maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/fcmp64.ll

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

75 lines
2.9 KiB
LLVM
Raw Normal View History

R600/SI: Add a stub GCNTargetMachine This is equivalent to the AMDGPUTargetMachine now, but it is the starting point for separating R600 and GCN functionality into separate targets. It is recommened that users start using the gcn triple for GCN-based GPUs, because using the r600 triple for these GPUs will be deprecated in the future. llvm-svn: 225277
2015-01-07 02:00:21 +08:00
; RUN: llc < %s -march=amdgcn -mcpu=tahiti -verify-machineinstrs | FileCheck %s
Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc < %s -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs | FileCheck %s
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}flt_f64:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; CHECK: v_cmp_nge_f64_e32 vcc, {{s[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @flt_f64(i32 addrspace(1)* %out, double addrspace(1)* %in1,
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
double addrspace(1)* %in2) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp ult double %r0, %r1
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
%r3 = zext i1 %r2 to i32
store i32 %r3, i32 addrspace(1)* %out
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
ret void
}
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}fle_f64:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; CHECK: v_cmp_ngt_f64_e32 vcc, {{s[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @fle_f64(i32 addrspace(1)* %out, double addrspace(1)* %in1,
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
double addrspace(1)* %in2) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp ule double %r0, %r1
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
%r3 = zext i1 %r2 to i32
store i32 %r3, i32 addrspace(1)* %out
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
ret void
}
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}fgt_f64:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; CHECK: v_cmp_nle_f64_e32 vcc, {{s[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @fgt_f64(i32 addrspace(1)* %out, double addrspace(1)* %in1,
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
double addrspace(1)* %in2) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp ugt double %r0, %r1
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
%r3 = zext i1 %r2 to i32
store i32 %r3, i32 addrspace(1)* %out
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
ret void
}
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}fge_f64:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; CHECK: v_cmp_nlt_f64_e32 vcc, {{s[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @fge_f64(i32 addrspace(1)* %out, double addrspace(1)* %in1,
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
double addrspace(1)* %in2) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp uge double %r0, %r1
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
%r3 = zext i1 %r2 to i32
store i32 %r3, i32 addrspace(1)* %out
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
ret void
}
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}fne_f64:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; CHECK: v_cmp_neq_f64_e32 vcc, {{s[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @fne_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
double addrspace(1)* %in2) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp une double %r0, %r1
%r3 = select i1 %r2, double %r0, double %r1
store double %r3, double addrspace(1)* %out
ret void
}
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}feq_f64:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; CHECK: v_cmp_nlg_f64_e32 vcc, {{s[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @feq_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
double addrspace(1)* %in2) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp ueq double %r0, %r1
%r3 = select i1 %r2, double %r0, double %r1
store double %r3, double addrspace(1)* %out
ret void
}