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

75 lines
2.8 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
R600/SI: Enable all tests that pass on VI without changes llvm-svn: 227214
2015-01-28 01:27:15 +08:00
; RUN: llc < %s -march=amdgcn -mcpu=tonga -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:
R600/SI: Make more unordered comparisons legal This saves a second compare and an and / or by using the unordered comparison instructions. llvm-svn: 224066
2014-12-12 06:15:39 +08:00
; CHECK: v_cmp_nge_f64_e32 vcc, {{v[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
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
define 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:
R600/SI: Make more unordered comparisons legal This saves a second compare and an and / or by using the unordered comparison instructions. llvm-svn: 224066
2014-12-12 06:15:39 +08:00
; CHECK: v_cmp_ngt_f64_e32 vcc, {{v[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
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
define 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:
R600/SI: Make more unordered comparisons legal This saves a second compare and an and / or by using the unordered comparison instructions. llvm-svn: 224066
2014-12-12 06:15:39 +08:00
; CHECK: v_cmp_nle_f64_e32 vcc, {{v[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
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
define 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:
R600/SI: Make more unordered comparisons legal This saves a second compare and an and / or by using the unordered comparison instructions. llvm-svn: 224066
2014-12-12 06:15:39 +08:00
; CHECK: v_cmp_nlt_f64_e32 vcc, {{v[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
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
define 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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%r0 = load double, double addrspace(1)* %in1
%r1 = load double, double addrspace(1)* %in2
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
%r2 = fcmp uge double %r0, %r1
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
%r3 = zext i1 %r2 to i32
store i32 %r3, i32 addrspace(1)* %out
R600/SI: Implement select and compares for SI Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 186181
2013-07-13 02:15:19 +08:00
ret void
}
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI select_cc is expanded on SI, so this was never matched. llvm-svn: 221941
2014-11-14 07:03:09 +08:00
; CHECK-LABEL: {{^}}fne_f64:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; CHECK: v_cmp_neq_f64_e32 vcc, {{v[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
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
define void @fne_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
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:
R600/SI: Use unordered equal instructions llvm-svn: 224067
2014-12-12 06:15:43 +08:00
; CHECK: v_cmp_nlg_f64_e32 vcc, {{v[[0-9]+:[0-9]+], v[[0-9]+:[0-9]+]}}
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
define void @feq_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
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
}