mirror of
https://github.com/RPCS3/llvm.git
synced 2026-01-31 01:25:19 +01:00
7f18dddc3d
Summary: r363675 changed the exec modification helper function, now called execMayBeModifiedBeforeUse, so that if no UseMI is specified it checks all instructions in the basic block, even beyond the last use. That meant that the DPP combiner no longer worked in any basic block that ended with a control flow instruction, and in particular it didn't work on code sequences generated by the atomic optimizer. Fix it by reinstating the old behaviour but in a new helper function execMayBeModifiedBeforeAnyUse, and limiting the number of instructions scanned. Reviewers: arsenm, vpykhtin Subscribers: kzhuravl, nemanjai, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kbarton, MaskRay, jfb, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D64393 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365910 91177308-0d34-0410-b5e6-96231b3b80d8
134 lines
6.4 KiB
LLVM
134 lines
6.4 KiB
LLVM
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|
|
declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32)
|
|
declare i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32)
|
|
|
|
; Show that what the atomic optimization pass will do for raw buffers.
|
|
|
|
; GCN-LABEL: add_i32_constant:
|
|
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
|
|
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
|
|
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
|
|
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
|
|
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
|
|
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
|
|
; GCN: buffer_atomic_add v[[value]]
|
|
define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
|
|
entry:
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: add_i32_uniform:
|
|
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
|
|
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
|
|
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
|
|
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
|
|
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
|
|
; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
|
|
; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GCN: buffer_atomic_add v[[value]]
|
|
define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
|
|
entry:
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: add_i32_varying_vdata:
|
|
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
|
|
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
|
|
; GFX7LESS-NOT: s_bcnt1_i32_b64
|
|
; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
|
|
; GFX8MORE: v_add_u32_dpp
|
|
; GFX8MORE: v_add_u32_dpp
|
|
; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: buffer_atomic_add v[[value]]
|
|
define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: add_i32_varying_offset:
|
|
; GCN-NOT: v_mbcnt_lo_u32_b32
|
|
; GCN-NOT: v_mbcnt_hi_u32_b32
|
|
; GCN-NOT: s_bcnt1_i32_b64
|
|
; GCN: buffer_atomic_add v{{[0-9]+}}
|
|
define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: sub_i32_constant:
|
|
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
|
|
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
|
|
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
|
|
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
|
|
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
|
|
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
|
|
; GCN: buffer_atomic_sub v[[value]]
|
|
define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
|
|
entry:
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: sub_i32_uniform:
|
|
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
|
|
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
|
|
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
|
|
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
|
|
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
|
|
; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
|
|
; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GCN: buffer_atomic_sub v[[value]]
|
|
define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
|
|
entry:
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: sub_i32_varying_vdata:
|
|
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
|
|
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
|
|
; GFX7LESS-NOT: s_bcnt1_i32_b64
|
|
; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
|
|
; GFX8MORE: v_sub{{(rev)?}}_u32_dpp
|
|
; GFX8MORE: v_sub{{(rev)?}}_u32_dpp
|
|
; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: buffer_atomic_sub v[[value]]
|
|
define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: sub_i32_varying_offset:
|
|
; GCN-NOT: v_mbcnt_lo_u32_b32
|
|
; GCN-NOT: v_mbcnt_hi_u32_b32
|
|
; GCN-NOT: s_bcnt1_i32_b64
|
|
; GCN: buffer_atomic_sub v{{[0-9]+}}
|
|
define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|