derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/CodeGen/RISCV/rvv/vreductions-fp-vp.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

520 lines
22 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfh,+v -target-abi=ilp32d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfh,+v -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
define half @vpreduce_fadd_nxv1f16(half %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv1f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call reassoc half @llvm.vp.reduce.fadd.nxv1f16(half %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_ord_fadd_nxv1f16(half %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv1f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call half @llvm.vp.reduce.fadd.nxv1f16(half %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_fadd_nxv2f16(half %s, <vscale x 2 x half> %v, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv2f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT: vfredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call reassoc half @llvm.vp.reduce.fadd.nxv2f16(half %s, <vscale x 2 x half> %v, <vscale x 2 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_ord_fadd_nxv2f16(half %s, <vscale x 2 x half> %v, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv2f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT: vfredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call half @llvm.vp.reduce.fadd.nxv2f16(half %s, <vscale x 2 x half> %v, <vscale x 2 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_fadd_nxv4f16(half %s, <vscale x 4 x half> %v, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv4f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT: vfredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call reassoc half @llvm.vp.reduce.fadd.nxv4f16(half %s, <vscale x 4 x half> %v, <vscale x 4 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_ord_fadd_nxv4f16(half %s, <vscale x 4 x half> %v, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv4f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT: vfredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call half @llvm.vp.reduce.fadd.nxv4f16(half %s, <vscale x 4 x half> %v, <vscale x 4 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_fadd_nxv64f16(half %s, <vscale x 64 x half> %v, <vscale x 64 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv64f16:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: srli a1, a2, 1
; CHECK-NEXT: slli a2, a2, 2
; CHECK-NEXT: vsetvli a3, zero, e8, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v24, v0, a1
; CHECK-NEXT: sub a1, a0, a2
; CHECK-NEXT: sltu a3, a0, a1
; CHECK-NEXT: addi a3, a3, -1
; CHECK-NEXT: and a1, a3, a1
; CHECK-NEXT: bltu a0, a2, .LBB6_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: mv a0, a2
; CHECK-NEXT: .LBB6_2:
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vfmv.s.f v25, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT: vfredusum.vs v25, v8, v25, v0.t
; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
; CHECK-NEXT: vfredusum.vs v25, v16, v25, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v25
; CHECK-NEXT: ret
%r = call reassoc half @llvm.vp.reduce.fadd.nxv64f16(half %s, <vscale x 64 x half> %v, <vscale x 64 x i1> %m, i32 %evl)
ret half %r
}
define half @vpreduce_ord_fadd_nxv64f16(half %s, <vscale x 64 x half> %v, <vscale x 64 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv64f16:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: srli a1, a2, 1
; CHECK-NEXT: slli a2, a2, 2
; CHECK-NEXT: vsetvli a3, zero, e8, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v24, v0, a1
; CHECK-NEXT: sub a1, a0, a2
; CHECK-NEXT: sltu a3, a0, a1
; CHECK-NEXT: addi a3, a3, -1
; CHECK-NEXT: and a1, a3, a1
; CHECK-NEXT: bltu a0, a2, .LBB7_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: mv a0, a2
; CHECK-NEXT: .LBB7_2:
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vfmv.s.f v25, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT: vfredosum.vs v25, v8, v25, v0.t
; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
; CHECK-NEXT: vfredosum.vs v25, v16, v25, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v25
; CHECK-NEXT: ret
%r = call half @llvm.vp.reduce.fadd.nxv64f16(half %s, <vscale x 64 x half> %v, <vscale x 64 x i1> %m, i32 %evl)
ret half %r
}
define float @vpreduce_fadd_nxv1f32(float %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call reassoc float @llvm.vp.reduce.fadd.nxv1f32(float %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_ord_fadd_nxv1f32(float %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call float @llvm.vp.reduce.fadd.nxv1f32(float %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_fadd_nxv2f32(float %s, <vscale x 2 x float> %v, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT: vfredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call reassoc float @llvm.vp.reduce.fadd.nxv2f32(float %s, <vscale x 2 x float> %v, <vscale x 2 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_ord_fadd_nxv2f32(float %s, <vscale x 2 x float> %v, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT: vfredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call float @llvm.vp.reduce.fadd.nxv2f32(float %s, <vscale x 2 x float> %v, <vscale x 2 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_fadd_nxv4f32(float %s, <vscale x 4 x float> %v, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vfredusum.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%r = call reassoc float @llvm.vp.reduce.fadd.nxv4f32(float %s, <vscale x 4 x float> %v, <vscale x 4 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_ord_fadd_nxv4f32(float %s, <vscale x 4 x float> %v, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vfredosum.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%r = call float @llvm.vp.reduce.fadd.nxv4f32(float %s, <vscale x 4 x float> %v, <vscale x 4 x i1> %m, i32 %evl)
ret float %r
}
define double @vpreduce_fadd_nxv1f64(double %s, <vscale x 1 x double> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT: vfredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call reassoc double @llvm.vp.reduce.fadd.nxv1f64(double %s, <vscale x 1 x double> %v, <vscale x 1 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_ord_fadd_nxv1f64(double %s, <vscale x 1 x double> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT: vfredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%r = call double @llvm.vp.reduce.fadd.nxv1f64(double %s, <vscale x 1 x double> %v, <vscale x 1 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_fadd_nxv2f64(double %s, <vscale x 2 x double> %v, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; CHECK-NEXT: vfredusum.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%r = call reassoc double @llvm.vp.reduce.fadd.nxv2f64(double %s, <vscale x 2 x double> %v, <vscale x 2 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_ord_fadd_nxv2f64(double %s, <vscale x 2 x double> %v, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; CHECK-NEXT: vfredosum.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%r = call double @llvm.vp.reduce.fadd.nxv2f64(double %s, <vscale x 2 x double> %v, <vscale x 2 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_fadd_nxv3f64(double %s, <vscale x 3 x double> %v, <vscale x 3 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv3f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v12, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT: vfredusum.vs v12, v8, v12, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v12
; CHECK-NEXT: ret
%r = call reassoc double @llvm.vp.reduce.fadd.nxv3f64(double %s, <vscale x 3 x double> %v, <vscale x 3 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_ord_fadd_nxv3f64(double %s, <vscale x 3 x double> %v, <vscale x 3 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv3f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v12, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT: vfredosum.vs v12, v8, v12, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v12
; CHECK-NEXT: ret
%r = call double @llvm.vp.reduce.fadd.nxv3f64(double %s, <vscale x 3 x double> %v, <vscale x 3 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_fadd_nxv4f64(double %s, <vscale x 4 x double> %v, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_nxv4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v12, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT: vfredusum.vs v12, v8, v12, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v12
; CHECK-NEXT: ret
%r = call reassoc double @llvm.vp.reduce.fadd.nxv4f64(double %s, <vscale x 4 x double> %v, <vscale x 4 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_ord_fadd_nxv4f64(double %s, <vscale x 4 x double> %v, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_nxv4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v12, fa0
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT: vfredosum.vs v12, v8, v12, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v12
; CHECK-NEXT: ret
%r = call double @llvm.vp.reduce.fadd.nxv4f64(double %s, <vscale x 4 x double> %v, <vscale x 4 x i1> %m, i32 %evl)
ret double %r
}
define float @vpreduce_fminimum_nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fminimum_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vmfne.vv v10, v8, v8, v0.t
; CHECK-NEXT: feq.s a1, fa0, fa0
; CHECK-NEXT: vcpop.m a2, v10, v0.t
; CHECK-NEXT: xori a1, a1, 1
; CHECK-NEXT: or a1, a2, a1
; CHECK-NEXT: beqz a1, .LBB22_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: lui a0, 523264
; CHECK-NEXT: fmv.w.x fa0, a0
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB22_2:
; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vfredmin.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%s = call float @llvm.vp.reduce.fminimum.nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 %evl)
ret float %s
}
define float @vpreduce_fmaximum_nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fmaximum_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vmfne.vv v10, v8, v8, v0.t
; CHECK-NEXT: feq.s a1, fa0, fa0
; CHECK-NEXT: vcpop.m a2, v10, v0.t
; CHECK-NEXT: xori a1, a1, 1
; CHECK-NEXT: or a1, a2, a1
; CHECK-NEXT: beqz a1, .LBB23_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: lui a0, 523264
; CHECK-NEXT: fmv.w.x fa0, a0
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB23_2:
; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vfredmax.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%s = call float @llvm.vp.reduce.fmaximum.nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 %evl)
ret float %s
}
define float @vpreduce_fminimum_nnan_nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fminimum_nnan_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vfredmin.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%s = call nnan float @llvm.vp.reduce.fminimum.nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 %evl)
ret float %s
}
define float @vpreduce_fmaximum_nnan_nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fmaximum_nnan_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v10, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vfredmax.vs v10, v8, v10, v0.t
; CHECK-NEXT: vfmv.f.s fa0, v10
; CHECK-NEXT: ret
%s = call nnan float @llvm.vp.reduce.fmaximum.nxv4f32(float %start, <vscale x 4 x float> %val, <vscale x 4 x i1> %m, i32 %evl)
ret float %s
}
define float @vpreduce_fadd_fpext_vp_nxv1f16_nxv1f32(float %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_fpext_vp_nxv1f16_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfwredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = call <vscale x 1 x float> @llvm.vp.fpext(<vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 %evl)
%r = call reassoc float @llvm.vp.reduce.fadd(float %s, <vscale x 1 x float> %w, <vscale x 1 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_ord_fadd_fpext_vp_fpext_nxv1f16_nxv1f32(float %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_fpext_vp_fpext_nxv1f16_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfwredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = call <vscale x 1 x float> @llvm.vp.fpext(<vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 %evl)
%r = call float @llvm.vp.reduce.fadd(float %s, <vscale x 1 x float> %w, <vscale x 1 x i1> %m, i32 %evl)
ret float %r
}
define double @vpreduce_fadd_fpext_vp_nxv1f32_nxv1f64(double %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_fpext_vp_nxv1f32_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfwredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = call <vscale x 1 x double> @llvm.vp.fpext(<vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 %evl)
%r = call reassoc double @llvm.vp.reduce.fadd(double %s, <vscale x 1 x double> %w, <vscale x 1 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_ord_fadd_fpext_vp_fpext_nxv1f32_nxv1f64(double %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_fpext_vp_fpext_nxv1f32_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfwredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = call <vscale x 1 x double> @llvm.vp.fpext(<vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 %evl)
%r = call double @llvm.vp.reduce.fadd(double %s, <vscale x 1 x double> %w, <vscale x 1 x i1> %m, i32 %evl)
ret double %r
}
define float @vpreduce_fadd_fpext_nxv1f16_nxv1f32(float %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_fpext_nxv1f16_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfwredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = fpext <vscale x 1 x half> %v to <vscale x 1 x float>
%r = call reassoc float @llvm.vp.reduce.fadd(float %s, <vscale x 1 x float> %w, <vscale x 1 x i1> %m, i32 %evl)
ret float %r
}
define float @vpreduce_ord_fadd_fpext_nxv1f16_nxv1f32(float %s, <vscale x 1 x half> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_fpext_nxv1f16_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfwredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = fpext <vscale x 1 x half> %v to <vscale x 1 x float>
%r = call float @llvm.vp.reduce.fadd(float %s, <vscale x 1 x float> %w, <vscale x 1 x i1> %m, i32 %evl)
ret float %r
}
define double @vpreduce_fadd_fpext_nxv1f32_nxv1f64(double %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_fadd_fpext_nxv1f32_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfwredusum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = fpext <vscale x 1 x float> %v to <vscale x 1 x double>
%r = call reassoc double @llvm.vp.reduce.fadd(double %s, <vscale x 1 x double> %w, <vscale x 1 x i1> %m, i32 %evl)
ret double %r
}
define double @vpreduce_ord_fadd_fpext_nxv1f32_nxv1f64(double %s, <vscale x 1 x float> %v, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpreduce_ord_fadd_fpext_nxv1f32_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.s.f v9, fa0
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfwredosum.vs v9, v8, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v9
; CHECK-NEXT: ret
%w = fpext <vscale x 1 x float> %v to <vscale x 1 x double>
%r = call double @llvm.vp.reduce.fadd(double %s, <vscale x 1 x double> %w, <vscale x 1 x i1> %m, i32 %evl)
ret double %r
}
Reference in new issue View Git Blame Copy Permalink