mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-17 18:31:04 +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
70 lines
3.5 KiB
LLVM
70 lines
3.5 KiB
LLVM
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs -mattr=+load-store-opt -enable-misched < %s | FileCheck -check-prefix=SI --check-prefix=CHECK %s
|
|
; RUN: llc -march=r600 -mcpu=bonaire -verify-machineinstrs -mattr=+load-store-opt -enable-misched < %s | FileCheck -check-prefix=CI --check-prefix=CHECK %s
|
|
|
|
declare i32 @llvm.r600.read.tidig.x() #0
|
|
declare void @llvm.AMDGPU.barrier.local() #1
|
|
|
|
; Function Attrs: nounwind
|
|
; CHECK-LABEL: {{^}}signed_ds_offset_addressing_loop:
|
|
; CHECK: BB0_1:
|
|
; CHECK: v_add_i32_e32 [[VADDR:v[0-9]+]],
|
|
; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[VADDR]]
|
|
; SI-DAG: v_add_i32_e32 [[VADDR4:v[0-9]+]], 4, [[VADDR]]
|
|
; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[VADDR4]]
|
|
; SI-DAG: v_add_i32_e32 [[VADDR0x80:v[0-9]+]], 0x80, [[VADDR]]
|
|
; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[VADDR0x80]]
|
|
; SI-DAG: v_add_i32_e32 [[VADDR0x84:v[0-9]+]], 0x84, [[VADDR]]
|
|
; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[VADDR0x84]]
|
|
; SI-DAG: v_add_i32_e32 [[VADDR0x100:v[0-9]+]], 0x100, [[VADDR]]
|
|
; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[VADDR0x100]]
|
|
|
|
; CI-DAG: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[VADDR]] offset0:0 offset1:1
|
|
; CI-DAG: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[VADDR]] offset0:32 offset1:33
|
|
; CI-DAG: ds_read_b32 v{{[0-9]+}}, [[VADDR]] offset:256
|
|
; CHECK: s_endpgm
|
|
define void @signed_ds_offset_addressing_loop(float addrspace(1)* noalias nocapture %out, float addrspace(3)* noalias nocapture readonly %lptr, i32 %n) #2 {
|
|
entry:
|
|
%x.i = tail call i32 @llvm.r600.read.tidig.x() #0
|
|
%mul = shl nsw i32 %x.i, 1
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%sum.03 = phi float [ 0.000000e+00, %entry ], [ %add13, %for.body ]
|
|
%offset.02 = phi i32 [ %mul, %entry ], [ %add14, %for.body ]
|
|
%k.01 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
|
tail call void @llvm.AMDGPU.barrier.local() #1
|
|
%arrayidx = getelementptr inbounds float addrspace(3)* %lptr, i32 %offset.02
|
|
%tmp = load float addrspace(3)* %arrayidx, align 4
|
|
%add1 = add nsw i32 %offset.02, 1
|
|
%arrayidx2 = getelementptr inbounds float addrspace(3)* %lptr, i32 %add1
|
|
%tmp1 = load float addrspace(3)* %arrayidx2, align 4
|
|
%add3 = add nsw i32 %offset.02, 32
|
|
%arrayidx4 = getelementptr inbounds float addrspace(3)* %lptr, i32 %add3
|
|
%tmp2 = load float addrspace(3)* %arrayidx4, align 4
|
|
%add5 = add nsw i32 %offset.02, 33
|
|
%arrayidx6 = getelementptr inbounds float addrspace(3)* %lptr, i32 %add5
|
|
%tmp3 = load float addrspace(3)* %arrayidx6, align 4
|
|
%add7 = add nsw i32 %offset.02, 64
|
|
%arrayidx8 = getelementptr inbounds float addrspace(3)* %lptr, i32 %add7
|
|
%tmp4 = load float addrspace(3)* %arrayidx8, align 4
|
|
%add9 = fadd float %tmp, %tmp1
|
|
%add10 = fadd float %add9, %tmp2
|
|
%add11 = fadd float %add10, %tmp3
|
|
%add12 = fadd float %add11, %tmp4
|
|
%add13 = fadd float %sum.03, %add12
|
|
%inc = add nsw i32 %k.01, 1
|
|
%add14 = add nsw i32 %offset.02, 97
|
|
%exitcond = icmp eq i32 %inc, 8
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
%tmp5 = sext i32 %x.i to i64
|
|
%arrayidx15 = getelementptr inbounds float addrspace(1)* %out, i64 %tmp5
|
|
store float %add13, float addrspace(1)* %arrayidx15, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|
|
attributes #1 = { noduplicate nounwind }
|
|
attributes #2 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|