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
70 lines
2.6 KiB
LLVM
70 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_53 -mattr=+ptx42 | FileCheck %s
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_53 -mattr=+ptx60 | FileCheck %s
|
|
; RUN: %if ptxas-isa-4.2 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_53 -mattr=+ptx42 | %ptxas-verify%}
|
|
; RUN: %if ptxas-isa-6.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_53 -mattr=+ptx60 | %ptxas-verify%}
|
|
|
|
define half @sub_rn_sat_f16(half %a, half %b) {
|
|
; CHECK-LABEL: sub_rn_sat_f16(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b16 %rs<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b16 %rs1, [sub_rn_sat_f16_param_0];
|
|
; CHECK-NEXT: ld.param.b16 %rs2, [sub_rn_sat_f16_param_1];
|
|
; CHECK-NEXT: sub.rn.sat.f16 %rs3, %rs1, %rs2;
|
|
; CHECK-NEXT: st.param.b16 [func_retval0], %rs3;
|
|
; CHECK-NEXT: ret;
|
|
%1 = fneg half %b
|
|
%res = call half @llvm.nvvm.add.rn.sat.f16(half %a, half %1)
|
|
ret half %res
|
|
}
|
|
|
|
define <2 x half> @sub_rn_sat_f16x2(<2 x half> %a, <2 x half> %b) {
|
|
; CHECK-LABEL: sub_rn_sat_f16x2(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b32 %r1, [sub_rn_sat_f16x2_param_0];
|
|
; CHECK-NEXT: ld.param.b32 %r2, [sub_rn_sat_f16x2_param_1];
|
|
; CHECK-NEXT: sub.rn.sat.f16x2 %r3, %r1, %r2;
|
|
; CHECK-NEXT: st.param.b32 [func_retval0], %r3;
|
|
; CHECK-NEXT: ret;
|
|
%1 = fneg <2 x half> %b
|
|
%res = call <2 x half> @llvm.nvvm.add.rn.sat.v2f16(<2 x half> %a, <2 x half> %1)
|
|
ret <2 x half> %res
|
|
}
|
|
|
|
define half @sub_rn_ftz_sat_f16(half %a, half %b) {
|
|
; CHECK-LABEL: sub_rn_ftz_sat_f16(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b16 %rs<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b16 %rs1, [sub_rn_ftz_sat_f16_param_0];
|
|
; CHECK-NEXT: ld.param.b16 %rs2, [sub_rn_ftz_sat_f16_param_1];
|
|
; CHECK-NEXT: sub.rn.ftz.sat.f16 %rs3, %rs1, %rs2;
|
|
; CHECK-NEXT: st.param.b16 [func_retval0], %rs3;
|
|
; CHECK-NEXT: ret;
|
|
%1 = fneg half %b
|
|
%res = call half @llvm.nvvm.add.rn.ftz.sat.f16(half %a, half %1)
|
|
ret half %res
|
|
}
|
|
|
|
define <2 x half> @sub_rn_ftz_sat_f16x2(<2 x half> %a, <2 x half> %b) {
|
|
; CHECK-LABEL: sub_rn_ftz_sat_f16x2(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b32 %r1, [sub_rn_ftz_sat_f16x2_param_0];
|
|
; CHECK-NEXT: ld.param.b32 %r2, [sub_rn_ftz_sat_f16x2_param_1];
|
|
; CHECK-NEXT: sub.rn.ftz.sat.f16x2 %r3, %r1, %r2;
|
|
; CHECK-NEXT: st.param.b32 [func_retval0], %r3;
|
|
; CHECK-NEXT: ret;
|
|
%1 = fneg <2 x half> %b
|
|
%res = call <2 x half> @llvm.nvvm.add.rn.ftz.sat.v2f16(<2 x half> %a, <2 x half> %1)
|
|
ret <2 x half> %res
|
|
}
|