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
45 lines
2.1 KiB
LLVM
45 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -O3 -tail-predication=force-enabled-no-reductions %s -o - | FileCheck %s
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @arm_max_no_idx_f32_mve(ptr %pSrc, i32 %blockSize, ptr nocapture %pResult) {
|
|
; CHECK-LABEL: arm_max_no_idx_f32_mve:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: .save {r7, lr}
|
|
; CHECK-NEXT: push {r7, lr}
|
|
; CHECK-NEXT: movs r3, #0
|
|
; CHECK-NEXT: movt r3, #65408
|
|
; CHECK-NEXT: vdup.32 q0, r3
|
|
; CHECK-NEXT: dlstp.32 lr, r1
|
|
; CHECK-NEXT: .LBB0_1: @ %do.body
|
|
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: vldrw.u32 q1, [r0], #16
|
|
; CHECK-NEXT: vmaxnm.f32 q0, q1, q0
|
|
; CHECK-NEXT: letp lr, .LBB0_1
|
|
; CHECK-NEXT: @ %bb.2: @ %do.end
|
|
; CHECK-NEXT: pop {r7, pc}
|
|
entry:
|
|
br label %do.body
|
|
|
|
do.body: ; preds = %do.body, %entry
|
|
%blockSize.addr.0 = phi i32 [ %blockSize, %entry ], [ %sub, %do.body ]
|
|
%curExtremValVec.0 = phi <4 x float> [ <float 0xFFF0000000000000, float 0xFFF0000000000000, float 0xFFF0000000000000, float 0xFFF0000000000000>, %entry ], [ %3, %do.body ]
|
|
%pSrc.addr.0 = phi ptr [ %pSrc, %entry ], [ %add.ptr, %do.body ]
|
|
%0 = tail call <4 x i1> @llvm.arm.mve.vctp32(i32 %blockSize.addr.0)
|
|
%1 = bitcast ptr %pSrc.addr.0 to ptr
|
|
%2 = tail call fast <4 x float> @llvm.masked.load.v4f32.p0(ptr %1, i32 4, <4 x i1> %0, <4 x float> zeroinitializer)
|
|
%3 = tail call fast <4 x float> @llvm.arm.mve.max.predicated.v4f32.v4i1(<4 x float> %2, <4 x float> %curExtremValVec.0, i32 0, <4 x i1> %0, <4 x float> %curExtremValVec.0)
|
|
%add.ptr = getelementptr inbounds float, ptr %pSrc.addr.0, i32 4
|
|
%sub = add i32 %blockSize.addr.0, -4
|
|
%cmp = icmp sgt i32 %sub, 0
|
|
br i1 %cmp, label %do.body, label %do.end
|
|
|
|
do.end: ; preds = %do.body
|
|
ret <4 x float> %3
|
|
}
|
|
|
|
declare <4 x i1> @llvm.arm.mve.vctp32(i32)
|
|
|
|
declare <4 x float> @llvm.masked.load.v4f32.p0(ptr, i32 immarg, <4 x i1>, <4 x float>)
|
|
|
|
declare <4 x float> @llvm.arm.mve.max.predicated.v4f32.v4i1(<4 x float>, <4 x float>, i32, <4 x i1>, <4 x float>)
|