mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-27 13:29:50 +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
200 lines
6.2 KiB
LLVM
200 lines
6.2 KiB
LLVM
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG %s -check-prefix=FUNC
|
|
; RUN: llc -march=r600 -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
; mul24 and mad24 are affected
|
|
|
|
; FUNC-LABEL: {{^}}test_mul_v2i32:
|
|
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
|
|
define void @test_mul_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
|
|
%a = load <2 x i32> addrspace(1) * %in
|
|
%b = load <2 x i32> addrspace(1) * %b_ptr
|
|
%result = mul <2 x i32> %a, %b
|
|
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_mul_v4i32:
|
|
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
|
|
define void @v_mul_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
|
|
%a = load <4 x i32> addrspace(1) * %in
|
|
%b = load <4 x i32> addrspace(1) * %b_ptr
|
|
%result = mul <4 x i32> %a, %b
|
|
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}s_trunc_i64_mul_to_i32:
|
|
; SI: s_load_dword
|
|
; SI: s_load_dword
|
|
; SI: s_mul_i32
|
|
; SI: buffer_store_dword
|
|
define void @s_trunc_i64_mul_to_i32(i32 addrspace(1)* %out, i64 %a, i64 %b) {
|
|
%mul = mul i64 %b, %a
|
|
%trunc = trunc i64 %mul to i32
|
|
store i32 %trunc, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_trunc_i64_mul_to_i32:
|
|
; SI: s_load_dword
|
|
; SI: s_load_dword
|
|
; SI: v_mul_lo_i32
|
|
; SI: buffer_store_dword
|
|
define void @v_trunc_i64_mul_to_i32(i32 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) nounwind {
|
|
%a = load i64 addrspace(1)* %aptr, align 8
|
|
%b = load i64 addrspace(1)* %bptr, align 8
|
|
%mul = mul i64 %b, %a
|
|
%trunc = trunc i64 %mul to i32
|
|
store i32 %trunc, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; This 64-bit multiply should just use MUL_HI and MUL_LO, since the top
|
|
; 32-bits of both arguments are sign bits.
|
|
; FUNC-LABEL: {{^}}mul64_sext_c:
|
|
; EG-DAG: MULLO_INT
|
|
; EG-DAG: MULHI_INT
|
|
; SI-DAG: s_mul_i32
|
|
; SI-DAG: v_mul_hi_i32
|
|
define void @mul64_sext_c(i64 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%0 = sext i32 %in to i64
|
|
%1 = mul i64 %0, 80
|
|
store i64 %1, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_mul64_sext_c:
|
|
; EG-DAG: MULLO_INT
|
|
; EG-DAG: MULHI_INT
|
|
; SI-DAG: v_mul_lo_i32
|
|
; SI-DAG: v_mul_hi_i32
|
|
; SI: s_endpgm
|
|
define void @v_mul64_sext_c(i64 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%val = load i32 addrspace(1)* %in, align 4
|
|
%ext = sext i32 %val to i64
|
|
%mul = mul i64 %ext, 80
|
|
store i64 %mul, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_mul64_sext_inline_imm:
|
|
; SI-DAG: v_mul_lo_i32 v{{[0-9]+}}, 9, v{{[0-9]+}}
|
|
; SI-DAG: v_mul_hi_i32 v{{[0-9]+}}, 9, v{{[0-9]+}}
|
|
; SI: s_endpgm
|
|
define void @v_mul64_sext_inline_imm(i64 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%val = load i32 addrspace(1)* %in, align 4
|
|
%ext = sext i32 %val to i64
|
|
%mul = mul i64 %ext, 9
|
|
store i64 %mul, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}s_mul_i32:
|
|
; SI: s_load_dword [[SRC0:s[0-9]+]],
|
|
; SI: s_load_dword [[SRC1:s[0-9]+]],
|
|
; SI: s_mul_i32 [[SRESULT:s[0-9]+]], [[SRC0]], [[SRC1]]
|
|
; SI: v_mov_b32_e32 [[VRESULT:v[0-9]+]], [[SRESULT]]
|
|
; SI: buffer_store_dword [[VRESULT]],
|
|
; SI: s_endpgm
|
|
define void @s_mul_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
|
|
%mul = mul i32 %a, %b
|
|
store i32 %mul, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_mul_i32:
|
|
; SI: v_mul_lo_i32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
|
|
define void @v_mul_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%b_ptr = getelementptr i32 addrspace(1)* %in, i32 1
|
|
%a = load i32 addrspace(1)* %in
|
|
%b = load i32 addrspace(1)* %b_ptr
|
|
%result = mul i32 %a, %b
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; A standard 64-bit multiply. The expansion should be around 6 instructions.
|
|
; It would be difficult to match the expansion correctly without writing
|
|
; a really complicated list of FileCheck expressions. I don't want
|
|
; to confuse people who may 'break' this test with a correct optimization,
|
|
; so this test just uses FUNC-LABEL to make sure the compiler does not
|
|
; crash with a 'failed to select' error.
|
|
|
|
; FUNC-LABEL: {{^}}s_mul_i64:
|
|
define void @s_mul_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind {
|
|
%mul = mul i64 %a, %b
|
|
store i64 %mul, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_mul_i64:
|
|
; SI: v_mul_lo_i32
|
|
define void @v_mul_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) {
|
|
%a = load i64 addrspace(1)* %aptr, align 8
|
|
%b = load i64 addrspace(1)* %bptr, align 8
|
|
%mul = mul i64 %a, %b
|
|
store i64 %mul, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}mul32_in_branch:
|
|
; SI: s_mul_i32
|
|
define void @mul32_in_branch(i32 addrspace(1)* %out, i32 addrspace(1)* %in, i32 %a, i32 %b, i32 %c) {
|
|
entry:
|
|
%0 = icmp eq i32 %a, 0
|
|
br i1 %0, label %if, label %else
|
|
|
|
if:
|
|
%1 = load i32 addrspace(1)* %in
|
|
br label %endif
|
|
|
|
else:
|
|
%2 = mul i32 %a, %b
|
|
br label %endif
|
|
|
|
endif:
|
|
%3 = phi i32 [%1, %if], [%2, %else]
|
|
store i32 %3, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}mul64_in_branch:
|
|
; SI-DAG: s_mul_i32
|
|
; SI-DAG: v_mul_hi_u32
|
|
; SI: s_endpgm
|
|
define void @mul64_in_branch(i64 addrspace(1)* %out, i64 addrspace(1)* %in, i64 %a, i64 %b, i64 %c) {
|
|
entry:
|
|
%0 = icmp eq i64 %a, 0
|
|
br i1 %0, label %if, label %else
|
|
|
|
if:
|
|
%1 = load i64 addrspace(1)* %in
|
|
br label %endif
|
|
|
|
else:
|
|
%2 = mul i64 %a, %b
|
|
br label %endif
|
|
|
|
endif:
|
|
%3 = phi i64 [%1, %if], [%2, %else]
|
|
store i64 %3, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|