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/NVPTX/cp-async-bulk-tensor-s2g.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

229 lines
17 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80| FileCheck --check-prefixes=CHECK-PTX64 %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| FileCheck --check-prefixes=CHECK-PTX-SHARED32 %s
; RUN: %if ptxas-sm_90 && ptxas-isa-8.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80| %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-8.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| %ptxas-verify -arch=sm_90 %}
target triple = "nvptx64-nvidia-cuda"
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.1d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.2d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.3d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.4d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.5d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.3d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.4d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch, i1 %flag);
declare void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.5d(ptr addrspace(3) %s, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch, i1 %flag);
; CHECK-LABEL: cp_async_bulk_tensor_s2g_tile_1d
define void @cp_async_bulk_tensor_s2g_tile_1d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_s2g_tile_1d(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b32 %r<2>;
; CHECK-PTX64-NEXT: .reg .b64 %rd<4>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_tile_1d_param_0];
; CHECK-PTX64-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_tile_1d_param_1];
; CHECK-PTX64-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_tile_1d_param_2];
; CHECK-PTX64-NEXT: ld.param.b64 %rd3, [cp_async_bulk_tensor_s2g_tile_1d_param_3];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.1d.global.shared::cta.tile.bulk_group [%rd2, {%r1}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.1d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd2, {%r1}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_s2g_tile_1d(
; CHECK-PTX-SHARED32: {
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<3>;
; CHECK-PTX-SHARED32-NEXT: .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_tile_1d_param_0];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_tile_1d_param_1];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_tile_1d_param_2];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_tile_1d_param_3];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.1d.global.shared::cta.tile.bulk_group [%rd1, {%r2}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.1d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd1, {%r2}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: ret;
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.1d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.1d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i64 %ch, i1 1)
ret void
}
; CHECK-LABEL: cp_async_bulk_tensor_s2g_tile_2d
define void @cp_async_bulk_tensor_s2g_tile_2d(i32 %flag, ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_s2g_tile_2d(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b32 %r<3>;
; CHECK-PTX64-NEXT: .reg .b64 %rd<4>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_tile_2d_param_1];
; CHECK-PTX64-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_tile_2d_param_2];
; CHECK-PTX64-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_tile_2d_param_3];
; CHECK-PTX64-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_tile_2d_param_4];
; CHECK-PTX64-NEXT: ld.param.b64 %rd3, [cp_async_bulk_tensor_s2g_tile_2d_param_5];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.2d.global.shared::cta.tile.bulk_group [%rd2, {%r1, %r2}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.2d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd2, {%r1, %r2}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_s2g_tile_2d(
; CHECK-PTX-SHARED32: {
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<4>;
; CHECK-PTX-SHARED32-NEXT: .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_tile_2d_param_1];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_tile_2d_param_2];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_tile_2d_param_3];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_tile_2d_param_4];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_tile_2d_param_5];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.2d.global.shared::cta.tile.bulk_group [%rd1, {%r2, %r3}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.2d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd1, {%r2, %r3}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: ret;
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.2d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.2d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i64 %ch, i1 1)
ret void
}
; CHECK-LABEL: cp_async_bulk_tensor_s2g_3d
define void @cp_async_bulk_tensor_s2g_3d(i32 %flag, ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_s2g_3d(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b32 %r<4>;
; CHECK-PTX64-NEXT: .reg .b64 %rd<4>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_3d_param_1];
; CHECK-PTX64-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_3d_param_2];
; CHECK-PTX64-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_3d_param_3];
; CHECK-PTX64-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_3d_param_4];
; CHECK-PTX64-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_3d_param_5];
; CHECK-PTX64-NEXT: ld.param.b64 %rd3, [cp_async_bulk_tensor_s2g_3d_param_6];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.tile.bulk_group [%rd2, {%r1, %r2, %r3}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd2, {%r1, %r2, %r3}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.im2col_no_offs.bulk_group [%rd2, {%r1, %r2, %r3}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.im2col_no_offs.bulk_group.L2::cache_hint [%rd2, {%r1, %r2, %r3}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_s2g_3d(
; CHECK-PTX-SHARED32: {
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<5>;
; CHECK-PTX-SHARED32-NEXT: .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_3d_param_1];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_3d_param_2];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_3d_param_3];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_3d_param_4];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r4, [cp_async_bulk_tensor_s2g_3d_param_5];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_3d_param_6];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.tile.bulk_group [%rd1, {%r2, %r3, %r4}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd1, {%r2, %r3, %r4}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.im2col_no_offs.bulk_group [%rd1, {%r2, %r3, %r4}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.3d.global.shared::cta.im2col_no_offs.bulk_group.L2::cache_hint [%rd1, {%r2, %r3, %r4}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: ret;
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.3d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.3d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i64 %ch, i1 1)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.3d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.3d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i64 %ch, i1 1)
ret void
}
; CHECK-LABEL: cp_async_bulk_tensor_s2g_4d
define void @cp_async_bulk_tensor_s2g_4d(i32 %flag, ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_s2g_4d(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b32 %r<5>;
; CHECK-PTX64-NEXT: .reg .b64 %rd<4>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_4d_param_1];
; CHECK-PTX64-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_4d_param_2];
; CHECK-PTX64-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_4d_param_3];
; CHECK-PTX64-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_4d_param_4];
; CHECK-PTX64-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_4d_param_5];
; CHECK-PTX64-NEXT: ld.param.b32 %r4, [cp_async_bulk_tensor_s2g_4d_param_6];
; CHECK-PTX64-NEXT: ld.param.b64 %rd3, [cp_async_bulk_tensor_s2g_4d_param_7];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.tile.bulk_group [%rd2, {%r1, %r2, %r3, %r4}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd2, {%r1, %r2, %r3, %r4}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.im2col_no_offs.bulk_group [%rd2, {%r1, %r2, %r3, %r4}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.im2col_no_offs.bulk_group.L2::cache_hint [%rd2, {%r1, %r2, %r3, %r4}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_s2g_4d(
; CHECK-PTX-SHARED32: {
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<6>;
; CHECK-PTX-SHARED32-NEXT: .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_4d_param_1];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_4d_param_2];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_4d_param_3];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_4d_param_4];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r4, [cp_async_bulk_tensor_s2g_4d_param_5];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r5, [cp_async_bulk_tensor_s2g_4d_param_6];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_4d_param_7];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.tile.bulk_group [%rd1, {%r2, %r3, %r4, %r5}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd1, {%r2, %r3, %r4, %r5}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.im2col_no_offs.bulk_group [%rd1, {%r2, %r3, %r4, %r5}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.4d.global.shared::cta.im2col_no_offs.bulk_group.L2::cache_hint [%rd1, {%r2, %r3, %r4, %r5}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: ret;
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.4d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.4d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch, i1 1)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.4d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.4d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i64 %ch, i1 1)
ret void
}
; CHECK-LABEL: cp_async_bulk_tensor_s2g_5d
define void @cp_async_bulk_tensor_s2g_5d(i32 %flag, ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_s2g_5d(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b32 %r<6>;
; CHECK-PTX64-NEXT: .reg .b64 %rd<4>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_5d_param_1];
; CHECK-PTX64-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_5d_param_2];
; CHECK-PTX64-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_5d_param_3];
; CHECK-PTX64-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_5d_param_4];
; CHECK-PTX64-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_5d_param_5];
; CHECK-PTX64-NEXT: ld.param.b32 %r4, [cp_async_bulk_tensor_s2g_5d_param_6];
; CHECK-PTX64-NEXT: ld.param.b32 %r5, [cp_async_bulk_tensor_s2g_5d_param_7];
; CHECK-PTX64-NEXT: ld.param.b64 %rd3, [cp_async_bulk_tensor_s2g_5d_param_8];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.tile.bulk_group [%rd2, {%r1, %r2, %r3, %r4, %r5}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd2, {%r1, %r2, %r3, %r4, %r5}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.im2col_no_offs.bulk_group [%rd2, {%r1, %r2, %r3, %r4, %r5}], [%rd1];
; CHECK-PTX64-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.im2col_no_offs.bulk_group.L2::cache_hint [%rd2, {%r1, %r2, %r3, %r4, %r5}], [%rd1], %rd3;
; CHECK-PTX64-NEXT: ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_s2g_5d(
; CHECK-PTX-SHARED32: {
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<7>;
; CHECK-PTX-SHARED32-NEXT: .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [cp_async_bulk_tensor_s2g_5d_param_1];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd1, [cp_async_bulk_tensor_s2g_5d_param_2];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r2, [cp_async_bulk_tensor_s2g_5d_param_3];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r3, [cp_async_bulk_tensor_s2g_5d_param_4];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r4, [cp_async_bulk_tensor_s2g_5d_param_5];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r5, [cp_async_bulk_tensor_s2g_5d_param_6];
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r6, [cp_async_bulk_tensor_s2g_5d_param_7];
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd2, [cp_async_bulk_tensor_s2g_5d_param_8];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.tile.bulk_group [%rd1, {%r2, %r3, %r4, %r5, %r6}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.tile.bulk_group.L2::cache_hint [%rd1, {%r2, %r3, %r4, %r5, %r6}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.im2col_no_offs.bulk_group [%rd1, {%r2, %r3, %r4, %r5, %r6}], [%r1];
; CHECK-PTX-SHARED32-NEXT: cp.async.bulk.tensor.5d.global.shared::cta.im2col_no_offs.bulk_group.L2::cache_hint [%rd1, {%r2, %r3, %r4, %r5, %r6}], [%r1], %rd2;
; CHECK-PTX-SHARED32-NEXT: ret;
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.5d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.tile.5d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch, i1 1)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.5d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch, i1 0)
tail call void @llvm.nvvm.cp.async.bulk.tensor.s2g.im2col.5d(ptr addrspace(3) %src, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i64 %ch, i1 1)
ret void
}
Reference in new issue View Git Blame Copy Permalink