mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-21 16:31:16 +00:00
a140448780
This should expose more of the actually used VALU instructions to the machine optimization passes. This also should help getting i1 handling into a better state. For not entirly understood reasons, this fixes the split-scalar-i64-add.ll test where a 64-bit add would only partially be moved to the VALU resulting in use of undefined VCC. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222256 91177308-0d34-0410-b5e6-96231b3b80d8
49 lines
1.8 KiB
LLVM
49 lines
1.8 KiB
LLVM
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
declare i32 @llvm.r600.read.tidig.x() readnone
|
|
|
|
; This is broken because the low half of the 64-bit add remains on the
|
|
; SALU, but the upper half does not. The addc expects the carry bit
|
|
; set in vcc, which is undefined since the low scalar half add sets
|
|
; scc instead.
|
|
|
|
; FUNC-LABEL: {{^}}imp_def_vcc_split_i64_add_0:
|
|
; SI: v_add_i32
|
|
; SI: v_addc_u32
|
|
define void @imp_def_vcc_split_i64_add_0(i64 addrspace(1)* %out, i32 %val) {
|
|
%vec.0 = insertelement <2 x i32> undef, i32 %val, i32 0
|
|
%vec.1 = insertelement <2 x i32> %vec.0, i32 999999, i32 1
|
|
%bc = bitcast <2 x i32> %vec.1 to i64
|
|
%add = add i64 %bc, 399
|
|
store i64 %add, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}imp_def_vcc_split_i64_add_1:
|
|
; SI: v_add_i32
|
|
; SI: v_addc_u32
|
|
define void @imp_def_vcc_split_i64_add_1(i64 addrspace(1)* %out, i32 %val0, i64 %val1) {
|
|
%vec.0 = insertelement <2 x i32> undef, i32 %val0, i32 0
|
|
%vec.1 = insertelement <2 x i32> %vec.0, i32 99999, i32 1
|
|
%bc = bitcast <2 x i32> %vec.1 to i64
|
|
%add = add i64 %bc, %val1
|
|
store i64 %add, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; Doesn't use constants
|
|
; FUNC-LABEL @imp_def_vcc_split_i64_add_2
|
|
; SI: v_add_i32
|
|
; SI: v_addc_u32
|
|
define void @imp_def_vcc_split_i64_add_2(i64 addrspace(1)* %out, i32 addrspace(1)* %in, i32 %val0, i64 %val1) {
|
|
%tid = call i32 @llvm.r600.read.tidig.x() readnone
|
|
%gep = getelementptr i32 addrspace(1)* %in, i32 %tid
|
|
%load = load i32 addrspace(1)* %gep
|
|
%vec.0 = insertelement <2 x i32> undef, i32 %val0, i32 0
|
|
%vec.1 = insertelement <2 x i32> %vec.0, i32 %load, i32 1
|
|
%bc = bitcast <2 x i32> %vec.1 to i64
|
|
%add = add i64 %bc, %val1
|
|
store i64 %add, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|