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
316 lines
11 KiB
LLVM
316 lines
11 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc --mtriple=riscv64-linux-gnu --mattr=+v,+zvfh,+zvfbfmin < %s | FileCheck %s --check-prefixes=CHECK,ZVFBFMIN,ZVFH
|
|
; RUN: llc --mtriple=riscv64-linux-gnu --mattr=+v,+zvfhmin,+zfh,+zvfbfmin < %s | FileCheck %s --check-prefixes=CHECK,ZVFBFMIN,ZVFHMIN
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfhmin,+experimental-zvfbfa,+v \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN,ZVFBFA
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfhmin,+experimental-zvfbfa,+v \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN,ZVFBFA
|
|
|
|
define <2 x double> @max_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: max_v2f64:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v9
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <2 x double> @llvm.maximumnum.v2f64(<2 x double> %a, <2 x double> %b)
|
|
ret <2 x double> %c
|
|
}
|
|
|
|
define <3 x double> @max_v3f64(<3 x double> %a, <3 x double> %b) {
|
|
; CHECK-LABEL: max_v3f64:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <3 x double> @llvm.maximumnum.v3f64(<3 x double> %a, <3 x double> %b)
|
|
ret <3 x double> %c
|
|
}
|
|
|
|
define <4 x double> @max_v4f64(<4 x double> %a, <4 x double> %b) {
|
|
; CHECK-LABEL: max_v4f64:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <4 x double> @llvm.maximumnum.v4f64(<4 x double> %a, <4 x double> %b)
|
|
ret <4 x double> %c
|
|
}
|
|
|
|
define <2 x float> @max_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: max_v2f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v9
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> %a, <2 x float> %b)
|
|
ret <2 x float> %c
|
|
}
|
|
|
|
define <3 x float> @max_v3f32(<3 x float> %a, <3 x float> %b) {
|
|
; CHECK-LABEL: max_v3f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v9
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <3 x float> @llvm.maximumnum.v3f32(<3 x float> %a, <3 x float> %b)
|
|
ret <3 x float> %c
|
|
}
|
|
|
|
define <4 x float> @max_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: max_v4f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v9
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> %a, <4 x float> %b)
|
|
ret <4 x float> %c
|
|
}
|
|
|
|
define <5 x float> @max_v5f32(<5 x float> %a, <5 x float> %b) {
|
|
; CHECK-LABEL: max_v5f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <5 x float> @llvm.maximumnum.v5f32(<5 x float> %a, <5 x float> %b)
|
|
ret <5 x float> %c
|
|
}
|
|
|
|
define <8 x float> @max_v8f32(<8 x float> %a, <8 x float> %b) {
|
|
; CHECK-LABEL: max_v8f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
|
|
; CHECK-NEXT: vfmax.vv v8, v8, v10
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%c = call <8 x float> @llvm.maximumnum.v8f32(<8 x float> %a, <8 x float> %b)
|
|
ret <8 x float> %c
|
|
}
|
|
|
|
define <2 x half> @max_v2f16(<2 x half> %a, <2 x half> %b) {
|
|
; ZVFH-LABEL: max_v2f16:
|
|
; ZVFH: # %bb.0: # %entry
|
|
; ZVFH-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; ZVFH-NEXT: vfmax.vv v8, v8, v9
|
|
; ZVFH-NEXT: ret
|
|
;
|
|
; ZVFHMIN-LABEL: max_v2f16:
|
|
; ZVFHMIN: # %bb.0: # %entry
|
|
; ZVFHMIN-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
|
|
; ZVFHMIN-NEXT: vfmax.vv v9, v9, v10
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
|
|
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
|
|
; ZVFHMIN-NEXT: ret
|
|
entry:
|
|
%c = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> %a, <2 x half> %b)
|
|
ret <2 x half> %c
|
|
}
|
|
|
|
define <4 x half> @max_v4f16(<4 x half> %a, <4 x half> %b) {
|
|
; ZVFH-LABEL: max_v4f16:
|
|
; ZVFH: # %bb.0: # %entry
|
|
; ZVFH-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
|
|
; ZVFH-NEXT: vfmax.vv v8, v8, v9
|
|
; ZVFH-NEXT: ret
|
|
;
|
|
; ZVFHMIN-LABEL: max_v4f16:
|
|
; ZVFHMIN: # %bb.0: # %entry
|
|
; ZVFHMIN-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
|
|
; ZVFHMIN-NEXT: vfmax.vv v9, v9, v10
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
|
|
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
|
|
; ZVFHMIN-NEXT: ret
|
|
entry:
|
|
%c = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> %a, <4 x half> %b)
|
|
ret <4 x half> %c
|
|
}
|
|
|
|
define <8 x half> @max_v8f16(<8 x half> %a, <8 x half> %b) {
|
|
; ZVFH-LABEL: max_v8f16:
|
|
; ZVFH: # %bb.0: # %entry
|
|
; ZVFH-NEXT: vsetivli zero, 8, e16, m1, ta, ma
|
|
; ZVFH-NEXT: vfmax.vv v8, v8, v9
|
|
; ZVFH-NEXT: ret
|
|
;
|
|
; ZVFHMIN-LABEL: max_v8f16:
|
|
; ZVFHMIN: # %bb.0: # %entry
|
|
; ZVFHMIN-NEXT: vsetivli zero, 8, e16, m1, ta, ma
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v8
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; ZVFHMIN-NEXT: vfmax.vv v10, v12, v10
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m1, ta, ma
|
|
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10
|
|
; ZVFHMIN-NEXT: ret
|
|
entry:
|
|
%c = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> %a, <8 x half> %b)
|
|
ret <8 x half> %c
|
|
}
|
|
|
|
define <9 x half> @max_v9f16(<9 x half> %a, <9 x half> %b) {
|
|
; ZVFH-LABEL: max_v9f16:
|
|
; ZVFH: # %bb.0: # %entry
|
|
; ZVFH-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFH-NEXT: vfmax.vv v8, v8, v10
|
|
; ZVFH-NEXT: ret
|
|
;
|
|
; ZVFHMIN-LABEL: max_v9f16:
|
|
; ZVFHMIN: # %bb.0: # %entry
|
|
; ZVFHMIN-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
|
|
; ZVFHMIN-NEXT: vfmax.vv v12, v16, v12
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
|
|
; ZVFHMIN-NEXT: ret
|
|
entry:
|
|
%c = call <9 x half> @llvm.maximumnum.v9f16(<9 x half> %a, <9 x half> %b)
|
|
ret <9 x half> %c
|
|
}
|
|
|
|
define <16 x half> @max_v16f16(<16 x half> %a, <16 x half> %b) {
|
|
; ZVFH-LABEL: max_v16f16:
|
|
; ZVFH: # %bb.0: # %entry
|
|
; ZVFH-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFH-NEXT: vfmax.vv v8, v8, v10
|
|
; ZVFH-NEXT: ret
|
|
;
|
|
; ZVFHMIN-LABEL: max_v16f16:
|
|
; ZVFHMIN: # %bb.0: # %entry
|
|
; ZVFHMIN-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10
|
|
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
|
|
; ZVFHMIN-NEXT: vfmax.vv v12, v16, v12
|
|
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
|
|
; ZVFHMIN-NEXT: ret
|
|
entry:
|
|
%c = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> %a, <16 x half> %b)
|
|
ret <16 x half> %c
|
|
}
|
|
|
|
define <2 x bfloat> @max_v2bf16(<2 x bfloat> %a, <2 x bfloat> %b) {
|
|
; ZVFBFMIN-LABEL: max_v2bf16:
|
|
; ZVFBFMIN: # %bb.0: # %entry
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v10, v9
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v9, v8
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfmax.vv v9, v9, v10
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
|
|
; ZVFBFMIN-NEXT: vfncvtbf16.f.f.w v8, v9
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: max_v2bf16:
|
|
; ZVFBFA: # %bb.0: # %entry
|
|
; ZVFBFA-NEXT: vsetivli zero, 2, e16alt, mf4, ta, ma
|
|
; ZVFBFA-NEXT: vfmax.vv v8, v8, v9
|
|
; ZVFBFA-NEXT: ret
|
|
entry:
|
|
%c = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> %a, <2 x bfloat> %b)
|
|
ret <2 x bfloat> %c
|
|
}
|
|
|
|
define <4 x bfloat> @max_v4bf16(<4 x bfloat> %a, <4 x bfloat> %b) {
|
|
; ZVFBFMIN-LABEL: max_v4bf16:
|
|
; ZVFBFMIN: # %bb.0: # %entry
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v10, v9
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v9, v8
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
|
|
; ZVFBFMIN-NEXT: vfmax.vv v9, v9, v10
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfncvtbf16.f.f.w v8, v9
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: max_v4bf16:
|
|
; ZVFBFA: # %bb.0: # %entry
|
|
; ZVFBFA-NEXT: vsetivli zero, 4, e16alt, mf2, ta, ma
|
|
; ZVFBFA-NEXT: vfmax.vv v8, v8, v9
|
|
; ZVFBFA-NEXT: ret
|
|
entry:
|
|
%c = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> %a, <4 x bfloat> %b)
|
|
ret <4 x bfloat> %c
|
|
}
|
|
|
|
define <8 x bfloat> @max_v8bf16(<8 x bfloat> %a, <8 x bfloat> %b) {
|
|
; ZVFBFMIN-LABEL: max_v8bf16:
|
|
; ZVFBFMIN: # %bb.0: # %entry
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 8, e16, m1, ta, ma
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v10, v9
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v12, v8
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e32, m2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfmax.vv v10, v12, v10
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e16, m1, ta, ma
|
|
; ZVFBFMIN-NEXT: vfncvtbf16.f.f.w v8, v10
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: max_v8bf16:
|
|
; ZVFBFA: # %bb.0: # %entry
|
|
; ZVFBFA-NEXT: vsetivli zero, 8, e16alt, m1, ta, ma
|
|
; ZVFBFA-NEXT: vfmax.vv v8, v8, v9
|
|
; ZVFBFA-NEXT: ret
|
|
entry:
|
|
%c = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> %a, <8 x bfloat> %b)
|
|
ret <8 x bfloat> %c
|
|
}
|
|
|
|
define <9 x bfloat> @max_v9bf16(<9 x bfloat> %a, <9 x bfloat> %b) {
|
|
; ZVFBFMIN-LABEL: max_v9bf16:
|
|
; ZVFBFMIN: # %bb.0: # %entry
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v12, v10
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v16, v8
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
|
|
; ZVFBFMIN-NEXT: vfmax.vv v12, v16, v12
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfncvtbf16.f.f.w v8, v12
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: max_v9bf16:
|
|
; ZVFBFA: # %bb.0: # %entry
|
|
; ZVFBFA-NEXT: vsetivli zero, 16, e16alt, m2, ta, ma
|
|
; ZVFBFA-NEXT: vfmax.vv v8, v8, v10
|
|
; ZVFBFA-NEXT: ret
|
|
entry:
|
|
%c = call <9 x bfloat> @llvm.maximumnum.v9bf16(<9 x bfloat> %a, <9 x bfloat> %b)
|
|
ret <9 x bfloat> %c
|
|
}
|
|
|
|
define <16 x bfloat> @max_v16bf16(<16 x bfloat> %a, <16 x bfloat> %b) {
|
|
; ZVFBFMIN-LABEL: max_v16bf16:
|
|
; ZVFBFMIN: # %bb.0: # %entry
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v12, v10
|
|
; ZVFBFMIN-NEXT: vfwcvtbf16.f.f.v v16, v8
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
|
|
; ZVFBFMIN-NEXT: vfmax.vv v12, v16, v12
|
|
; ZVFBFMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; ZVFBFMIN-NEXT: vfncvtbf16.f.f.w v8, v12
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: max_v16bf16:
|
|
; ZVFBFA: # %bb.0: # %entry
|
|
; ZVFBFA-NEXT: vsetivli zero, 16, e16alt, m2, ta, ma
|
|
; ZVFBFA-NEXT: vfmax.vv v8, v8, v10
|
|
; ZVFBFA-NEXT: ret
|
|
entry:
|
|
%c = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> %a, <16 x bfloat> %b)
|
|
ret <16 x bfloat> %c
|
|
}
|