6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-24 06:30:19 +00:00
Code Issues Projects Releases Wiki Activity
f033db57e9
llvm-6502/test/CodeGen/R600/private-memory.ll

312 lines
11 KiB
LLVM
Raw Normal View History

R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
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. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225277 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-06 18:00:21 +00:00
; RUN: llc -show-mc-encoding -mattr=+promote-alloca -verify-machineinstrs -march=amdgcn -mcpu=SI < %s | FileCheck %s -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC
; RUN: llc -show-mc-encoding -mattr=-promote-alloca -verify-machineinstrs -march=amdgcn -mcpu=SI < %s | FileCheck %s -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC
R600: Make sure to schedule AR register uses and defs in the same clause Reviewed-by: vljn at ovi.com git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183294 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-05 03:43:06 +00:00
R600: Add some testcases for promote alloca pass. More complicated GEPs are skipped. Add some tests to actually stress this skipping. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 03:55:55 +00:00
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}mova_same_clause:
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600: LDS_WRITE
; R600: LDS_WRITE
; R600: LDS_READ
; R600: LDS_READ
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-PROMOTE: ds_write_b32
; SI-PROMOTE: ds_write_b32
; SI-PROMOTE: ds_read_b32
; SI-PROMOTE: ds_read_b32
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-ALLOCA: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ; encoding: [0x00,0x10,0x70,0xe0
; SI-ALLOCA: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ; encoding: [0x00,0x10,0x70,0xe0
R600: Make sure to schedule AR register uses and defs in the same clause Reviewed-by: vljn at ovi.com git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183294 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-05 03:43:06 +00:00
define void @mova_same_clause(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
entry:
%stack = alloca [5 x i32], align 4
%0 = load i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds [5 x i32]* %stack, i32 0, i32 %0
store i32 4, i32* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds i32 addrspace(1)* %in, i32 1
%1 = load i32 addrspace(1)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds [5 x i32]* %stack, i32 0, i32 %1
store i32 5, i32* %arrayidx3, align 4
%arrayidx10 = getelementptr inbounds [5 x i32]* %stack, i32 0, i32 0
%2 = load i32* %arrayidx10, align 4
store i32 %2, i32 addrspace(1)* %out, align 4
%arrayidx12 = getelementptr inbounds [5 x i32]* %stack, i32 0, i32 1
%3 = load i32* %arrayidx12
%arrayidx13 = getelementptr inbounds i32 addrspace(1)* %out, i32 1
store i32 %3, i32 addrspace(1)* %arrayidx13
ret void
}
R600: Fix calculation of stack offset in AMDGPUFrameLowering We weren't computing structure size correctly and we were relying on the original alloca instruction to compute the offset, which isn't always reliable. Reviewed-by: Vincent Lejeune <vljn@ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183568 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-07 20:52:05 +00:00
; This test checks that the stack offset is calculated correctly for structs.
; All register loads/stores should be optimized away, so there shouldn't be
; any MOVA instructions.
;
; XXX: This generated code has unnecessary MOVs, we should be able to optimize
; this.
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}multiple_structs:
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600-NOT: MOVA_INT
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-NOT: v_movrel
; SI-NOT: v_movrel
R600: Fix calculation of stack offset in AMDGPUFrameLowering We weren't computing structure size correctly and we were relying on the original alloca instruction to compute the offset, which isn't always reliable. Reviewed-by: Vincent Lejeune <vljn@ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183568 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-07 20:52:05 +00:00
%struct.point = type { i32, i32 }
define void @multiple_structs(i32 addrspace(1)* %out) {
entry:
%a = alloca %struct.point
%b = alloca %struct.point
%a.x.ptr = getelementptr %struct.point* %a, i32 0, i32 0
%a.y.ptr = getelementptr %struct.point* %a, i32 0, i32 1
%b.x.ptr = getelementptr %struct.point* %b, i32 0, i32 0
%b.y.ptr = getelementptr %struct.point* %b, i32 0, i32 1
store i32 0, i32* %a.x.ptr
store i32 1, i32* %a.y.ptr
store i32 2, i32* %b.x.ptr
store i32 3, i32* %b.y.ptr
%a.indirect.ptr = getelementptr %struct.point* %a, i32 0, i32 0
%b.indirect.ptr = getelementptr %struct.point* %b, i32 0, i32 0
%a.indirect = load i32* %a.indirect.ptr
%b.indirect = load i32* %b.indirect.ptr
%0 = add i32 %a.indirect, %b.indirect
store i32 %0, i32 addrspace(1)* %out
ret void
}
R600: Simplify handling of private address space The AMDGPUIndirectAddressing pass was previously responsible for lowering private loads and stores to indirect addressing instructions. However, this pass was buggy and way too complicated. The only advantage it had over the new simplified code was that it saved one instruction per direct write to private memory. This optimization likely has a minimal impact on performance, and we may be able to duplicate it using some other transformation. For the private address space, we now: 1. Lower private loads/store to Register(Load|Store) instructions 2. Reserve part of the register file as 'private memory' 3. After regalloc lower the Register(Load|Store) instructions to MOV instructions that use indirect addressing. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193179 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-22 18:19:10 +00:00
; Test direct access of a private array inside a loop. The private array
; loads and stores should be lowered to copies, so there shouldn't be any
; MOVA instructions.
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}direct_loop:
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600-NOT: MOVA_INT
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-NOT: v_movrel
R600: Simplify handling of private address space The AMDGPUIndirectAddressing pass was previously responsible for lowering private loads and stores to indirect addressing instructions. However, this pass was buggy and way too complicated. The only advantage it had over the new simplified code was that it saved one instruction per direct write to private memory. This optimization likely has a minimal impact on performance, and we may be able to duplicate it using some other transformation. For the private address space, we now: 1. Lower private loads/store to Register(Load|Store) instructions 2. Reserve part of the register file as 'private memory' 3. After regalloc lower the Register(Load|Store) instructions to MOV instructions that use indirect addressing. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193179 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-22 18:19:10 +00:00
define void @direct_loop(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
entry:
%prv_array_const = alloca [2 x i32]
%prv_array = alloca [2 x i32]
%a = load i32 addrspace(1)* %in
%b_src_ptr = getelementptr i32 addrspace(1)* %in, i32 1
%b = load i32 addrspace(1)* %b_src_ptr
%a_dst_ptr = getelementptr [2 x i32]* %prv_array_const, i32 0, i32 0
store i32 %a, i32* %a_dst_ptr
%b_dst_ptr = getelementptr [2 x i32]* %prv_array_const, i32 0, i32 1
store i32 %b, i32* %b_dst_ptr
br label %for.body
for.body:
%inc = phi i32 [0, %entry], [%count, %for.body]
%x_ptr = getelementptr [2 x i32]* %prv_array_const, i32 0, i32 0
%x = load i32* %x_ptr
%y_ptr = getelementptr [2 x i32]* %prv_array, i32 0, i32 0
%y = load i32* %y_ptr
%xy = add i32 %x, %y
store i32 %xy, i32* %y_ptr
%count = add i32 %inc, 1
%done = icmp eq i32 %count, 4095
br i1 %done, label %for.end, label %for.body
for.end:
%value_ptr = getelementptr [2 x i32]* %prv_array, i32 0, i32 0
%value = load i32* %value_ptr
store i32 %value, i32 addrspace(1)* %out
ret void
}
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}short_array:
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600: MOVA_INT
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-PROMOTE-DAG: buffer_store_short v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ; encoding: [0x00,0x10,0x68,0xe0
R600/SI: Change mubuf offsets to print as decimal This matches SC's behavior. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223194 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-03 03:12:13 +00:00
; SI-PROMOTE-DAG: buffer_store_short v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen offset:2 ; encoding: [0x02,0x10,0x68,0xe0
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-PROMOTE: buffer_load_sshort v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}}
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
define void @short_array(i32 addrspace(1)* %out, i32 %index) {
entry:
%0 = alloca [2 x i16]
%1 = getelementptr [2 x i16]* %0, i32 0, i32 0
%2 = getelementptr [2 x i16]* %0, i32 0, i32 1
store i16 0, i16* %1
store i16 1, i16* %2
%3 = getelementptr [2 x i16]* %0, i32 0, i32 %index
%4 = load i16* %3
%5 = sext i16 %4 to i32
store i32 %5, i32 addrspace(1)* %out
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}char_array:
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600: MOVA_INT
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-DAG: buffer_store_byte v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ; encoding: [0x00,0x10,0x60,0xe0
R600/SI: Change mubuf offsets to print as decimal This matches SC's behavior. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223194 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-03 03:12:13 +00:00
; SI-DAG: buffer_store_byte v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen offset:1 ; encoding: [0x01,0x10,0x60,0xe0
R600/SI: Add support for i8 and i16 private loads/stores git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199823 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:14 +00:00
define void @char_array(i32 addrspace(1)* %out, i32 %index) {
entry:
%0 = alloca [2 x i8]
%1 = getelementptr [2 x i8]* %0, i32 0, i32 0
%2 = getelementptr [2 x i8]* %0, i32 0, i32 1
store i8 0, i8* %1
store i8 1, i8* %2
%3 = getelementptr [2 x i8]* %0, i32 0, i32 %index
%4 = load i8* %3
%5 = sext i8 %4 to i32
store i32 %5, i32 addrspace(1)* %out
ret void
}
R600: Begin private memory at the second GPR. This way private memory does not over-write work group information stored in GPRs 0 and 1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199824 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:19 +00:00
; Make sure we don't overwrite workitem information with private memory
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}work_item_info:
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600-NOT: MOV T0.X
R600: Begin private memory at the second GPR. This way private memory does not over-write work group information stored in GPRs 0 and 1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199824 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:19 +00:00
; Additional check in case the move ends up in the last slot
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600-NOT: MOV * TO.X
R600: Begin private memory at the second GPR. This way private memory does not over-write work group information stored in GPRs 0 and 1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199824 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:19 +00:00
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-NOT: v_mov_b32_e{{(32|64)}} v0
R600: Begin private memory at the second GPR. This way private memory does not over-write work group information stored in GPRs 0 and 1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199824 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:19 +00:00
define void @work_item_info(i32 addrspace(1)* %out, i32 %in) {
entry:
%0 = alloca [2 x i32]
%1 = getelementptr [2 x i32]* %0, i32 0, i32 0
%2 = getelementptr [2 x i32]* %0, i32 0, i32 1
store i32 0, i32* %1
store i32 1, i32* %2
%3 = getelementptr [2 x i32]* %0, i32 0, i32 %in
%4 = load i32* %3
%5 = call i32 @llvm.r600.read.tidig.x()
%6 = add i32 %4, %5
store i32 %6, i32 addrspace(1)* %out
ret void
}
R600: Take alignment into account when calculating the stack offset git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199826 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:23 +00:00
; Test that two stack objects are not stored in the same register
; The second stack object should be in T3.X
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}no_overlap:
R600: Use LDS and vectors for private memory git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211110 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 16:53:14 +00:00
; R600_CHECK: MOV
; R600_CHECK: [[CHAN:[XYZW]]]+
R600: Run private-memory test with and without alloca promote The unpromoted path still needs to be tested since we can't always promote to using LDS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212894 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-13 02:18:06 +00:00
; R600-NOT: [[CHAN]]+
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: v_mov_b32_e32 v3
R600: Take alignment into account when calculating the stack offset git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199826 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:23 +00:00
define void @no_overlap(i32 addrspace(1)* %out, i32 %in) {
entry:
%0 = alloca [3 x i8], align 1
%1 = alloca [2 x i8], align 1
%2 = getelementptr [3 x i8]* %0, i32 0, i32 0
%3 = getelementptr [3 x i8]* %0, i32 0, i32 1
%4 = getelementptr [3 x i8]* %0, i32 0, i32 2
%5 = getelementptr [2 x i8]* %1, i32 0, i32 0
%6 = getelementptr [2 x i8]* %1, i32 0, i32 1
store i8 0, i8* %2
store i8 1, i8* %3
store i8 2, i8* %4
store i8 1, i8* %5
store i8 0, i8* %6
%7 = getelementptr [3 x i8]* %0, i32 0, i32 %in
%8 = getelementptr [2 x i8]* %1, i32 0, i32 %in
%9 = load i8* %7
%10 = load i8* %8
%11 = add i8 %9, %10
%12 = sext i8 %11 to i32
store i32 %12, i32 addrspace(1)* %out
ret void
}
R600: Add some testcases for promote alloca pass. More complicated GEPs are skipped. Add some tests to actually stress this skipping. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 03:55:55 +00:00
define void @char_array_array(i32 addrspace(1)* %out, i32 %index) {
entry:
%alloca = alloca [2 x [2 x i8]]
%gep0 = getelementptr [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 0
%gep1 = getelementptr [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 1
store i8 0, i8* %gep0
store i8 1, i8* %gep1
%gep2 = getelementptr [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 %index
%load = load i8* %gep2
%sext = sext i8 %load to i32
store i32 %sext, i32 addrspace(1)* %out
ret void
}
R600: Take alignment into account when calculating the stack offset git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199826 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:23 +00:00
R600: Add some testcases for promote alloca pass. More complicated GEPs are skipped. Add some tests to actually stress this skipping. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 03:55:55 +00:00
define void @i32_array_array(i32 addrspace(1)* %out, i32 %index) {
entry:
%alloca = alloca [2 x [2 x i32]]
%gep0 = getelementptr [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 0
%gep1 = getelementptr [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 1
store i32 0, i32* %gep0
store i32 1, i32* %gep1
%gep2 = getelementptr [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 %index
%load = load i32* %gep2
store i32 %load, i32 addrspace(1)* %out
ret void
}
R600: Take alignment into account when calculating the stack offset git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199826 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-22 19:24:23 +00:00
R600: Add some testcases for promote alloca pass. More complicated GEPs are skipped. Add some tests to actually stress this skipping. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 03:55:55 +00:00
define void @i64_array_array(i64 addrspace(1)* %out, i32 %index) {
entry:
%alloca = alloca [2 x [2 x i64]]
%gep0 = getelementptr [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 0
%gep1 = getelementptr [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 1
store i64 0, i64* %gep0
store i64 1, i64* %gep1
%gep2 = getelementptr [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 %index
%load = load i64* %gep2
store i64 %load, i64 addrspace(1)* %out
ret void
}
%struct.pair32 = type { i32, i32 }
define void @struct_array_array(i32 addrspace(1)* %out, i32 %index) {
entry:
%alloca = alloca [2 x [2 x %struct.pair32]]
%gep0 = getelementptr [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 0, i32 1
%gep1 = getelementptr [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 1, i32 1
store i32 0, i32* %gep0
store i32 1, i32* %gep1
%gep2 = getelementptr [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 %index, i32 0
%load = load i32* %gep2
store i32 %load, i32 addrspace(1)* %out
ret void
}
define void @struct_pair32_array(i32 addrspace(1)* %out, i32 %index) {
entry:
%alloca = alloca [2 x %struct.pair32]
%gep0 = getelementptr [2 x %struct.pair32]* %alloca, i32 0, i32 0, i32 1
%gep1 = getelementptr [2 x %struct.pair32]* %alloca, i32 0, i32 1, i32 0
store i32 0, i32* %gep0
store i32 1, i32* %gep1
%gep2 = getelementptr [2 x %struct.pair32]* %alloca, i32 0, i32 %index, i32 0
%load = load i32* %gep2
store i32 %load, i32 addrspace(1)* %out
ret void
R600: Don't crash on unhandled instruction in promote alloca git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211906 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 16:52:49 +00:00
}
R600: Add some testcases for promote alloca pass. More complicated GEPs are skipped. Add some tests to actually stress this skipping. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 03:55:55 +00:00
R600: Don't crash on unhandled instruction in promote alloca git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211906 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 16:52:49 +00:00
define void @select_private(i32 addrspace(1)* %out, i32 %in) nounwind {
entry:
%tmp = alloca [2 x i32]
%tmp1 = getelementptr [2 x i32]* %tmp, i32 0, i32 0
%tmp2 = getelementptr [2 x i32]* %tmp, i32 0, i32 1
store i32 0, i32* %tmp1
store i32 1, i32* %tmp2
%cmp = icmp eq i32 %in, 0
%sel = select i1 %cmp, i32* %tmp1, i32* %tmp2
%load = load i32* %sel
store i32 %load, i32 addrspace(1)* %out
ret void
R600: Add some testcases for promote alloca pass. More complicated GEPs are skipped. Add some tests to actually stress this skipping. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 03:55:55 +00:00
}
R600: Don't crash on unhandled instruction in promote alloca git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211906 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-27 16:52:49 +00:00
R600: Don't promote allocas when one of the users is a ptrtoint instruction We need to figure out how to track ptrtoint values all the way until result is converted back to a pointer in order to correctly rewrite the pointer type. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220997 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-31 20:52:04 +00:00
; AMDGPUPromoteAlloca does not know how to handle ptrtoint. When it
; finds one, it should stop trying to promote.
; FUNC-LABEL: ptrtoint:
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-NOT: ds_write
; SI: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen
R600/SI: Change mubuf offsets to print as decimal This matches SC's behavior. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223194 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-03 03:12:13 +00:00
; SI: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen offset:5
R600: Don't promote allocas when one of the users is a ptrtoint instruction We need to figure out how to track ptrtoint values all the way until result is converted back to a pointer in order to correctly rewrite the pointer type. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220997 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-31 20:52:04 +00:00
define void @ptrtoint(i32 addrspace(1)* %out, i32 %a, i32 %b) {
%alloca = alloca [16 x i32]
%tmp0 = getelementptr [16 x i32]* %alloca, i32 0, i32 %a
store i32 5, i32* %tmp0
%tmp1 = ptrtoint [16 x i32]* %alloca to i32
%tmp2 = add i32 %tmp1, 5
%tmp3 = inttoptr i32 %tmp2 to i32*
%tmp4 = getelementptr i32* %tmp3, i32 %b
%tmp5 = load i32* %tmp4
store i32 %tmp5, i32 addrspace(1)* %out
ret void
}
Reference in New Issue Copy Permalink