654e6aabb9
The final piece of IR-level analysis to allow this was committed with: rL350188 Using the intrinsics should improve transforms based on cost models like vectorization and inlining. The backend should be prepared too, so we can now canonicalize more sequences of shift/logic to the intrinsics and know that the end result should be equal or better to the original code even if the target does not have an actual rotate instruction. llvm-svn: 350199
39 lines
1.2 KiB
LLVM
39 lines
1.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -O3 -S < %s | FileCheck %s --check-prefixes=ANY,OLDPM
|
|
; RUN: opt -passes='default<O3>' -S < %s | FileCheck %s --check-prefixes=ANY,NEWPM
|
|
|
|
; This should become a single funnel shift through a combination
|
|
; of aggressive-instcombine, simplifycfg, and instcombine.
|
|
; https://bugs.llvm.org/show_bug.cgi?id=34924
|
|
; These are equivalent, but the value name with the new-pm shows a bug -
|
|
; this code should not have been converted to a speculative select with
|
|
; an intermediate transform.
|
|
|
|
define i32 @rotl(i32 %a, i32 %b) {
|
|
; OLDPM-LABEL: @rotl(
|
|
; OLDPM-NEXT: entry:
|
|
; OLDPM-NEXT: [[TMP0:%.*]] = tail call i32 @llvm.fshl.i32(i32 [[A:%.*]], i32 [[A]], i32 [[B:%.*]])
|
|
; OLDPM-NEXT: ret i32 [[TMP0]]
|
|
;
|
|
; NEWPM-LABEL: @rotl(
|
|
; NEWPM-NEXT: entry:
|
|
; NEWPM-NEXT: [[SPEC_SELECT:%.*]] = tail call i32 @llvm.fshl.i32(i32 [[A:%.*]], i32 [[A]], i32 [[B:%.*]])
|
|
; NEWPM-NEXT: ret i32 [[SPEC_SELECT]]
|
|
;
|
|
entry:
|
|
%cmp = icmp eq i32 %b, 0
|
|
br i1 %cmp, label %end, label %rotbb
|
|
|
|
rotbb:
|
|
%sub = sub i32 32, %b
|
|
%shr = lshr i32 %a, %sub
|
|
%shl = shl i32 %a, %b
|
|
%or = or i32 %shr, %shl
|
|
br label %end
|
|
|
|
end:
|
|
%cond = phi i32 [ %or, %rotbb ], [ %a, %entry ]
|
|
ret i32 %cond
|
|
}
|
|
|