shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c
Jameson Nash 0dd21ad1c6
[clang] remove addrspace cast from CreateIRTemp (#179327) 
This just added unnecessary work to the IR, since they are only used for
load and store, which just causes some IR noise. Tests updated by UTC
script to remove the extra lines.
2026-02-04 13:09:32 -05:00

172 lines
7.3 KiB
C
Raw Permalink Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
// RUN: %clang_cc1 -fnative-half-arguments-and-returns -triple amdgcn-amd-amdhsa-gnu -target-cpu gfx900 -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,SAFE %s
// RUN: %clang_cc1 -fnative-half-arguments-and-returns -triple amdgcn-amd-amdhsa-gnu -target-cpu gfx900 -emit-llvm -munsafe-fp-atomics -o - %s | FileCheck -check-prefixes=CHECK,UNSAFE %s
// SAFE-LABEL: define dso_local float @test_float_post_inc(
// SAFE-SAME: ) #[[ATTR0:[0-9]+]] {
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_float_post_inc.n to ptr), float 1.000000e+00 seq_cst, align 4, !amdgpu.no.fine.grained.memory [[META3:![0-9]+]], !amdgpu.no.remote.memory [[META3]]
// SAFE-NEXT: ret float [[TMP0]]
//
// UNSAFE-LABEL: define dso_local float @test_float_post_inc(
// UNSAFE-SAME: ) #[[ATTR0:[0-9]+]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_float_post_inc.n to ptr), float 1.000000e+00 seq_cst, align 4, !amdgpu.no.fine.grained.memory [[META3:![0-9]+]], !amdgpu.no.remote.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
// UNSAFE-NEXT: ret float [[TMP0]]
//
float test_float_post_inc()
{
static _Atomic float n;
return n++;
}
// CHECK-LABEL: define dso_local float @test_float_post_dc(
// CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_float_post_dc.n to ptr), float 1.000000e+00 seq_cst, align 4, !amdgpu.no.fine.grained.memory [[META3:![0-9]+]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: ret float [[TMP0]]
//
float test_float_post_dc()
{
static _Atomic float n;
return n--;
}
// CHECK-LABEL: define dso_local float @test_float_pre_dc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_float_pre_dc.n to ptr), float 1.000000e+00 seq_cst, align 4, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: [[TMP1:%.*]] = fsub float [[TMP0]], 1.000000e+00
// CHECK-NEXT: ret float [[TMP1]]
//
float test_float_pre_dc()
{
static _Atomic float n;
return --n;
}
// SAFE-LABEL: define dso_local float @test_float_pre_inc(
// SAFE-SAME: ) #[[ATTR0]] {
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_float_pre_inc.n to ptr), float 1.000000e+00 seq_cst, align 4, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// SAFE-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00
// SAFE-NEXT: ret float [[TMP1]]
//
// UNSAFE-LABEL: define dso_local float @test_float_pre_inc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_float_pre_inc.n to ptr), float 1.000000e+00 seq_cst, align 4, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
// UNSAFE-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00
// UNSAFE-NEXT: ret float [[TMP1]]
//
float test_float_pre_inc()
{
static _Atomic float n;
return ++n;
}
// CHECK-LABEL: define dso_local double @test_double_post_inc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_post_inc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: ret double [[TMP0]]
//
double test_double_post_inc()
{
static _Atomic double n;
return n++;
}
// CHECK-LABEL: define dso_local double @test_double_post_dc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_post_dc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: ret double [[TMP0]]
//
double test_double_post_dc()
{
static _Atomic double n;
return n--;
}
// CHECK-LABEL: define dso_local double @test_double_pre_dc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_pre_dc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: [[TMP1:%.*]] = fsub double [[TMP0]], 1.000000e+00
// CHECK-NEXT: ret double [[TMP1]]
//
double test_double_pre_dc()
{
static _Atomic double n;
return --n;
}
// CHECK-LABEL: define dso_local double @test_double_pre_inc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_pre_inc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00
// CHECK-NEXT: ret double [[TMP1]]
//
double test_double_pre_inc()
{
static _Atomic double n;
return ++n;
}
// CHECK-LABEL: define dso_local half @test__Float16_post_inc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_post_inc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: ret half [[TMP0]]
//
_Float16 test__Float16_post_inc()
{
static _Atomic _Float16 n;
return n++;
}
// CHECK-LABEL: define dso_local half @test__Float16_post_dc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_post_dc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: ret half [[TMP0]]
//
_Float16 test__Float16_post_dc()
{
static _Atomic _Float16 n;
return n--;
}
// CHECK-LABEL: define dso_local half @test__Float16_pre_dc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_dc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: [[TMP1:%.*]] = fsub half [[TMP0]], 0xH3C00
// CHECK-NEXT: ret half [[TMP1]]
//
_Float16 test__Float16_pre_dc()
{
static _Atomic _Float16 n;
return --n;
}
// CHECK-LABEL: define dso_local half @test__Float16_pre_inc(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_inc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.no.remote.memory [[META3]]
// CHECK-NEXT: [[TMP1:%.*]] = fadd half [[TMP0]], 0xH3C00
// CHECK-NEXT: ret half [[TMP1]]
//
_Float16 test__Float16_pre_inc()
{
static _Atomic _Float16 n;
return ++n;
}
//.
// SAFE: [[META3]] = !{}
//.
// UNSAFE: [[META3]] = !{}
//.
Reference in New Issue View Git Blame Copy Permalink