mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-16 11:30:51 +00:00
041211cd79
The llvm.SI.end.cf intrinsic is used to mark the end of if-then blocks,
if-then-else blocks, and loops. It is responsible for updating the
exec mask to re-enable threads that had been masked during the preceding
control flow block. For example:
s_mov_b64 exec, 0x3 ; Initial exec mask
s_mov_b64 s[0:1], exec ; Saved exec mask
v_cmpx_gt_u32 exec, s[2:3], v0, 0 ; llvm.SI.if
do_stuff()
s_or_b64 exec, exec, s[0:1] ; llvm.SI.end.cf
The bug fixed by this patch was one where the llvm.SI.end.cf intrinsic
was being inserted into the header of loops. This would happen when
an if block terminated in a loop header and we would end up with
code like this:
s_mov_b64 exec, 0x3 ; Initial exec mask
s_mov_b64 s[0:1], exec ; Saved exec mask
v_cmpx_gt_u32 exec, s[2:3], v0, 0 ; llvm.SI.if
do_stuff()
LOOP: ; Start of loop header
s_or_b64 exec, exec, s[0:1] ; llvm.SI.end.cf <-BUG: The exec mask has the
same value at the beginning of each loop
iteration.
do_stuff();
s_cbranch_execnz LOOP
The fix is to create a new basic block before the loop and insert the
llvm.SI.end.cf there. This way the exec mask is restored before the
start of the loop instead of at the beginning of each iteration.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228302 91177308-0d34-0410-b5e6-96231b3b80d8
35 lines
944 B
LLVM
35 lines
944 B
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=SI -verify-machineinstrs | FileCheck %s
|
|
|
|
; This tests that the llvm.SI.end.cf intrinsic is not inserted into the
|
|
; loop block. This intrinsic will be lowered to s_or_b64 by the code
|
|
; generator.
|
|
|
|
; CHECK-LABEL: {{^}}test:
|
|
|
|
; This is was lowered from the llvm.SI.end.cf intrinsic:
|
|
; CHECK: s_or_b64 exec, exec
|
|
|
|
; CHECK: [[LOOP_LABEL:[0-9A-Za-z_]+]]: ; %loop{{$}}
|
|
; CHECK-NOT: s_or_b64 exec, exec
|
|
; CHECK: s_cbranch_execnz [[LOOP_LABEL]]
|
|
define void @test(i32 addrspace(1)* %out, i32 %cond) {
|
|
entry:
|
|
%tmp0 = icmp eq i32 %cond, 0
|
|
br i1 %tmp0, label %if, label %loop
|
|
|
|
if:
|
|
store i32 0, i32 addrspace(1)* %out
|
|
br label %loop
|
|
|
|
loop:
|
|
%tmp1 = phi i32 [0, %entry], [0, %if], [%inc, %loop]
|
|
%inc = add i32 %tmp1, %cond
|
|
%tmp2 = icmp ugt i32 %inc, 10
|
|
br i1 %tmp2, label %done, label %loop
|
|
|
|
done:
|
|
%tmp3 = getelementptr i32 addrspace(1)* %out, i64 1
|
|
store i32 %inc, i32 addrspace(1)* %tmp3
|
|
ret void
|
|
}
|