mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-28 14:10:41 +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
75 lines
3.0 KiB
LLVM
75 lines
3.0 KiB
LLVM
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
|
|
; FUNC-LABEL: {{^}}v_fsub_f32:
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
define void @v_fsub_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
|
|
%b_ptr = getelementptr float addrspace(1)* %in, i32 1
|
|
%a = load float addrspace(1)* %in, align 4
|
|
%b = load float addrspace(1)* %b_ptr, align 4
|
|
%result = fsub float %a, %b
|
|
store float %result, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}s_fsub_f32:
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, -KC0[2].W
|
|
|
|
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
|
|
define void @s_fsub_f32(float addrspace(1)* %out, float %a, float %b) {
|
|
%sub = fsub float %a, %b
|
|
store float %sub, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.R600.load.input(i32) readnone
|
|
|
|
declare void @llvm.AMDGPU.store.output(float, i32)
|
|
|
|
; FUNC-LABEL: {{^}}fsub_v2f32:
|
|
; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, -KC0[3].Z
|
|
; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, -KC0[3].Y
|
|
|
|
; FIXME: Should be using SGPR directly for first operand
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
define void @fsub_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
|
|
%sub = fsub <2 x float> %a, %b
|
|
store <2 x float> %sub, <2 x float> addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_fsub_v4f32:
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
define void @v_fsub_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, align 16
|
|
%b = load <4 x float> addrspace(1)* %b_ptr, align 16
|
|
%result = fsub <4 x float> %a, %b
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
|
|
ret void
|
|
}
|
|
|
|
; FIXME: Should be using SGPR directly for first operand
|
|
|
|
; FUNC-LABEL: {{^}}s_fsub_v4f32:
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
|
|
; SI: s_endpgm
|
|
define void @s_fsub_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 x float> %b) {
|
|
%result = fsub <4 x float> %a, %b
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
|
|
ret void
|
|
}
|