mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-21 16:31:16 +00:00
8eaed0f63d
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
90 lines
3.2 KiB
LLVM
90 lines
3.2 KiB
LLVM
; RUN: llc -march=r600 -mcpu=SI -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefix=SI-ALLOCA -check-prefix=SI %s
|
|
; RUN: llc -march=r600 -mcpu=SI -mattr=+promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefix=SI-PROMOTE -check-prefix=SI %s
|
|
|
|
|
|
declare void @llvm.AMDGPU.barrier.local() noduplicate nounwind
|
|
|
|
; SI-LABEL: {{^}}private_access_f64_alloca:
|
|
|
|
; SI-ALLOCA: buffer_store_dwordx2
|
|
; SI-ALLOCA: buffer_load_dwordx2
|
|
|
|
; SI-PROMOTE: ds_write_b64
|
|
; SI-PROMOTE: ds_read_b64
|
|
define void @private_access_f64_alloca(double addrspace(1)* noalias %out, double addrspace(1)* noalias %in, i32 %b) nounwind {
|
|
%val = load double addrspace(1)* %in, align 8
|
|
%array = alloca double, i32 16, align 8
|
|
%ptr = getelementptr double* %array, i32 %b
|
|
store double %val, double* %ptr, align 8
|
|
call void @llvm.AMDGPU.barrier.local() noduplicate nounwind
|
|
%result = load double* %ptr, align 8
|
|
store double %result, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}private_access_v2f64_alloca:
|
|
|
|
; SI-ALLOCA: buffer_store_dwordx4
|
|
; SI-ALLOCA: buffer_load_dwordx4
|
|
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
define void @private_access_v2f64_alloca(<2 x double> addrspace(1)* noalias %out, <2 x double> addrspace(1)* noalias %in, i32 %b) nounwind {
|
|
%val = load <2 x double> addrspace(1)* %in, align 16
|
|
%array = alloca <2 x double>, i32 16, align 16
|
|
%ptr = getelementptr <2 x double>* %array, i32 %b
|
|
store <2 x double> %val, <2 x double>* %ptr, align 16
|
|
call void @llvm.AMDGPU.barrier.local() noduplicate nounwind
|
|
%result = load <2 x double>* %ptr, align 16
|
|
store <2 x double> %result, <2 x double> addrspace(1)* %out, align 16
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}private_access_i64_alloca:
|
|
|
|
; SI-ALLOCA: buffer_store_dwordx2
|
|
; SI-ALLOCA: buffer_load_dwordx2
|
|
|
|
; SI-PROMOTE: ds_write_b64
|
|
; SI-PROMOTE: ds_read_b64
|
|
define void @private_access_i64_alloca(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in, i32 %b) nounwind {
|
|
%val = load i64 addrspace(1)* %in, align 8
|
|
%array = alloca i64, i32 16, align 8
|
|
%ptr = getelementptr i64* %array, i32 %b
|
|
store i64 %val, i64* %ptr, align 8
|
|
call void @llvm.AMDGPU.barrier.local() noduplicate nounwind
|
|
%result = load i64* %ptr, align 8
|
|
store i64 %result, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}private_access_v2i64_alloca:
|
|
|
|
; SI-ALLOCA: buffer_store_dwordx4
|
|
; SI-ALLOCA: buffer_load_dwordx4
|
|
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_write_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
; SI-PROMOTE: ds_read_b32
|
|
define void @private_access_v2i64_alloca(<2 x i64> addrspace(1)* noalias %out, <2 x i64> addrspace(1)* noalias %in, i32 %b) nounwind {
|
|
%val = load <2 x i64> addrspace(1)* %in, align 16
|
|
%array = alloca <2 x i64>, i32 16, align 16
|
|
%ptr = getelementptr <2 x i64>* %array, i32 %b
|
|
store <2 x i64> %val, <2 x i64>* %ptr, align 16
|
|
call void @llvm.AMDGPU.barrier.local() noduplicate nounwind
|
|
%result = load <2 x i64>* %ptr, align 16
|
|
store <2 x i64> %result, <2 x i64> addrspace(1)* %out, align 16
|
|
ret void
|
|
}
|