {
; CHECK-LABEL: @full_unroll(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: br label [[L3:%.*]]
; CHECK: l3:
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: br label [[A:%.*]]
; CHECK: a:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_1:%.*]]
; CHECK: a.1:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_2:%.*]]
; CHECK: a.2:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: ret i32 0
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
br label %l3
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %a ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, 3
br label %a
a:
call void @f() [ "convergencectrl"(token %tok.loop) ]
br i1 %exitcond, label %exit, label %l3
exit:
ret i32 0
}
; This loop contains a convergent instruction, but it should be partially
; unrolled. The unroll count is the largest power of 2 that divides the
; multiple -- 4, in this case.
define i32 @runtime_unroll(i32 %n) {
; CHECK-LABEL: @runtime_unroll(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: [[LOOP_CTL:%.*]] = mul nsw i32 [[N:%.*]], 12
; CHECK-NEXT: br label [[L3:%.*]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC_3:%.*]], [[A_3:%.*]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: br label [[A:%.*]]
; CHECK: a:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_1:%.*]]
; CHECK: a.1:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_2:%.*]]
; CHECK: a.2:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_3]]
; CHECK: a.3:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: [[INC_3]] = add nsw i32 [[X_0]], 4
; CHECK-NEXT: [[EXITCOND_3:%.*]] = icmp eq i32 [[INC_3]], [[LOOP_CTL]]
; CHECK-NEXT: br i1 [[EXITCOND_3]], label [[EXIT:%.*]], label [[L3]]
; CHECK: exit:
; CHECK-NEXT: ret i32 0
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
%loop_ctl = mul nsw i32 %n, 12
br label %l3
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %a ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
br label %a
a:
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, %loop_ctl
br i1 %exitcond, label %exit, label %l3
exit:
ret i32 0
}
; This loop contains a convergent instruction, so its partial unroll
; count must divide its trip multiple. This overrides its unroll
; pragma -- we unroll exactly 8 times, even though 16 is requested.
define i32 @pragma_unroll(i32 %n) {
; CHECK-LABEL: @pragma_unroll(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: [[LOOP_CTL:%.*]] = mul nsw i32 [[N:%.*]], 24
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC_7:%.*]], [[A_7:%.*]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: br label [[A:%.*]]
; CHECK: a:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_1:%.*]]
; CHECK: a.1:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_2:%.*]]
; CHECK: a.2:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_3:%.*]]
; CHECK: a.3:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_4:%.*]]
; CHECK: a.4:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_5:%.*]]
; CHECK: a.5:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_6:%.*]]
; CHECK: a.6:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: br label [[A_7]]
; CHECK: a.7:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: [[INC_7]] = add nsw i32 [[X_0]], 8
; CHECK-NEXT: [[EXITCOND_7:%.*]] = icmp eq i32 [[INC_7]], [[LOOP_CTL]]
; CHECK-NEXT: br i1 [[EXITCOND_7]], label [[EXIT:%.*]], label [[L3]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret i32 0
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
%loop_ctl = mul nsw i32 %n, 24
br label %l3, !llvm.loop !0
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %a ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
br label %a
a:
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, %loop_ctl
br i1 %exitcond, label %exit, label %l3, !llvm.loop !0
exit:
ret i32 0
}
; This loop contains a convergent instruction. Since the pragma loop unroll
; count 2 divides trip count 4. The loop unroll should respect the pragma.
define void @pragma_unroll_divisible_trip_count() {
; CHECK-LABEL: @pragma_unroll_divisible_trip_count(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC_1:%.*]], [[L3]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: [[INC_1]] = add nuw nsw i32 [[X_0]], 2
; CHECK-NEXT: [[EXITCOND_1:%.*]] = icmp eq i32 [[INC_1]], 4
; CHECK-NEXT: br i1 [[EXITCOND_1]], label [[EXIT:%.*]], label [[L3]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
br label %l3, !llvm.loop !1
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %l3 ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, 4
br i1 %exitcond, label %exit, label %l3, !llvm.loop !1
exit:
ret void
}
; This loop contains a convergent instruction. Since the pragma loop unroll
; count 2 divides trip multiple 2. The loop unroll should respect the pragma.
define i32 @pragma_unroll_divisible_trip_multiple(i32 %n) {
; CHECK-LABEL: @pragma_unroll_divisible_trip_multiple(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: [[LOOP_CTL:%.*]] = mul nsw i32 [[N:%.*]], 2
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC_1:%.*]], [[L3]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: [[INC_1]] = add nsw i32 [[X_0]], 2
; CHECK-NEXT: [[EXITCOND_1:%.*]] = icmp eq i32 [[INC_1]], [[LOOP_CTL]]
; CHECK-NEXT: br i1 [[EXITCOND_1]], label [[EXIT:%.*]], label [[L3]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret i32 0
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
%loop_ctl = mul nsw i32 %n, 2
br label %l3, !llvm.loop !1
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %l3 ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, %loop_ctl
br i1 %exitcond, label %exit, label %l3, !llvm.loop !1
exit:
ret i32 0
}
; This loop contains a convergent instruction. Since the pragma loop unroll
; count 2 is unknown to divide runtime trip count, the loop is not unrolled
; since remainder is forbidden for unrolling convergent loop.
define i32 @pragma_unroll_indivisible_runtime_trip_count(i32 %n) {
; CHECK-LABEL: @pragma_unroll_indivisible_runtime_trip_count(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[L3]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: [[INC]] = add nsw i32 [[X_0]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N:%.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[L3]], !llvm.loop [[LOOP4]]
; CHECK: exit:
; CHECK-NEXT: ret i32 0
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
br label %l3, !llvm.loop !1
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %l3 ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %exit, label %l3, !llvm.loop !1
exit:
ret i32 0
}
; This loop contains a convergent instruction. Since the pragma loop unroll
; count 2 does not divide trip count 5, the loop is not unrolled by 2
; since remainder is forbidden for unrolling convergent loop. Instead, the
; loop gets fully unrolled.
define i32 @pragma_unroll_indivisible_trip_count() {
; CHECK-LABEL: @pragma_unroll_indivisible_trip_count(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ANCHOR:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l3:
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[ANCHOR]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: ret i32 0
;
entry:
%anchor = call token @llvm.experimental.convergence.anchor()
br label %l3, !llvm.loop !1
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %l3 ]
%tok.loop = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token %anchor) ]
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, 5
br i1 %exitcond, label %exit, label %l3, !llvm.loop !1
exit:
ret i32 0
}
; This loop contains a convergent instruction that is anchored inside the loop
; itself. It is unrolled by 2 with remainder, as requested by the loop metadata.
define i32 @pragma_unroll_with_remainder(i32 %n) {
; CHECK-LABEL: @pragma_unroll_with_remainder(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[N:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[TMP0]], -1
; CHECK-NEXT: [[XTRAITER:%.*]] = and i32 [[TMP0]], 1
; CHECK-NEXT: [[TMP2:%.*]] = icmp ult i32 [[TMP1]], 1
; CHECK-NEXT: br i1 [[TMP2]], label [[L3_EPIL_PREHEADER:%.*]], label [[ENTRY_NEW:%.*]]
; CHECK: entry.new:
; CHECK-NEXT: [[UNROLL_ITER:%.*]] = sub i32 [[TMP0]], [[XTRAITER]]
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY_NEW]] ], [ [[INC_1:%.*]], [[L3]] ]
; CHECK-NEXT: [[NITER:%.*]] = phi i32 [ 0, [[ENTRY_NEW]] ], [ [[NITER_NEXT_1:%.*]], [[L3]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: [[TOK_LOOP_1:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP_1]]) ]
; CHECK-NEXT: [[INC_1]] = add nsw i32 [[X_0]], 2
; CHECK-NEXT: [[NITER_NEXT_1]] = add i32 [[NITER]], 2
; CHECK-NEXT: [[NITER_NCMP_1:%.*]] = icmp eq i32 [[NITER_NEXT_1]], [[UNROLL_ITER]]
; CHECK-NEXT: br i1 [[NITER_NCMP_1]], label [[EXIT_UNR_LCSSA:%.*]], label [[L3]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: exit.unr-lcssa:
; CHECK-NEXT: [[LCMP_MOD:%.*]] = icmp ne i32 [[XTRAITER]], 0
; CHECK-NEXT: br i1 [[LCMP_MOD]], label [[L3_EPIL_PREHEADER]], label [[EXIT:%.*]]
; CHECK: l3.epil.preheader:
; CHECK-NEXT: [[LCMP_MOD1:%.*]] = icmp ne i32 [[XTRAITER]], 0
; CHECK-NEXT: call void @llvm.assume(i1 [[LCMP_MOD1]])
; CHECK-NEXT: br label [[L3_EPIL:%.*]]
; CHECK: l3.epil:
; CHECK-NEXT: [[TOK_LOOP_EPIL:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP_EPIL]]) ]
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret i32 0
;
entry:
br label %l3, !llvm.loop !1
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %l3 ]
%tok.loop = call token @llvm.experimental.convergence.anchor()
call void @f() [ "convergencectrl"(token %tok.loop) ]
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %exit, label %l3, !llvm.loop !1
exit:
ret i32 0
}
; Don't unroll a loop that is extended by convergence controls.
;
; We could theoretically duplicate the extension part, but this is not
; implemented.
define i32 @extended_loop(i32 %n) {
; CHECK-LABEL: @extended_loop(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[L3]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: [[INC]] = add nsw i32 [[X_0]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N:%.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[L3]], !llvm.loop [[LOOP4]]
; CHECK: exit:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_LOOP]]) ]
; CHECK-NEXT: ret i32 0
;
entry:
br label %l3, !llvm.loop !1
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %l3 ]
%tok.loop = call token @llvm.experimental.convergence.anchor()
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %exit, label %l3, !llvm.loop !1
exit:
call void @f() [ "convergencectrl"(token %tok.loop) ]
ret i32 0
}
; Inner loop is extended beyond the outer loop. No unrolling possible.
define i32 @extended_inner_loop_1(i32 %n, i1 %cond) {
; CHECK-LABEL: @extended_inner_loop_1(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L3:%.*]]
; CHECK: l3:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT: [[TOK_LOOP:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: [[INC]] = add nsw i32 [[X_0]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 4
; CHECK-NEXT: br label [[L2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2:
; CHECK-NEXT: [[TOK_L2:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2]]) ]
; CHECK-NEXT: br i1 [[COND:%.*]], label [[L2]], label [[LATCH]], !llvm.loop [[LOOP4]]
; CHECK: latch:
; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[L3]]
; CHECK: exit:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2]]) ]
; CHECK-NEXT: ret i32 0
;
entry:
br label %l3
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %latch ]
%tok.loop = call token @llvm.experimental.convergence.anchor()
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, 4
br label %l2, !llvm.loop !1
l2:
%tok.l2 = call token @llvm.experimental.convergence.anchor()
call void @f() [ "convergencectrl"(token %tok.l2) ]
br i1 %cond, label %l2, label %latch, !llvm.loop !1
latch:
br i1 %exitcond, label %exit, label %l3
exit:
call void @f() [ "convergencectrl"(token %tok.l2) ]
ret i32 0
}
; Inner loop is extended inside the outer loop. Outer loop is unrolled.
define i32 @extended_inner_loop_2(i32 %n, i1 %cond) {
; CHECK-LABEL: @extended_inner_loop_2(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L3:%.*]]
; CHECK: l3:
; CHECK-NEXT: br label [[L2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2:
; CHECK-NEXT: [[TOK_L2:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2]]) ]
; CHECK-NEXT: br i1 [[COND:%.*]], label [[L2]], label [[LATCH:%.*]], !llvm.loop [[LOOP4]]
; CHECK: latch:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2]]) ]
; CHECK-NEXT: br label [[L2_1:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.1:
; CHECK-NEXT: [[TOK_L2_1:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_1]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_1]], label [[LATCH_1:%.*]], !llvm.loop [[LOOP4]]
; CHECK: latch.1:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_1]]) ]
; CHECK-NEXT: br label [[L2_2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.2:
; CHECK-NEXT: [[TOK_L2_2:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_2]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_2]], label [[LATCH_2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: latch.2:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_2]]) ]
; CHECK-NEXT: br label [[L2_3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.3:
; CHECK-NEXT: [[TOK_L2_3:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_3]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_3]], label [[LATCH_3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: latch.3:
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_3]]) ]
; CHECK-NEXT: ret i32 0
;
entry:
br label %l3
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %latch ]
%tok.loop = call token @llvm.experimental.convergence.anchor()
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, 4
br label %l2, !llvm.loop !1
l2:
%tok.l2 = call token @llvm.experimental.convergence.anchor()
call void @f() [ "convergencectrl"(token %tok.l2) ]
br i1 %cond, label %l2, label %latch, !llvm.loop !1
latch:
call void @f() [ "convergencectrl"(token %tok.l2) ]
br i1 %exitcond, label %exit, label %l3
exit:
ret i32 0
}
; No extension. Both loops unrolled.
define i32 @unroll_nest(i32 %n, i1 %cond) {
; CHECK-LABEL: @unroll_nest(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L3:%.*]]
; CHECK: l3:
; CHECK-NEXT: br label [[L2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2:
; CHECK-NEXT: [[TOK_L2:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2]]) ]
; CHECK-NEXT: br i1 [[COND:%.*]], label [[L2_1:%.*]], label [[LATCH:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.1:
; CHECK-NEXT: [[TOK_L2_1:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_1]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2]], label [[LATCH]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: latch:
; CHECK-NEXT: br label [[L2_12:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.12:
; CHECK-NEXT: [[TOK_L2_11:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_11]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_1_1:%.*]], label [[LATCH_1:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.1.1:
; CHECK-NEXT: [[TOK_L2_1_1:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_1_1]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_12]], label [[LATCH_1]], !llvm.loop [[LOOP9]]
; CHECK: latch.1:
; CHECK-NEXT: br label [[L2_2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.2:
; CHECK-NEXT: [[TOK_L2_2:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_2]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_1_2:%.*]], label [[LATCH_2:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.1.2:
; CHECK-NEXT: [[TOK_L2_1_2:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_1_2]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_2]], label [[LATCH_2]], !llvm.loop [[LOOP9]]
; CHECK: latch.2:
; CHECK-NEXT: br label [[L2_3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.3:
; CHECK-NEXT: [[TOK_L2_3:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_3]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_1_3:%.*]], label [[LATCH_3:%.*]], !llvm.loop [[LOOP4]]
; CHECK: l2.1.3:
; CHECK-NEXT: [[TOK_L2_1_3:%.*]] = call token @llvm.experimental.convergence.anchor()
; CHECK-NEXT: call void @f() [ "convergencectrl"(token [[TOK_L2_1_3]]) ]
; CHECK-NEXT: br i1 [[COND]], label [[L2_3]], label [[LATCH_3]], !llvm.loop [[LOOP9]]
; CHECK: latch.3:
; CHECK-NEXT: ret i32 0
;
entry:
br label %l3
l3:
%x.0 = phi i32 [ 0, %entry ], [ %inc, %latch ]
%tok.loop = call token @llvm.experimental.convergence.anchor()
%inc = add nsw i32 %x.0, 1
%exitcond = icmp eq i32 %inc, 4
br label %l2, !llvm.loop !1
l2:
%tok.l2 = call token @llvm.experimental.convergence.anchor()
call void @f() [ "convergencectrl"(token %tok.l2) ]
br i1 %cond, label %l2, label %latch, !llvm.loop !1
latch:
br i1 %exitcond, label %exit, label %l3
exit:
ret i32 0
}
declare token @llvm.experimental.convergence.anchor()
declare token @llvm.experimental.convergence.loop()
!0 = !{!0, !{!"llvm.loop.unroll.count", i32 16}}
!1 = !{!1, !{!"llvm.loop.unroll.count", i32 2}}
Reference in New Issue View Git Blame Copy Permalink