mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 20:23:11 +01:00
72f01d1369
Summary:
Reduce the statefulness of the algorithm in two ways:
1. More clearly split generateWaitcntInstBefore into two phases: the
first one which determines the required wait, if any, without changing
the ScoreBrackets, and the second one which actually inserts the wait
and updates the brackets.
2. Communicate pre-existing s_waitcnt instructions using an argument to
generateWaitcntInstBefore instead of through the ScoreBrackets.
To simplify these changes, a Waitcnt structure is introduced which carries
the counts of an s_waitcnt instruction in decoded form.
There are some functional changes:
1. The FIXME for the VCCZ bug workaround was implemented: we only wait for
SMEM instructions as required instead of waiting on all counters.
2. We now properly track pre-existing waitcnt's in all cases, which leads
to less conservative waitcnts being emitted in some cases.
s_load_dword ...
s_waitcnt lgkmcnt(0) <-- pre-existing wait count
ds_read_b32 v0, ...
ds_read_b32 v1, ...
s_waitcnt lgkmcnt(0) <-- this is too conservative
use(v0)
more code
use(v1)
This increases code size a bit, but the reduced latency should still be a
win in basically all cases. The worst code size regressions in my shader-db
are:
WORST REGRESSIONS - Code Size
Before After Delta Percentage
1724 1736 12 0.70 % shaders/private/f1-2015/1334.shader_test [0]
2276 2284 8 0.35 % shaders/private/f1-2015/1306.shader_test [0]
4632 4640 8 0.17 % shaders/private/ue4_elemental/62.shader_test [0]
2376 2384 8 0.34 % shaders/private/f1-2015/1308.shader_test [0]
3284 3292 8 0.24 % shaders/private/talos_principle/1955.shader_test [0]
Reviewers: msearles, rampitec, scott.linder, kanarayan
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits, hakzsam
Differential Revision: https://reviews.llvm.org/D54226
llvm-svn: 347848
48 lines
1.5 KiB
LLVM
48 lines
1.5 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VCCZ-BUG %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VCCZ-BUG %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=NOVCCZ-BUG %s
|
|
|
|
; GCN-FUNC: {{^}}vccz_workaround:
|
|
; GCN: s_load_dword s{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0x0
|
|
; GCN: v_cmp_neq_f32_e64 {{[^,]*}}, s{{[0-9]+}}, 0{{$}}
|
|
; VCCZ-BUG: s_waitcnt lgkmcnt(0)
|
|
; VCCZ-BUG: s_mov_b64 vcc, vcc
|
|
; NOVCCZ-BUG-NOT: s_mov_b64 vcc, vcc
|
|
; GCN: s_cbranch_vccnz [[EXIT:[0-9A-Za-z_]+]]
|
|
; GCN: buffer_store_dword
|
|
; GCN: [[EXIT]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @vccz_workaround(i32 addrspace(4)* %in, i32 addrspace(1)* %out, float %cond) {
|
|
entry:
|
|
%cnd = fcmp oeq float 0.0, %cond
|
|
%sgpr = load volatile i32, i32 addrspace(4)* %in
|
|
br i1 %cnd, label %if, label %endif
|
|
|
|
if:
|
|
store i32 %sgpr, i32 addrspace(1)* %out
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|
|
|
|
; GCN-FUNC: {{^}}vccz_noworkaround:
|
|
; GCN: v_cmp_neq_f32_e32 vcc, 0, v{{[0-9]+}}
|
|
; GCN: s_cbranch_vccnz [[EXIT:[0-9A-Za-z_]+]]
|
|
; GCN: buffer_store_dword
|
|
; GCN: [[EXIT]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @vccz_noworkaround(float addrspace(1)* %in, float addrspace(1)* %out) {
|
|
entry:
|
|
%vgpr = load volatile float, float addrspace(1)* %in
|
|
%cnd = fcmp oeq float 0.0, %vgpr
|
|
br i1 %cnd, label %if, label %endif
|
|
|
|
if:
|
|
store float %vgpr, float addrspace(1)* %out
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|