6f1a8c2da2
This patch implements autovectorization support for the 'all-in-one' histogram intrinsic, which seems to have more support than the 'standalone' intrinsic. See https://discourse.llvm.org/t/rfc-vectorization-support-for-histogram-count-operations/74788/ for an overview of the work and my notes on the tradeoffs between the two approaches.
45 lines
2.1 KiB
LLVM
45 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
|
|
; RUN: opt < %s -passes=loop-vectorize,instcombine -enable-histogram-loop-vectorization -force-vector-width=2 -S | FileCheck %s
|
|
|
|
;; Currently we don't expect this to vectorize, since the generic cost model returns
|
|
;; invalid for the histogram intrinsic.
|
|
define void @simple_histogram(ptr noalias %buckets, ptr readonly %indices, i64 %N) {
|
|
; CHECK-LABEL: define void @simple_histogram(
|
|
; CHECK-SAME: ptr noalias [[BUCKETS:%.*]], ptr readonly [[INDICES:%.*]], i64 [[N:%.*]]) {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[INDICES]], i64 [[IV]]
|
|
; CHECK-NEXT: [[TMP12:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
|
|
; CHECK-NEXT: [[IDXPROM1:%.*]] = zext i32 [[TMP12]] to i64
|
|
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[BUCKETS]], i64 [[IDXPROM1]]
|
|
; CHECK-NEXT: [[TMP13:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
|
|
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP13]], 1
|
|
; CHECK-NEXT: store i32 [[INC]], ptr [[ARRAYIDX2]], align 4
|
|
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_EXIT:%.*]], label [[FOR_BODY]]
|
|
; CHECK: for.exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%gep.indices = getelementptr inbounds i32, ptr %indices, i64 %iv
|
|
%l.idx = load i32, ptr %gep.indices, align 4
|
|
%idxprom1 = zext i32 %l.idx to i64
|
|
%gep.bucket = getelementptr inbounds i32, ptr %buckets, i64 %idxprom1
|
|
%l.bucket = load i32, ptr %gep.bucket, align 4
|
|
%inc = add nsw i32 %l.bucket, 1
|
|
store i32 %inc, ptr %gep.bucket, align 4
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond = icmp eq i64 %iv.next, %N
|
|
br i1 %exitcond, label %for.exit, label %for.body
|
|
|
|
for.exit:
|
|
ret void
|
|
}
|