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
68 lines
2.4 KiB
LLVM
68 lines
2.4 KiB
LLVM
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 %s
|
|
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
|
|
; These tests check that fdiv is expanded correctly and also test that the
|
|
; scheduler is scheduling the RECIP_IEEE and MUL_IEEE instructions in separate
|
|
; instruction groups.
|
|
|
|
; FUNC-LABEL: {{^}}fdiv_f32:
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Z
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Y
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, PS
|
|
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
define void @fdiv_f32(float addrspace(1)* %out, float %a, float %b) {
|
|
entry:
|
|
%0 = fdiv float %a, %b
|
|
store float %0, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
|
|
; FUNC-LABEL: {{^}}fdiv_v2f32:
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Z
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Y
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, PS
|
|
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
define void @fdiv_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
|
|
entry:
|
|
%0 = fdiv <2 x float> %a, %b
|
|
store <2 x float> %0, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fdiv_v4f32:
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
define void @fdiv_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x float> addrspace(1)* %in, i32 1
|
|
%a = load <4 x float> addrspace(1) * %in
|
|
%b = load <4 x float> addrspace(1) * %b_ptr
|
|
%result = fdiv <4 x float> %a, %b
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|