shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c
Yaxun (Sam) Liu 240f2269ff
Add clang atomic control options and attribute (#114841) 
Add option and statement attribute for controlling emitting of
target-specific
metadata to atomicrmw instructions in IR.

The RFC for this attribute and option is

https://discourse.llvm.org/t/rfc-add-clang-atomic-control-options-and-pragmas/80641,
Originally a pragma was proposed, then it was changed to clang
attribute.

This attribute allows users to specify one, two, or all three options
and must be applied
to a compound statement. The attribute can also be nested, with inner
attributes
overriding the options specified by outer attributes or the target's
default
options. These options will then determine the target-specific metadata
added to atomic
instructions in the IR.

In addition to the attribute, three new compiler options are introduced:
`-f[no-]atomic-remote-memory`, `-f[no-]atomic-fine-grained-memory`,
 `-f[no-]atomic-ignore-denormal-mode`.
These compiler options allow users to override the default options
through the
Clang driver and front end. `-m[no-]unsafe-fp-atomics` is aliased to
`-f[no-]ignore-denormal-mode`.

In terms of implementation, the atomic attribute is represented in the
AST by the
existing AttributedStmt, with minimal changes to AST and Sema.

During code generation in Clang, the CodeGenModule maintains the current
atomic options,
which are used to emit the relevant metadata for atomic instructions.
RAII is used
to manage the saving and restoring of atomic options when entering
and exiting nested AttributedStmt.
2025-02-27 10:41:04 -05:00

200 lines
9.6 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: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
// 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