llvm-6502/test/CodeGen/R600/fadd.ll
Tom Stellard f15dfe4eb4 R600: Set scheduling preference to Sched::Source
R600 doesn't need to do any scheduling on the SelectionDAG now that it
has a very good MachineScheduler.  Also, using the VLIW SelectionDAG
scheduler was having a major impact on compile times. For example with
the phatk kernel here are the LLVM IR to machine code compile times:

With Sched::VLIW

Total Compile Time:                  1.4890 Seconds (User + System)
SelectionDAG Instruction Scheduling: 1.1670 Seconds (User + System)

With Sched::Source

Total Compile Time:                  0.3330 Seconds (User + System)
SelectionDAG Instruction Scheduling: 0.0070 Seconds (User + System)

The code ouput was identical with both schedulers.  This may not be true
for all programs, but it gives me confidence that there won't be much
reduction, if any, in code quality by using Sched::Source.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@188215 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-12 22:33:21 +00:00

42 lines
1.4 KiB
LLVM

; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
; CHECK: @fadd_f32
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define void @fadd_f32() {
%r0 = call float @llvm.R600.load.input(i32 0)
%r1 = call float @llvm.R600.load.input(i32 1)
%r2 = fadd float %r0, %r1
call void @llvm.AMDGPU.store.output(float %r2, i32 0)
ret void
}
declare float @llvm.R600.load.input(i32) readnone
declare void @llvm.AMDGPU.store.output(float, i32)
; CHECK: @fadd_v2f32
; CHECK-DAG: ADD * T{{[0-9]\.[XYZW]}}, KC0[3].X, KC0[3].Z
; CHECK-DAG: ADD * T{{[0-9]\.[XYZW]}}, KC0[2].W, KC0[3].Y
define void @fadd_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
entry:
%0 = fadd <2 x float> %a, %b
store <2 x float> %0, <2 x float> addrspace(1)* %out
ret void
}
; CHECK: @fadd_v4f32
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define void @fadd_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 = fadd <4 x float> %a, %b
store <4 x float> %result, <4 x float> addrspace(1)* %out
ret void
}