mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-28 06:29:45 +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
102 lines
4.6 KiB
LLVM
102 lines
4.6 KiB
LLVM
; RUN: llc < %s -march=r600 -mcpu=SI -show-mc-encoding -verify-machineinstrs | FileCheck %s
|
|
|
|
; SMRD load with an immediate offset.
|
|
; CHECK-LABEL: {{^}}smrd0:
|
|
; CHECK: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x1 ; encoding: [0x01
|
|
define void @smrd0(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
|
|
entry:
|
|
%0 = getelementptr i32 addrspace(2)* %ptr, i64 1
|
|
%1 = load i32 addrspace(2)* %0
|
|
store i32 %1, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SMRD load with the largest possible immediate offset.
|
|
; CHECK-LABEL: {{^}}smrd1:
|
|
; CHECK: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0xff ; encoding: [0xff
|
|
define void @smrd1(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
|
|
entry:
|
|
%0 = getelementptr i32 addrspace(2)* %ptr, i64 255
|
|
%1 = load i32 addrspace(2)* %0
|
|
store i32 %1, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SMRD load with an offset greater than the largest possible immediate.
|
|
; CHECK-LABEL: {{^}}smrd2:
|
|
; CHECK: s_mov_b32 s[[OFFSET:[0-9]]], 0x400
|
|
; CHECK: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], s[[OFFSET]] ; encoding: [0x0[[OFFSET]]
|
|
; CHECK: s_endpgm
|
|
define void @smrd2(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
|
|
entry:
|
|
%0 = getelementptr i32 addrspace(2)* %ptr, i64 256
|
|
%1 = load i32 addrspace(2)* %0
|
|
store i32 %1, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SMRD load with a 64-bit offset
|
|
; CHECK-LABEL: {{^}}smrd3:
|
|
; CHECK-DAG: s_mov_b32 s[[SHI:[0-9]+]], 4
|
|
; CHECK-DAG: s_mov_b32 s[[SLO:[0-9]+]], 0 ;
|
|
; FIXME: We don't need to copy these values to VGPRs
|
|
; CHECK-DAG: v_mov_b32_e32 v[[VLO:[0-9]+]], s[[SLO]]
|
|
; CHECK-DAG: v_mov_b32_e32 v[[VHI:[0-9]+]], s[[SHI]]
|
|
; FIXME: We should be able to use s_load_dword here
|
|
; CHECK: buffer_load_dword v{{[0-9]+}}, v{{\[}}[[VLO]]:[[VHI]]{{\]}}, s[{{[0-9]+:[0-9]+}}], 0 addr64
|
|
; CHECK: s_endpgm
|
|
define void @smrd3(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
|
|
entry:
|
|
%0 = getelementptr i32 addrspace(2)* %ptr, i64 4294967296 ; 2 ^ 32
|
|
%1 = load i32 addrspace(2)* %0
|
|
store i32 %1, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SMRD load using the load.const intrinsic with an immediate offset
|
|
; CHECK-LABEL: {{^}}smrd_load_const0:
|
|
; CHECK: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x4 ; encoding: [0x04
|
|
define void @smrd_load_const0(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) #0 {
|
|
main_body:
|
|
%20 = getelementptr <16 x i8> addrspace(2)* %0, i32 0
|
|
%21 = load <16 x i8> addrspace(2)* %20
|
|
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 16)
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
|
|
ret void
|
|
}
|
|
|
|
; SMRD load using the load.const intrinsic with the largest possible immediate
|
|
; offset.
|
|
; CHECK-LABEL: {{^}}smrd_load_const1:
|
|
; CHECK: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0xff ; encoding: [0xff
|
|
define void @smrd_load_const1(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) #0 {
|
|
main_body:
|
|
%20 = getelementptr <16 x i8> addrspace(2)* %0, i32 0
|
|
%21 = load <16 x i8> addrspace(2)* %20
|
|
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 1020)
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
|
|
ret void
|
|
}
|
|
; SMRD load using the load.const intrinsic with an offset greater than the
|
|
; largets possible immediate.
|
|
; immediate offset.
|
|
; CHECK-LABEL: {{^}}smrd_load_const2:
|
|
; CHECK: s_mov_b32 s[[OFFSET:[0-9]]], 0x400
|
|
; CHECK: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], s[[OFFSET]] ; encoding: [0x0[[OFFSET]]
|
|
define void @smrd_load_const2(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) #0 {
|
|
main_body:
|
|
%20 = getelementptr <16 x i8> addrspace(2)* %0, i32 0
|
|
%21 = load <16 x i8> addrspace(2)* %20
|
|
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 1024)
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare float @llvm.SI.load.const(<16 x i8>, i32) #1
|
|
|
|
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
|
|
|
|
attributes #0 = { "ShaderType"="0" }
|
|
attributes #1 = { nounwind readnone }
|