mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 19:29:22 +00:00
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
55 lines
2.2 KiB
LLVM
55 lines
2.2 KiB
LLVM
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs< %s | FileCheck --check-prefix=SI --check-prefix=CHECK %s
|
|
; RUN: llc -march=r600 -mcpu=bonaire -verify-machineinstrs< %s | FileCheck --check-prefix=CI --check-prefix=CHECK %s
|
|
|
|
define void @use_gep_address_space([1024 x i32] addrspace(3)* %array) nounwind {
|
|
; CHECK-LABEL: {{^}}use_gep_address_space:
|
|
; CHECK: v_mov_b32_e32 [[PTR:v[0-9]+]], s{{[0-9]+}}
|
|
; CHECK: ds_write_b32 [[PTR]], v{{[0-9]+}} offset:64
|
|
%p = getelementptr [1024 x i32] addrspace(3)* %array, i16 0, i16 16
|
|
store i32 99, i32 addrspace(3)* %p
|
|
ret void
|
|
}
|
|
|
|
define void @use_gep_address_space_large_offset([1024 x i32] addrspace(3)* %array) nounwind {
|
|
; CHECK-LABEL: {{^}}use_gep_address_space_large_offset:
|
|
; The LDS offset will be 65536 bytes, which is larger than the size of LDS on
|
|
; SI, which is why it is being OR'd with the base pointer.
|
|
; SI: s_or_b32
|
|
; CI: s_add_i32
|
|
; CHECK: ds_write_b32
|
|
%p = getelementptr [1024 x i32] addrspace(3)* %array, i16 0, i16 16384
|
|
store i32 99, i32 addrspace(3)* %p
|
|
ret void
|
|
}
|
|
|
|
define void @gep_as_vector_v4(<4 x [1024 x i32] addrspace(3)*> %array) nounwind {
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v4:
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
%p = getelementptr <4 x [1024 x i32] addrspace(3)*> %array, <4 x i16> zeroinitializer, <4 x i16> <i16 16, i16 16, i16 16, i16 16>
|
|
%p0 = extractelement <4 x i32 addrspace(3)*> %p, i32 0
|
|
%p1 = extractelement <4 x i32 addrspace(3)*> %p, i32 1
|
|
%p2 = extractelement <4 x i32 addrspace(3)*> %p, i32 2
|
|
%p3 = extractelement <4 x i32 addrspace(3)*> %p, i32 3
|
|
store i32 99, i32 addrspace(3)* %p0
|
|
store i32 99, i32 addrspace(3)* %p1
|
|
store i32 99, i32 addrspace(3)* %p2
|
|
store i32 99, i32 addrspace(3)* %p3
|
|
ret void
|
|
}
|
|
|
|
define void @gep_as_vector_v2(<2 x [1024 x i32] addrspace(3)*> %array) nounwind {
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v2:
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
%p = getelementptr <2 x [1024 x i32] addrspace(3)*> %array, <2 x i16> zeroinitializer, <2 x i16> <i16 16, i16 16>
|
|
%p0 = extractelement <2 x i32 addrspace(3)*> %p, i32 0
|
|
%p1 = extractelement <2 x i32 addrspace(3)*> %p, i32 1
|
|
store i32 99, i32 addrspace(3)* %p0
|
|
store i32 99, i32 addrspace(3)* %p1
|
|
ret void
|
|
}
|
|
|