blob: 92092a704933a74776b7eec342df4caec9a8e3d2 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx74| FileCheck --check-prefixes=CHECK-PTX64 %s
; RUN: %if ptxas-sm_80 && ptxas-isa-7.4 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx74| %ptxas-verify -arch=sm_80 %}
target triple = "nvptx64-nvidia-cuda"
declare void @llvm.nvvm.applypriority.global.L2.evict.normal(ptr addrspace(1) %global_ptr, i64 %size)
declare void @llvm.nvvm.applypriority.L2.evict.normal(ptr %ptr, i64 %size)
define void @applypriority_global_L2(ptr addrspace(1) %global_ptr, i64 %size) {
; CHECK-PTX64-LABEL: applypriority_global_L2(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b64 %rd<2>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [applypriority_global_L2_param_0];
; CHECK-PTX64-NEXT: applypriority.global.L2::evict_normal [%rd1], 128;
; CHECK-PTX64-NEXT: ret;
tail call void @llvm.nvvm.applypriority.global.L2.evict.normal(ptr addrspace(1) %global_ptr, i64 128)
ret void
}
define void @applypriority_L2(ptr %ptr, i64 %size) {
; CHECK-PTX64-LABEL: applypriority_L2(
; CHECK-PTX64: {
; CHECK-PTX64-NEXT: .reg .b64 %rd<2>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT: // %bb.0:
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [applypriority_L2_param_0];
; CHECK-PTX64-NEXT: applypriority.L2::evict_normal [%rd1], 128;
; CHECK-PTX64-NEXT: ret;
tail call void @llvm.nvvm.applypriority.L2.evict.normal(ptr %ptr, i64 128)
ret void
}
|
