1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
llvm-mirror/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
Neil Henning 914315597c [AMDGPU] Add an AMDGPU specific atomic optimizer.
This commit adds a new IR level pass to the AMDGPU backend to perform
atomic optimizations. It works by:

- Running through a function and finding atomicrmw add/sub or uses of
  the atomic buffer intrinsics for add/sub.
- If all arguments except the value to be added/subtracted are uniform,
  record the value to be optimized.
- Run through the atomic operations we can optimize and, depending on
  whether the value is uniform/divergent use wavefront wide operations
  (DPP in the divergent case) to calculate the total amount to be
  atomically added/subtracted.
- Then let only a single lane of each wavefront perform the atomic
  operation, reducing the total number of atomic operations in flight.
- Lastly we recombine the result from the single lane to each lane of
  the wavefront, and calculate our individual lanes offset into the
  final result.

Differential Revision: https://reviews.llvm.org/D51969

llvm-svn: 343973
2018-10-08 15:49:19 +00:00

156 lines
7.3 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.struct.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32, i32)
declare i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32, i32)
; Show that what the atomic optimization pass will do for struct buffers.
; GCN-LABEL: add_i32_constant:
; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; 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.struct.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_uniform:
; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; 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.struct.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, 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_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.struct.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_varying_vindex:
; 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_vindex(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, 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.struct.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 0, i32 %lane, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_constant:
; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; 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.struct.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_uniform:
; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; 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.struct.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, 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_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.struct.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_varying_vindex:
; 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_vindex(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, 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.struct.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 0, i32 %lane, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}