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
592 lines
22 KiB
LLVM
592 lines
22 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -mattr=+v,+d -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV32
|
|
; RUN: llc -mtriple=riscv64 -mattr=+v,+d -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64
|
|
; RUN: llc -mtriple=riscv32 -mattr=+v,+d,+experimental-zvabd -verify-machineinstrs < %s | FileCheck %s --check-prefixes=ZVABD,ZVABD-RV32
|
|
; RUN: llc -mtriple=riscv64 -mattr=+v,+d,+experimental-zvabd -verify-machineinstrs < %s | FileCheck %s --check-prefixes=ZVABD,ZVABD-RV64
|
|
|
|
;
|
|
; SABD
|
|
;
|
|
|
|
define <vscale x 16 x i8> @sabd_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
|
|
; CHECK-LABEL: sabd_b:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; CHECK-NEXT: vmin.vv v12, v8, v10
|
|
; CHECK-NEXT: vmax.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_b:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; ZVABD-NEXT: vabd.vv v8, v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 16 x i8> %a to <vscale x 16 x i16>
|
|
%b.sext = sext <vscale x 16 x i8> %b to <vscale x 16 x i16>
|
|
%sub = sub <vscale x 16 x i16> %a.sext, %b.sext
|
|
%abs = call <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16> %sub, i1 true)
|
|
%trunc = trunc <vscale x 16 x i16> %abs to <vscale x 16 x i8>
|
|
ret <vscale x 16 x i8> %trunc
|
|
}
|
|
|
|
define <vscale x 16 x i8> @sabd_b_promoted_ops(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: sabd_b_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; CHECK-NEXT: vmxor.mm v0, v0, v8
|
|
; CHECK-NEXT: vmv.v.i v8, 0
|
|
; CHECK-NEXT: vmerge.vim v8, v8, 1, v0
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_b_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; ZVABD-NEXT: vmxor.mm v0, v0, v8
|
|
; ZVABD-NEXT: vmv.v.i v8, 0
|
|
; ZVABD-NEXT: vmerge.vim v8, v8, 1, v0
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 16 x i1> %a to <vscale x 16 x i8>
|
|
%b.sext = sext <vscale x 16 x i1> %b to <vscale x 16 x i8>
|
|
%sub = sub <vscale x 16 x i8> %a.sext, %b.sext
|
|
%abs = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> %sub, i1 true)
|
|
ret <vscale x 16 x i8> %abs
|
|
}
|
|
|
|
define <vscale x 8 x i16> @sabd_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
|
|
; CHECK-LABEL: sabd_h:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vmin.vv v12, v8, v10
|
|
; CHECK-NEXT: vmax.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_h:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m2, ta, ma
|
|
; ZVABD-NEXT: vabd.vv v8, v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 8 x i16> %a to <vscale x 8 x i32>
|
|
%b.sext = sext <vscale x 8 x i16> %b to <vscale x 8 x i32>
|
|
%sub = sub <vscale x 8 x i32> %a.sext, %b.sext
|
|
%abs = call <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32> %sub, i1 true)
|
|
%trunc = trunc <vscale x 8 x i32> %abs to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %trunc
|
|
}
|
|
|
|
define <vscale x 8 x i16> @sabd_h_promoted_ops(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b) {
|
|
; CHECK-LABEL: sabd_h_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vmin.vv v10, v8, v9
|
|
; CHECK-NEXT: vmax.vv v8, v8, v9
|
|
; CHECK-NEXT: vsub.vv v10, v8, v10
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_h_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; ZVABD-NEXT: vabd.vv v10, v8, v9
|
|
; ZVABD-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
%b.sext = sext <vscale x 8 x i8> %b to <vscale x 8 x i16>
|
|
%sub = sub <vscale x 8 x i16> %a.sext, %b.sext
|
|
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
|
|
ret <vscale x 8 x i16> %abs
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sabd_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
|
|
; CHECK-LABEL: sabd_s:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vmin.vv v12, v8, v10
|
|
; CHECK-NEXT: vmax.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_s:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vmin.vv v12, v8, v10
|
|
; ZVABD-NEXT: vmax.vv v8, v8, v10
|
|
; ZVABD-NEXT: vsub.vv v8, v8, v12
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 4 x i32> %a to <vscale x 4 x i64>
|
|
%b.sext = sext <vscale x 4 x i32> %b to <vscale x 4 x i64>
|
|
%sub = sub <vscale x 4 x i64> %a.sext, %b.sext
|
|
%abs = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> %sub, i1 true)
|
|
%trunc = trunc <vscale x 4 x i64> %abs to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %trunc
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sabd_s_promoted_ops(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b) {
|
|
; CHECK-LABEL: sabd_s_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma
|
|
; CHECK-NEXT: vmin.vv v10, v8, v9
|
|
; CHECK-NEXT: vmax.vv v8, v8, v9
|
|
; CHECK-NEXT: vsub.vv v10, v8, v10
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_s_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m1, ta, ma
|
|
; ZVABD-NEXT: vabd.vv v10, v8, v9
|
|
; ZVABD-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 4 x i16> %a to <vscale x 4 x i32>
|
|
%b.sext = sext <vscale x 4 x i16> %b to <vscale x 4 x i32>
|
|
%sub = sub <vscale x 4 x i32> %a.sext, %b.sext
|
|
%abs = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %sub, i1 true)
|
|
ret <vscale x 4 x i32> %abs
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sabd_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
|
|
; CHECK-LABEL: sabd_d:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma
|
|
; CHECK-NEXT: vmin.vv v12, v8, v10
|
|
; CHECK-NEXT: vmax.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_d:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e64, m2, ta, ma
|
|
; ZVABD-NEXT: vmin.vv v12, v8, v10
|
|
; ZVABD-NEXT: vmax.vv v8, v8, v10
|
|
; ZVABD-NEXT: vsub.vv v8, v8, v12
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 2 x i64> %a to <vscale x 2 x i128>
|
|
%b.sext = sext <vscale x 2 x i64> %b to <vscale x 2 x i128>
|
|
%sub = sub <vscale x 2 x i128> %a.sext, %b.sext
|
|
%abs = call <vscale x 2 x i128> @llvm.abs.nxv2i128(<vscale x 2 x i128> %sub, i1 true)
|
|
%trunc = trunc <vscale x 2 x i128> %abs to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %trunc
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sabd_d_promoted_ops(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b) {
|
|
; CHECK-LABEL: sabd_d_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
|
|
; CHECK-NEXT: vmin.vv v10, v8, v9
|
|
; CHECK-NEXT: vmax.vv v8, v8, v9
|
|
; CHECK-NEXT: vsub.vv v10, v8, v10
|
|
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: sabd_d_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e32, m1, ta, ma
|
|
; ZVABD-NEXT: vmin.vv v10, v8, v9
|
|
; ZVABD-NEXT: vmax.vv v8, v8, v9
|
|
; ZVABD-NEXT: vsub.vv v10, v8, v10
|
|
; ZVABD-NEXT: vsetvli zero, zero, e64, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 2 x i32> %a to <vscale x 2 x i64>
|
|
%b.sext = sext <vscale x 2 x i32> %b to <vscale x 2 x i64>
|
|
%sub = sub <vscale x 2 x i64> %a.sext, %b.sext
|
|
%abs = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> %sub, i1 true)
|
|
ret <vscale x 2 x i64> %abs
|
|
}
|
|
|
|
;
|
|
; UABD
|
|
;
|
|
|
|
define <vscale x 16 x i8> @uabd_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
|
|
; CHECK-LABEL: uabd_b:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; CHECK-NEXT: vminu.vv v12, v8, v10
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_b:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; ZVABD-NEXT: vabdu.vv v8, v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 16 x i8> %a to <vscale x 16 x i16>
|
|
%b.zext = zext <vscale x 16 x i8> %b to <vscale x 16 x i16>
|
|
%sub = sub <vscale x 16 x i16> %a.zext, %b.zext
|
|
%abs = call <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16> %sub, i1 true)
|
|
%trunc = trunc <vscale x 16 x i16> %abs to <vscale x 16 x i8>
|
|
ret <vscale x 16 x i8> %trunc
|
|
}
|
|
|
|
define <vscale x 16 x i8> @uabd_b_promoted_ops(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: uabd_b_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; CHECK-NEXT: vmxor.mm v0, v0, v8
|
|
; CHECK-NEXT: vmv.v.i v8, 0
|
|
; CHECK-NEXT: vmerge.vim v8, v8, 1, v0
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_b_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m2, ta, ma
|
|
; ZVABD-NEXT: vmxor.mm v0, v0, v8
|
|
; ZVABD-NEXT: vmv.v.i v8, 0
|
|
; ZVABD-NEXT: vmerge.vim v8, v8, 1, v0
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 16 x i1> %a to <vscale x 16 x i8>
|
|
%b.zext = zext <vscale x 16 x i1> %b to <vscale x 16 x i8>
|
|
%sub = sub <vscale x 16 x i8> %a.zext, %b.zext
|
|
%abs = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> %sub, i1 true)
|
|
ret <vscale x 16 x i8> %abs
|
|
}
|
|
|
|
define <vscale x 8 x i16> @uabd_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
|
|
; CHECK-LABEL: uabd_h:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vminu.vv v12, v8, v10
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_h:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m2, ta, ma
|
|
; ZVABD-NEXT: vabdu.vv v8, v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 8 x i16> %a to <vscale x 8 x i32>
|
|
%b.zext = zext <vscale x 8 x i16> %b to <vscale x 8 x i32>
|
|
%sub = sub <vscale x 8 x i32> %a.zext, %b.zext
|
|
%abs = call <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32> %sub, i1 true)
|
|
%trunc = trunc <vscale x 8 x i32> %abs to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %trunc
|
|
}
|
|
|
|
define <vscale x 8 x i16> @uabd_h_promoted_ops(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b) {
|
|
; CHECK-LABEL: uabd_h_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vminu.vv v10, v8, v9
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v9
|
|
; CHECK-NEXT: vsub.vv v10, v8, v10
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_h_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; ZVABD-NEXT: vabdu.vv v10, v8, v9
|
|
; ZVABD-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
%b.zext = zext <vscale x 8 x i8> %b to <vscale x 8 x i16>
|
|
%sub = sub <vscale x 8 x i16> %a.zext, %b.zext
|
|
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
|
|
ret <vscale x 8 x i16> %abs
|
|
}
|
|
|
|
define <vscale x 4 x i32> @uabd_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
|
|
; CHECK-LABEL: uabd_s:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vminu.vv v12, v8, v10
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_s:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vminu.vv v12, v8, v10
|
|
; ZVABD-NEXT: vmaxu.vv v8, v8, v10
|
|
; ZVABD-NEXT: vsub.vv v8, v8, v12
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 4 x i32> %a to <vscale x 4 x i64>
|
|
%b.zext = zext <vscale x 4 x i32> %b to <vscale x 4 x i64>
|
|
%sub = sub <vscale x 4 x i64> %a.zext, %b.zext
|
|
%abs = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> %sub, i1 true)
|
|
%trunc = trunc <vscale x 4 x i64> %abs to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %trunc
|
|
}
|
|
|
|
define <vscale x 4 x i32> @uabd_s_promoted_ops(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b) {
|
|
; CHECK-LABEL: uabd_s_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma
|
|
; CHECK-NEXT: vminu.vv v10, v8, v9
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v9
|
|
; CHECK-NEXT: vsub.vv v10, v8, v10
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_s_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m1, ta, ma
|
|
; ZVABD-NEXT: vabdu.vv v10, v8, v9
|
|
; ZVABD-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 4 x i16> %a to <vscale x 4 x i32>
|
|
%b.zext = zext <vscale x 4 x i16> %b to <vscale x 4 x i32>
|
|
%sub = sub <vscale x 4 x i32> %a.zext, %b.zext
|
|
%abs = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %sub, i1 true)
|
|
ret <vscale x 4 x i32> %abs
|
|
}
|
|
|
|
define <vscale x 2 x i64> @uabd_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
|
|
; CHECK-LABEL: uabd_d:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma
|
|
; CHECK-NEXT: vminu.vv v12, v8, v10
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v10
|
|
; CHECK-NEXT: vsub.vv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_d:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e64, m2, ta, ma
|
|
; ZVABD-NEXT: vminu.vv v12, v8, v10
|
|
; ZVABD-NEXT: vmaxu.vv v8, v8, v10
|
|
; ZVABD-NEXT: vsub.vv v8, v8, v12
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 2 x i64> %a to <vscale x 2 x i128>
|
|
%b.zext = zext <vscale x 2 x i64> %b to <vscale x 2 x i128>
|
|
%sub = sub <vscale x 2 x i128> %a.zext, %b.zext
|
|
%abs = call <vscale x 2 x i128> @llvm.abs.nxv2i128(<vscale x 2 x i128> %sub, i1 true)
|
|
%trunc = trunc <vscale x 2 x i128> %abs to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %trunc
|
|
}
|
|
|
|
define <vscale x 2 x i64> @uabd_d_promoted_ops(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b) {
|
|
; CHECK-LABEL: uabd_d_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
|
|
; CHECK-NEXT: vminu.vv v10, v8, v9
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v9
|
|
; CHECK-NEXT: vsub.vv v10, v8, v10
|
|
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_d_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e32, m1, ta, ma
|
|
; ZVABD-NEXT: vminu.vv v10, v8, v9
|
|
; ZVABD-NEXT: vmaxu.vv v8, v8, v9
|
|
; ZVABD-NEXT: vsub.vv v10, v8, v10
|
|
; ZVABD-NEXT: vsetvli zero, zero, e64, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 2 x i32> %a to <vscale x 2 x i64>
|
|
%b.zext = zext <vscale x 2 x i32> %b to <vscale x 2 x i64>
|
|
%sub = sub <vscale x 2 x i64> %a.zext, %b.zext
|
|
%abs = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> %sub, i1 true)
|
|
ret <vscale x 2 x i64> %abs
|
|
}
|
|
|
|
; Test the situation where isLegal(ISD::ABD, typeof(%a)) returns true but %a and
|
|
; %b have differing types.
|
|
define <vscale x 4 x i32> @uabd_non_matching_extension(<vscale x 4 x i32> %a, <vscale x 4 x i8> %b) {
|
|
; CHECK-LABEL: uabd_non_matching_extension:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf4 v12, v10
|
|
; CHECK-NEXT: vminu.vv v10, v8, v12
|
|
; CHECK-NEXT: vmaxu.vv v8, v8, v12
|
|
; CHECK-NEXT: vsub.vv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_non_matching_extension:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf4 v12, v10
|
|
; ZVABD-NEXT: vminu.vv v10, v8, v12
|
|
; ZVABD-NEXT: vmaxu.vv v8, v8, v12
|
|
; ZVABD-NEXT: vsub.vv v8, v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 4 x i32> %a to <vscale x 4 x i64>
|
|
%b.zext = zext <vscale x 4 x i8> %b to <vscale x 4 x i64>
|
|
%sub = sub <vscale x 4 x i64> %a.zext, %b.zext
|
|
%abs = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> %sub, i1 true)
|
|
%trunc = trunc <vscale x 4 x i64> %abs to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %trunc
|
|
}
|
|
|
|
; Test the situation where isLegal(ISD::ABD, typeof(%a.zext)) returns true but
|
|
; %a and %b have differing types.
|
|
define <vscale x 4 x i32> @uabd_non_matching_promoted_ops(<vscale x 4 x i8> %a, <vscale x 4 x i16> %b) {
|
|
; CHECK-LABEL: uabd_non_matching_promoted_ops:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v10, v8
|
|
; CHECK-NEXT: vminu.vv v8, v10, v9
|
|
; CHECK-NEXT: vmaxu.vv v9, v10, v9
|
|
; CHECK-NEXT: vsub.vv v10, v9, v8
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_non_matching_promoted_ops:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m1, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v10, v8
|
|
; ZVABD-NEXT: vabdu.vv v10, v10, v9
|
|
; ZVABD-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v8, v10
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 4 x i8> %a to <vscale x 4 x i32>
|
|
%b.zext = zext <vscale x 4 x i16> %b to <vscale x 4 x i32>
|
|
%sub = sub <vscale x 4 x i32> %a.zext, %b.zext
|
|
%abs = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %sub, i1 true)
|
|
ret <vscale x 4 x i32> %abs
|
|
}
|
|
|
|
; Test the situation where isLegal(ISD::ABD, typeof(%a)) returns true but %a and
|
|
; %b are promoted differently.
|
|
define <vscale x 4 x i32> @uabd_non_matching_promotion(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b) {
|
|
; CHECK-LABEL: uabd_non_matching_promotion:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf4 v10, v8
|
|
; CHECK-NEXT: vsext.vf4 v12, v9
|
|
; CHECK-NEXT: vmin.vv v8, v10, v12
|
|
; CHECK-NEXT: vmax.vv v10, v10, v12
|
|
; CHECK-NEXT: vsub.vv v8, v10, v8
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: uabd_non_matching_promotion:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e32, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf4 v10, v8
|
|
; ZVABD-NEXT: vsext.vf4 v12, v9
|
|
; ZVABD-NEXT: vmin.vv v8, v10, v12
|
|
; ZVABD-NEXT: vmax.vv v10, v10, v12
|
|
; ZVABD-NEXT: vsub.vv v8, v10, v8
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 4 x i8> %a to <vscale x 4 x i32>
|
|
%b.zext = sext <vscale x 4 x i8> %b to <vscale x 4 x i32>
|
|
%sub = sub <vscale x 4 x i32> %a.zext, %b.zext
|
|
%abs = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %sub, i1 true)
|
|
ret <vscale x 4 x i32> %abs
|
|
}
|
|
|
|
define <vscale x 8 x i16> @vwabda(<vscale x 8 x i16> %acc, <vscale x 8 x i8> %a, <vscale x 8 x i8> %b) {
|
|
; CHECK-LABEL: vwabda:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vmin.vv v12, v10, v11
|
|
; CHECK-NEXT: vmax.vv v10, v10, v11
|
|
; CHECK-NEXT: vsub.vv v10, v10, v12
|
|
; CHECK-NEXT: vwaddu.wv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: vwabda:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; ZVABD-NEXT: vwabda.vv v8, v10, v11
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
%b.sext = sext <vscale x 8 x i8> %b to <vscale x 8 x i16>
|
|
%sub = sub <vscale x 8 x i16> %a.sext, %b.sext
|
|
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
|
|
%ret = add <vscale x 8 x i16> %acc, %abs
|
|
ret <vscale x 8 x i16> %ret
|
|
}
|
|
|
|
define <vscale x 8 x i16> @vwabdau(<vscale x 8 x i16> %acc, <vscale x 8 x i8> %a, <vscale x 8 x i8> %b) {
|
|
; CHECK-LABEL: vwabdau:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vminu.vv v12, v10, v11
|
|
; CHECK-NEXT: vmaxu.vv v10, v10, v11
|
|
; CHECK-NEXT: vsub.vv v10, v10, v12
|
|
; CHECK-NEXT: vwaddu.wv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: vwabdau:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; ZVABD-NEXT: vwabdau.vv v8, v10, v11
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
%b.zext = zext <vscale x 8 x i8> %b to <vscale x 8 x i16>
|
|
%sub = sub <vscale x 8 x i16> %a.zext, %b.zext
|
|
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
|
|
%ret = add <vscale x 8 x i16> %acc, %abs
|
|
ret <vscale x 8 x i16> %ret
|
|
}
|
|
|
|
define <vscale x 8 x i32> @vwabda_sext_diff(<vscale x 8 x i32> %acc, <vscale x 8 x i8> %a, <vscale x 8 x i8> %b) {
|
|
; CHECK-LABEL: vwabda_sext_diff:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vmin.vv v14, v12, v13
|
|
; CHECK-NEXT: vmax.vv v12, v12, v13
|
|
; CHECK-NEXT: vsub.vv v14, v12, v14
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v12, v14
|
|
; CHECK-NEXT: vwaddu.wv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: vwabda_sext_diff:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m2, ta, ma
|
|
; ZVABD-NEXT: vsext.vf2 v14, v13
|
|
; ZVABD-NEXT: vsext.vf2 v16, v12
|
|
; ZVABD-NEXT: vwabda.vv v8, v16, v14
|
|
; ZVABD-NEXT: ret
|
|
%a.sext = sext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
%b.sext = sext <vscale x 8 x i8> %b to <vscale x 8 x i16>
|
|
%sub = sub <vscale x 8 x i16> %a.sext, %b.sext
|
|
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
|
|
%abs.zext = zext <vscale x 8 x i16> %abs to <vscale x 8 x i32>
|
|
%ret = add <vscale x 8 x i32> %acc, %abs.zext
|
|
ret <vscale x 8 x i32> %ret
|
|
}
|
|
|
|
define <vscale x 8 x i32> @vwabdau_zext_diff(<vscale x 8 x i32> %acc, <vscale x 8 x i8> %a, <vscale x 8 x i8> %b) {
|
|
; CHECK-LABEL: vwabdau_zext_diff:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vminu.vv v14, v12, v13
|
|
; CHECK-NEXT: vmaxu.vv v12, v12, v13
|
|
; CHECK-NEXT: vsub.vv v14, v12, v14
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vzext.vf2 v12, v14
|
|
; CHECK-NEXT: vwaddu.wv v8, v8, v12
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; ZVABD-LABEL: vwabdau_zext_diff:
|
|
; ZVABD: # %bb.0:
|
|
; ZVABD-NEXT: vsetvli a0, zero, e16, m2, ta, ma
|
|
; ZVABD-NEXT: vzext.vf2 v14, v13
|
|
; ZVABD-NEXT: vzext.vf2 v16, v12
|
|
; ZVABD-NEXT: vwabdau.vv v8, v16, v14
|
|
; ZVABD-NEXT: ret
|
|
%a.zext = zext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
%b.zext = zext <vscale x 8 x i8> %b to <vscale x 8 x i16>
|
|
%sub = sub <vscale x 8 x i16> %a.zext, %b.zext
|
|
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
|
|
%abs.zext = zext <vscale x 8 x i16> %abs to <vscale x 8 x i32>
|
|
%ret = add <vscale x 8 x i32> %acc, %abs.zext
|
|
ret <vscale x 8 x i32> %ret
|
|
}
|
|
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; RV32: {{.*}}
|
|
; RV64: {{.*}}
|
|
; ZVABD-RV32: {{.*}}
|
|
; ZVABD-RV64: {{.*}}
|