derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
47 lines
2.6 KiB
Plaintext
47 lines
2.6 KiB
Plaintext
// DEFINE: %{triple} =
|
|
// DEFINE: %{check-unroll} = %flang_fc1 -emit-llvm -O1 -vectorize-loops -funroll-loops -mllvm -force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s --check-prefixes=CHECK,UNROLL
|
|
// DEFINE: %{check-nounroll} = %flang_fc1 -emit-llvm -O1 -vectorize-loops -mllvm -force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s --check-prefixes=CHECK,NO-UNROLL
|
|
|
|
// REDEFINE: %{triple} = aarch64-unknown-linux-gnu
|
|
// RUN: %if aarch64-registered-target %{ %{check-unroll} %}
|
|
// RUN: %if aarch64-registered-target %{ %{check-nounroll} %}
|
|
|
|
// REDEFINE: %{triple} = x86_64-unknown-linux-gnu
|
|
// RUN: %if x86-registered-target %{ %{check-unroll} %}
|
|
// RUN: %if x86-registered-target %{ %{check-nounroll} %}
|
|
|
|
// CHECK-LABEL: @unroll
|
|
// CHECK-SAME: (ptr {{[^%]*}}%[[ARG0:.*]])
|
|
func.func @unroll(%arg0: !fir.ref<!fir.array<1000 x index>> {fir.bindc_name = "a"}) {
|
|
%scope = fir.dummy_scope : !fir.dscope
|
|
%c1000 = arith.constant 1000 : index
|
|
%shape = fir.shape %c1000 : (index) -> !fir.shape<1>
|
|
%a:2 = hlfir.declare %arg0(%shape) dummy_scope %scope {uniq_name = "unrollEa"} : (!fir.ref<!fir.array<1000xindex>>, !fir.shape<1>, !fir.dscope) -> (!fir.ref<!fir.array<1000 x index>>, !fir.ref<!fir.array<1000 x index>>)
|
|
%c1 = arith.constant 1 : index
|
|
fir.do_loop %arg1 = %c1 to %c1000 step %c1 {
|
|
// CHECK: br label %[[BLK:.*]]
|
|
// CHECK: [[BLK]]:
|
|
// CHECK-NEXT: %[[IND:.*]] = phi i64 [ 0, %{{.*}} ], [ %[[NIV:.*]], %[[BLK]] ]
|
|
// CHECK-NEXT: %[[VIND:.*]] = phi <2 x i64> [ <i64 1, i64 2>, %{{.*}} ], [ %[[NVIND:.*]], %[[BLK]] ]
|
|
|
|
// NO-UNROLL-NEXT: %[[GEP:.*]] = getelementptr [8 x i8], ptr %[[ARG0]], i64 %[[IND]]
|
|
// NO-UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP]]
|
|
// NO-UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %{{.*}}, 2
|
|
// NO-UNROLL-NEXT: %[[NVIND]] = add nuw nsw <2 x i64> %[[VIND]], splat (i64 2)
|
|
|
|
// UNROLL-NEXT: %[[VIND1:.*]] = add nuw nsw <2 x i64> %[[VIND]], splat (i64 2)
|
|
// UNROLL-NEXT: %[[GEP0:.*]] = getelementptr [8 x i8], ptr %[[ARG0]], i64 %[[IND]]
|
|
// UNROLL-NEXT: %[[GEP1:.*]] = getelementptr i8, ptr %[[GEP0]], i64 16
|
|
// UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP0]]
|
|
// UNROLL-NEXT: store <2 x i64> %[[VIND1]], ptr %[[GEP1]]
|
|
// UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %[[IND]], 4
|
|
// UNROLL-NEXT: %[[NVIND:.*]] = add nuw nsw <2 x i64> %[[VIND]], splat (i64 4)
|
|
|
|
// CHECK-NEXT: %[[EXIT:.*]] = icmp eq i64 %[[NIV]], 1000
|
|
// CHECK-NEXT: br i1 %[[EXIT]], label %{{.*}}, label %[[BLK]]
|
|
%ai = hlfir.designate %a#0 (%arg1) : (!fir.ref<!fir.array<1000 x index>>, index) -> !fir.ref<index>
|
|
hlfir.assign %arg1 to %ai : index, !fir.ref<index>
|
|
}
|
|
return
|
|
}
|