maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGenOpenCL/amdgpu-attrs.cl

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

194 lines
13 KiB
Common Lisp
Raw Normal View History

[AMDGPU] Remove use of OpenCL triple environment and replace with function attribute for AMDGPU (CLANG) - Remove use of the opencl and amdopencl environment member of the target triple for the AMDGPU target. - Use a function attribute to communicate to the AMDGPU backend. Differential Revision: https://reviews.llvm.org/D43735 llvm-svn: 328347
2018-03-24 02:43:15 +08:00
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// RUN: %clang_cc1 -triple amdgcn-- -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -O0 -emit-llvm -verify -o - %s | FileCheck -check-prefix=X86 %s
__attribute__((amdgpu_flat_work_group_size(0, 0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0() {}
__attribute__((amdgpu_waves_per_eu(0))) // expected-no-diagnostics
kernel void waves_per_eu_0() {}
__attribute__((amdgpu_waves_per_eu(0, 0))) // expected-no-diagnostics
kernel void waves_per_eu_0_0() {}
__attribute__((amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void num_sgpr0() {}
__attribute__((amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void num_vgpr0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_num_sgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_num_vgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_num_sgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_num_vgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0, 0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_0_num_sgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0, 0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_0_num_vgpr_0() {}
__attribute__((amdgpu_num_sgpr(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void num_sgpr_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_num_sgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0_num_sgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0), amdgpu_num_sgpr(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_num_sgpr_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0), amdgpu_num_sgpr(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0_num_sgpr_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(32, 64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64() [[FLAT_WORK_GROUP_SIZE_32_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_waves_per_eu(2))) // expected-no-diagnostics
kernel void waves_per_eu_2() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2() [[WAVES_PER_EU_2:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_waves_per_eu(2, 4))) // expected-no-diagnostics
kernel void waves_per_eu_2_4() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_4() [[WAVES_PER_EU_2_4:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void num_sgpr_32() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @num_sgpr_32() [[NUM_SGPR_32:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @num_vgpr_64() [[NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2_4() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_num_sgpr_32() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_num_sgpr_32() [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_waves_per_eu(2), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void waves_per_eu_2_num_sgpr_32() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_num_sgpr_32() [[WAVES_PER_EU_2_NUM_SGPR_32:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_waves_per_eu(2), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void waves_per_eu_2_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_num_vgpr_64() [[WAVES_PER_EU_2_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_waves_per_eu(2, 4), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void waves_per_eu_2_4_num_sgpr_32() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_4_num_sgpr_32() [[WAVES_PER_EU_2_4_NUM_SGPR_32:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_waves_per_eu(2, 4), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void waves_per_eu_2_4_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_4_num_vgpr_64() [[WAVES_PER_EU_2_4_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_num_sgpr(32), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void num_sgpr_32_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @num_sgpr_32_num_vgpr_64() [[NUM_SGPR_32_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2), amdgpu_num_sgpr(32)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2), amdgpu_num_vgpr(64)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4), amdgpu_num_sgpr(32)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4), amdgpu_num_vgpr(64)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_4_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2), amdgpu_num_sgpr(32), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4), amdgpu_num_sgpr(32), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32_num_vgpr_64() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64:#[0-9]+]]
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
}
[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_size These two attributes specify the same info in a different way. AMGPU BE only checks the latter as a target specific attribute as opposed to language specific reqd_work_group_size. This change produces amdgpu_flat_work_group_size out of reqd_work_group_size if specified. Differential Revision: https://reviews.llvm.org/D31728 llvm-svn: 299678
2017-04-07 02:15:44 +08:00
__attribute__((reqd_work_group_size(32, 2, 1))) // expected-no-diagnostics
kernel void reqd_work_group_size_32_2_1() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @reqd_work_group_size_32_2_1() [[FLAT_WORK_GROUP_SIZE_64_64:#[0-9]+]]
[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_size These two attributes specify the same info in a different way. AMGPU BE only checks the latter as a target specific attribute as opposed to language specific reqd_work_group_size. This change produces amdgpu_flat_work_group_size out of reqd_work_group_size if specified. Differential Revision: https://reviews.llvm.org/D31728 llvm-svn: 299678
2017-04-07 02:15:44 +08:00
}
__attribute__((reqd_work_group_size(32, 2, 1), amdgpu_flat_work_group_size(16, 128))) // expected-no-diagnostics
kernel void reqd_work_group_size_32_2_1_flat_work_group_size_16_128() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @reqd_work_group_size_32_2_1_flat_work_group_size_16_128() [[FLAT_WORK_GROUP_SIZE_16_128:#[0-9]+]]
[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_size These two attributes specify the same info in a different way. AMGPU BE only checks the latter as a target specific attribute as opposed to language specific reqd_work_group_size. This change produces amdgpu_flat_work_group_size out of reqd_work_group_size if specified. Differential Revision: https://reviews.llvm.org/D31728 llvm-svn: 299678
2017-04-07 02:15:44 +08:00
}
[AMDGPU] Remove use of OpenCL triple environment and replace with function attribute for AMDGPU (CLANG) - Remove use of the opencl and amdopencl environment member of the target triple for the AMDGPU target. - Use a function attribute to communicate to the AMDGPU backend. Differential Revision: https://reviews.llvm.org/D43735 llvm-svn: 328347
2018-03-24 02:43:15 +08:00
void a_function() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} void @a_function() [[A_FUNCTION:#[0-9]+]]
[AMDGPU] Remove use of OpenCL triple environment and replace with function attribute for AMDGPU (CLANG) - Remove use of the opencl and amdopencl environment member of the target triple for the AMDGPU target. - Use a function attribute to communicate to the AMDGPU backend. Differential Revision: https://reviews.llvm.org/D43735 llvm-svn: 328347
2018-03-24 02:43:15 +08:00
}
AMDGPU: Always emit amdgpu-flat-work-group-size The backend default maximum should be the hardware maximum, so the frontend should set the implementation defined default maximum. llvm-svn: 370101
2019-08-28 03:25:40 +08:00
kernel void default_kernel() {
[test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences For a default visibility external linkage definition, dso_local is set for ELF -fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences. To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition, which sets dso_local for default visibility external linkage definitions. To make this flip smooth and enable future (dso_local as definition default), this patch replaces (function) `define ` with `define{{.*}} `, (variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
2020-12-31 16:27:11 +08:00
// CHECK: define{{.*}} amdgpu_kernel void @default_kernel() [[DEFAULT_KERNEL_ATTRS:#[0-9]+]]
AMDGPU: Always emit amdgpu-flat-work-group-size The backend default maximum should be the hardware maximum, so the frontend should set the implementation defined default maximum. llvm-svn: 370101
2019-08-28 03:25:40 +08:00
}
[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_size These two attributes specify the same info in a different way. AMGPU BE only checks the latter as a target specific attribute as opposed to language specific reqd_work_group_size. This change produces amdgpu_flat_work_group_size out of reqd_work_group_size if specified. Differential Revision: https://reviews.llvm.org/D31728 llvm-svn: 299678
2017-04-07 02:15:44 +08:00
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
// Make sure this is silently accepted on other targets.
// X86-NOT: "amdgpu-flat-work-group-size"
// X86-NOT: "amdgpu-waves-per-eu"
// X86-NOT: "amdgpu-num-vgpr"
// X86-NOT: "amdgpu-num-sgpr"
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-NOT: "amdgpu-implicitarg-num-bytes"
[AMDGPU] Expose flat work group size, register and wave control attributes __attribute__((amdgpu_flat_work_group_size(<min>, <max>))) - request minimum and maximum flat work group size __attribute__((amdgpu_waves_per_eu(<min>[, <max>]))) - request minimum and/or maximum waves per execution unit Differential Revision: https://reviews.llvm.org/D24513 llvm-svn: 282371
2016-09-26 09:02:57 +08:00
// CHECK-NOT: "amdgpu-flat-work-group-size"="0,0"
// CHECK-NOT: "amdgpu-waves-per-eu"="0"
// CHECK-NOT: "amdgpu-waves-per-eu"="0,0"
// CHECK-NOT: "amdgpu-num-sgpr"="0"
// CHECK-NOT: "amdgpu-num-vgpr"="0"
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = {{.*}} "amdgpu-flat-work-group-size"="64,64"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = {{.*}} "amdgpu-flat-work-group-size"="16,128"
[OpenCL][CUDA][HIP][SYCL] Add norecurse norecurse function attr indicates the function is not called recursively directly or indirectly. Add norecurse to OpenCL functions, SYCL functions in device compilation and CUDA/HIP kernels. Although there is LLVM pass adding norecurse to functions, it only works for whole-program compilation. Also FE adding norecurse can make that pass run faster since functions with norecurse do not need to be checked again. Differential Revision: https://reviews.llvm.org/D73651
2020-01-30 03:11:37 +08:00
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-waves-per-eu"="2"
[OpenCL][CUDA][HIP][SYCL] Add norecurse norecurse function attr indicates the function is not called recursively directly or indirectly. Add norecurse to OpenCL functions, SYCL functions in device compilation and CUDA/HIP kernels. Although there is LLVM pass adding norecurse to functions, it only works for whole-program compilation. Also FE adding norecurse can make that pass run faster since functions with norecurse do not need to be checked again. Differential Revision: https://reviews.llvm.org/D73651
2020-01-30 03:11:37 +08:00
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32"
// CHECK-DAG: attributes [[NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64"
[OpenCL][CUDA][HIP][SYCL] Add norecurse norecurse function attr indicates the function is not called recursively directly or indirectly. Add norecurse to OpenCL functions, SYCL functions in device compilation and CUDA/HIP kernels. Although there is LLVM pass adding norecurse to functions, it only works for whole-program compilation. Also FE adding norecurse can make that pass run faster since functions with norecurse do not need to be checked again. Differential Revision: https://reviews.llvm.org/D73651
2020-01-30 03:11:37 +08:00
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64"
[OpenCL][CUDA][HIP][SYCL] Add norecurse norecurse function attr indicates the function is not called recursively directly or indirectly. Add norecurse to OpenCL functions, SYCL functions in device compilation and CUDA/HIP kernels. Although there is LLVM pass adding norecurse to functions, it only works for whole-program compilation. Also FE adding norecurse can make that pass run faster since functions with norecurse do not need to be checked again. Differential Revision: https://reviews.llvm.org/D73651
2020-01-30 03:11:37 +08:00
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
[OpenCL][CUDA][HIP][SYCL] Add norecurse norecurse function attr indicates the function is not called recursively directly or indirectly. Add norecurse to OpenCL functions, SYCL functions in device compilation and CUDA/HIP kernels. Although there is LLVM pass adding norecurse to functions, it only works for whole-program compilation. Also FE adding norecurse can make that pass run faster since functions with norecurse do not need to be checked again. Differential Revision: https://reviews.llvm.org/D73651
2020-01-30 03:11:37 +08:00
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
[OpenCL][CUDA][HIP][SYCL] Add norecurse norecurse function attr indicates the function is not called recursively directly or indirectly. Add norecurse to OpenCL functions, SYCL functions in device compilation and CUDA/HIP kernels. Although there is LLVM pass adding norecurse to functions, it only works for whole-program compilation. Also FE adding norecurse can make that pass run faster since functions with norecurse do not need to be checked again. Differential Revision: https://reviews.llvm.org/D73651
2020-01-30 03:11:37 +08:00
[clang][opencl][codegen] Remove the insertion of `correctly-rounded-divide-sqrt-fp-math` fn-attr. - `-cl-fp32-correctly-rounded-divide-sqrt` is already handled in a per-instruction manner by annotating the accuracy required. There's no need to add that fn-attr. So far, there's no in-tree backend handling that attr and that OpenCL specific option. - In case that out-of-tree backends are broken, this change could be reverted if those backends could not be fixed. Differential Revision: https://reviews.llvm.org/D88424
2020-09-28 22:54:16 +08:00
// CHECK-DAG: attributes [[A_FUNCTION]] = {{.*}}
clang/AMDGPU: Don't set implicit arg attribute to default size Since 2959e082e1427647e107af0b82770682eaa58fe1, we conservatively assume all inputs are enabled by default. This isn't the best interface for controlling these anyway, since it's not granular and only allows trimming the last fields.
2021-12-04 23:52:07 +08:00
// CHECK-DAG: attributes [[DEFAULT_KERNEL_ATTRS]] = {{.*}} "amdgpu-flat-work-group-size"="1,256"