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
233 lines
12 KiB
LLVM
233 lines
12 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc < %s -mtriple=riscv64 -mattr=+v | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n32:64-S128"
|
|
target triple = "riscv64-unknown-linux-gnu"
|
|
|
|
define i1 @main(ptr %var_117, ptr %arrayinit.element3045, ptr %arrayinit.element3047, ptr %arrayinit.element3049, ptr %arrayinit.element3051, ptr %arrayinit.element3053, ptr %arrayinit.element3055, ptr %arrayinit.element3057, ptr %arrayinit.element3059, ptr %arrayinit.element3061, ptr %arrayinit.element3063, ptr %arrayinit.element3065, ptr %arrayinit.element3067, i64 %var_94_i.07698, target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %0, target("riscv.vector.tuple", <vscale x 16 x i8>, 4) %1) {
|
|
; CHECK-LABEL: main:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: addi sp, sp, -16
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: csrr t0, vlenb
|
|
; CHECK-NEXT: slli t0, t0, 3
|
|
; CHECK-NEXT: mv t1, t0
|
|
; CHECK-NEXT: slli t0, t0, 1
|
|
; CHECK-NEXT: add t0, t0, t1
|
|
; CHECK-NEXT: sub sp, sp, t0
|
|
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
|
|
; CHECK-NEXT: sd a1, 8(sp) # 8-byte Folded Spill
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 4
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: addi a1, a1, 16
|
|
; CHECK-NEXT: vs4r.v v12, (a1) # vscale x 32-byte Folded Spill
|
|
; CHECK-NEXT: csrr t0, vlenb
|
|
; CHECK-NEXT: slli t0, t0, 2
|
|
; CHECK-NEXT: add a1, a1, t0
|
|
; CHECK-NEXT: vs4r.v v16, (a1) # vscale x 32-byte Folded Spill
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 2
|
|
; CHECK-NEXT: mv t0, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t0
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: addi a1, a1, 16
|
|
; CHECK-NEXT: vs4r.v v8, (a1) # vscale x 32-byte Folded Spill
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 3
|
|
; CHECK-NEXT: mv t0, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t0
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: ld t0, 56(a1)
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 3
|
|
; CHECK-NEXT: mv t1, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t1
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: ld t1, 48(a1)
|
|
; CHECK-NEXT: vsetvli t2, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v9, 0
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 3
|
|
; CHECK-NEXT: mv t2, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t2
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: ld t2, 40(a1)
|
|
; CHECK-NEXT: # kill: def $v10 killed $v9 killed $vtype
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 3
|
|
; CHECK-NEXT: mv t3, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t3
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: ld t3, 32(a1)
|
|
; CHECK-NEXT: vmv.v.i v11, 0
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 3
|
|
; CHECK-NEXT: mv t4, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t4
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: ld t4, 16(a1)
|
|
; CHECK-NEXT: vmv.v.i v12, 0
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 3
|
|
; CHECK-NEXT: mv t5, a1
|
|
; CHECK-NEXT: slli a1, a1, 1
|
|
; CHECK-NEXT: add a1, a1, t5
|
|
; CHECK-NEXT: add a1, sp, a1
|
|
; CHECK-NEXT: ld t5, 24(a1)
|
|
; CHECK-NEXT: vmv.v.i v13, 0
|
|
; CHECK-NEXT: vsetvli t6, zero, e8, m2, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v16, 0
|
|
; CHECK-NEXT: vmv1r.v v14, v9
|
|
; CHECK-NEXT: sd zero, 0(a0)
|
|
; CHECK-NEXT: vmv.v.i v18, 0
|
|
; CHECK-NEXT: vmv1r.v v15, v9
|
|
; CHECK-NEXT: vmv1r.v v28, v9
|
|
; CHECK-NEXT: li t6, 1023
|
|
; CHECK-NEXT: vmv.v.i v20, 0
|
|
; CHECK-NEXT: vmv1r.v v29, v9
|
|
; CHECK-NEXT: slli t6, t6, 52
|
|
; CHECK-NEXT: vmv.v.i v22, 0
|
|
; CHECK-NEXT: addi a1, sp, 16
|
|
; CHECK-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
|
|
; CHECK-NEXT: ld a1, 8(sp) # 8-byte Folded Reload
|
|
; CHECK-NEXT: vmv1r.v v30, v9
|
|
; CHECK-NEXT: sd t6, 0(t5)
|
|
; CHECK-NEXT: vmv1r.v v21, v9
|
|
; CHECK-NEXT: vmv2r.v v22, v10
|
|
; CHECK-NEXT: vmv4r.v v24, v12
|
|
; CHECK-NEXT: vmv1r.v v31, v9
|
|
; CHECK-NEXT: csrr t5, vlenb
|
|
; CHECK-NEXT: slli t5, t5, 3
|
|
; CHECK-NEXT: add t5, sp, t5
|
|
; CHECK-NEXT: addi t5, t5, 16
|
|
; CHECK-NEXT: vs4r.v v28, (t5) # vscale x 32-byte Folded Spill
|
|
; CHECK-NEXT: vsetivli zero, 0, e32, m1, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v13, 0
|
|
; CHECK-NEXT: vmclr.m v14
|
|
; CHECK-NEXT: .LBB0_1: # %for.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: vsetivli zero, 0, e64, m2, ta, ma
|
|
; CHECK-NEXT: vmv1r.v v0, v14
|
|
; CHECK-NEXT: vmv1r.v v17, v13
|
|
; CHECK-NEXT: vmv1r.v v15, v13
|
|
; CHECK-NEXT: vmv1r.v v9, v13
|
|
; CHECK-NEXT: vmv1r.v v16, v13
|
|
; CHECK-NEXT: vmv1r.v v19, v13
|
|
; CHECK-NEXT: vmv1r.v v28, v13
|
|
; CHECK-NEXT: vmv1r.v v12, v13
|
|
; CHECK-NEXT: vmv1r.v v2, v21
|
|
; CHECK-NEXT: vmv1r.v v4, v23
|
|
; CHECK-NEXT: vmv1r.v v5, v24
|
|
; CHECK-NEXT: vmv1r.v v6, v25
|
|
; CHECK-NEXT: vmv1r.v v7, v26
|
|
; CHECK-NEXT: vmv1r.v v8, v27
|
|
; CHECK-NEXT: vmv.v.i v10, 0
|
|
; CHECK-NEXT: vmv.v.i v30, 0
|
|
; CHECK-NEXT: vmv1r.v v29, v13
|
|
; CHECK-NEXT: vmv1r.v v18, v14
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, m1, tu, ma
|
|
; CHECK-NEXT: vle32.v v17, (t4)
|
|
; CHECK-NEXT: vle32.v v15, (t1)
|
|
; CHECK-NEXT: vle32.v v28, (a7)
|
|
; CHECK-NEXT: vle64.v v30, (a4)
|
|
; CHECK-NEXT: vle32.v v9, (t2)
|
|
; CHECK-NEXT: vle32.v v16, (t3)
|
|
; CHECK-NEXT: vle32.v v19, (a6)
|
|
; CHECK-NEXT: vmv1r.v v3, v28
|
|
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
|
|
; CHECK-NEXT: vmflt.vv v18, v30, v10, v0.t
|
|
; CHECK-NEXT: vmv1r.v v19, v13
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, m1, tu, mu
|
|
; CHECK-NEXT: vle32.v v29, (a2)
|
|
; CHECK-NEXT: vle32.v v19, (a3)
|
|
; CHECK-NEXT: vle32.v v12, (a5)
|
|
; CHECK-NEXT: vmv1r.v v1, v17
|
|
; CHECK-NEXT: csrr t5, vlenb
|
|
; CHECK-NEXT: slli t5, t5, 3
|
|
; CHECK-NEXT: add t5, sp, t5
|
|
; CHECK-NEXT: addi t5, t5, 16
|
|
; CHECK-NEXT: vl1r.v v9, (t5) # vscale x 8-byte Folded Reload
|
|
; CHECK-NEXT: csrr t6, vlenb
|
|
; CHECK-NEXT: add t5, t5, t6
|
|
; CHECK-NEXT: vl2r.v v10, (t5) # vscale x 16-byte Folded Reload
|
|
; CHECK-NEXT: slli t6, t6, 1
|
|
; CHECK-NEXT: add t5, t5, t6
|
|
; CHECK-NEXT: vl1r.v v12, (t5) # vscale x 8-byte Folded Reload
|
|
; CHECK-NEXT: vsseg4e32.v v9, (zero)
|
|
; CHECK-NEXT: vsseg8e32.v v1, (a1)
|
|
; CHECK-NEXT: vmv1r.v v0, v18
|
|
; CHECK-NEXT: vssub.vv v19, v13, v29, v0.t
|
|
; CHECK-NEXT: csrr t5, vlenb
|
|
; CHECK-NEXT: slli t5, t5, 2
|
|
; CHECK-NEXT: mv t6, t5
|
|
; CHECK-NEXT: slli t5, t5, 1
|
|
; CHECK-NEXT: add t5, t5, t6
|
|
; CHECK-NEXT: add t5, sp, t5
|
|
; CHECK-NEXT: addi t5, t5, 16
|
|
; CHECK-NEXT: vl4r.v v28, (t5) # vscale x 32-byte Folded Reload
|
|
; CHECK-NEXT: vsetvli zero, t0, e64, m2, ta, ma
|
|
; CHECK-NEXT: vsseg2e64.v v28, (zero)
|
|
; CHECK-NEXT: vmv1r.v v0, v14
|
|
; CHECK-NEXT: addi t5, sp, 16
|
|
; CHECK-NEXT: vl2r.v v2, (t5) # vscale x 16-byte Folded Reload
|
|
; CHECK-NEXT: csrr t6, vlenb
|
|
; CHECK-NEXT: slli t6, t6, 1
|
|
; CHECK-NEXT: add t5, t5, t6
|
|
; CHECK-NEXT: vl4r.v v4, (t5) # vscale x 32-byte Folded Reload
|
|
; CHECK-NEXT: slli t6, t6, 1
|
|
; CHECK-NEXT: add t5, t5, t6
|
|
; CHECK-NEXT: vl2r.v v8, (t5) # vscale x 16-byte Folded Reload
|
|
; CHECK-NEXT: vsetivli zero, 0, e64, m2, ta, ma
|
|
; CHECK-NEXT: vsseg4e64.v v2, (zero), v0.t
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma
|
|
; CHECK-NEXT: vsseg8e32.v v19, (a0)
|
|
; CHECK-NEXT: csrr t5, vlenb
|
|
; CHECK-NEXT: slli t5, t5, 4
|
|
; CHECK-NEXT: add t5, sp, t5
|
|
; CHECK-NEXT: addi t5, t5, 16
|
|
; CHECK-NEXT: vl8r.v v0, (t5) # vscale x 64-byte Folded Reload
|
|
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma
|
|
; CHECK-NEXT: vsseg4e64.v v0, (zero)
|
|
; CHECK-NEXT: j .LBB0_1
|
|
entry:
|
|
store double 0.000000e+00, ptr %var_117, align 8
|
|
store double 1.000000e+00, ptr %arrayinit.element3061, align 8
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%2 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3059, i64 0)
|
|
%3 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3067, i64 0)
|
|
%4 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3065, i64 0)
|
|
%5 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3063, i64 0)
|
|
%6 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3055, i64 0)
|
|
%7 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3057, i64 0)
|
|
%8 = call <vscale x 2 x float> @llvm.riscv.vle.nxv2f32.p0.i64(<vscale x 2 x float> zeroinitializer, ptr %arrayinit.element3053, i64 0)
|
|
%9 = call <vscale x 2 x double> @llvm.riscv.vle.nxv2f64.p0.i64(<vscale x 2 x double> zeroinitializer, ptr %arrayinit.element3051, i64 0)
|
|
%10 = tail call <vscale x 2 x i32> @llvm.riscv.vle.nxv2i32.p0.i64(<vscale x 2 x i32> zeroinitializer, ptr %arrayinit.element3047, i64 0)
|
|
%11 = tail call <vscale x 2 x i32> @llvm.riscv.vle.nxv2i32.p0.i64(<vscale x 2 x i32> zeroinitializer, ptr %arrayinit.element3049, i64 0)
|
|
call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) zeroinitializer, ptr null, i64 0, i64 5)
|
|
%12 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) zeroinitializer, <vscale x 2 x float> %8, i32 0)
|
|
%13 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %12, <vscale x 2 x float> %7, i32 2)
|
|
%14 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %13, <vscale x 2 x float> %6, i32 0)
|
|
%15 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %14, <vscale x 2 x float> %5, i32 0)
|
|
%16 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %15, <vscale x 2 x float> %4, i32 0)
|
|
%17 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %16, <vscale x 2 x float> %3, i32 0)
|
|
%18 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2f32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %17, <vscale x 2 x float> %2, i32 0)
|
|
call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %18, ptr %arrayinit.element3045, i64 0, i64 5)
|
|
%19 = tail call <vscale x 2 x i1> @llvm.riscv.vmfgt.mask.nxv2f64.nxv2f64.i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> zeroinitializer, <vscale x 2 x double> %9, <vscale x 2 x i1> zeroinitializer, i64 0)
|
|
%20 = tail call <vscale x 2 x i32> @llvm.riscv.vssub.mask.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> %11, <vscale x 2 x i32> zeroinitializer, <vscale x 2 x i32> %10, <vscale x 2 x i1> %19, i64 0, i64 0)
|
|
call void @llvm.riscv.vsseg2.triscv.vector.tuple_nxv16i8_2t.p0.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %0, ptr null, i64 %var_94_i.07698, i64 6)
|
|
call void @llvm.riscv.vsseg4.mask.triscv.vector.tuple_nxv16i8_4t.p0.nxv2i1.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) zeroinitializer, ptr null, <vscale x 2 x i1> zeroinitializer, i64 0, i64 6)
|
|
%21 = tail call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv2i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 2 x i32> %20, i32 0)
|
|
call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) %21, ptr %var_117, i64 0, i64 5)
|
|
call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv16i8_4t.p0.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) %1, ptr null, i64 0, i64 6)
|
|
br label %for.body
|
|
}
|