caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
12ccdd67aaf56bd05ab3375d81c58dfd5a2db02c
clang-p2996/llvm/test/CodeGen/AMDGPU/sched_barrier.mir
Austin Kerbow 2db700215a [AMDGPU] Add llvm.amdgcn.sched.barrier intrinsic 
Adds an intrinsic/builtin that can be used to fine tune scheduler behavior. If
there is a need to have highly optimized codegen and kernel developers have
knowledge of inter-wave runtime behavior which is unknown to the compiler this
builtin can be used to tune scheduling.

This intrinsic creates a barrier between scheduling regions. The immediate
parameter is a mask to determine the types of instructions that should be
prevented from crossing the sched_barrier. In this initial patch, there are only
two variations. A mask of 0 means that no instructions may be scheduled across
the sched_barrier. A mask of 1 means that non-memory, non-side-effect inducing
instructions may cross the sched_barrier.

Note that this intrinsic is only meant to work with the scheduling passes. Any
other transformations that may move code will not be impacted in the ways
described above.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D124700
2022-05-11 13:22:51 -07:00

100 lines
6.5 KiB
YAML
Raw Blame History

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx908 -run-pass=machine-scheduler -verify-misched -o - %s | FileCheck %s
--- |
define amdgpu_kernel void @no_sched_barrier(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) { ret void }
define amdgpu_kernel void @sched_barrier_0(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) { ret void }
define amdgpu_kernel void @sched_barrier_1(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) { ret void }
!0 = distinct !{!0}
!1 = !{!1, !0}
...
---
name: no_sched_barrier
tracksRegLiveness: true
body: |
bb.0:
; CHECK-LABEL: name: no_sched_barrier
; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
; CHECK-NEXT: S_NOP 0
; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_1]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
; CHECK-NEXT: S_ENDPGM 0
%0:sreg_64 = IMPLICIT_DEF
%1:vgpr_32 = IMPLICIT_DEF
%3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
%4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
S_NOP 0
%5:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
%6:vgpr_32 = nsw V_MUL_LO_U32_e64 %5, %5, implicit $exec
GLOBAL_STORE_DWORD_SADDR %1, %6, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
S_ENDPGM 0
...
---
name: sched_barrier_0
tracksRegLiveness: true
body: |
bb.0:
; CHECK-LABEL: name: sched_barrier_0
; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
; CHECK-NEXT: S_NOP 0
; CHECK-NEXT: SCHED_BARRIER 0
; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_1]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
; CHECK-NEXT: S_ENDPGM 0
%0:sreg_64 = IMPLICIT_DEF
%1:vgpr_32 = IMPLICIT_DEF
%3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
%4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
S_NOP 0
SCHED_BARRIER 0
%5:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
%6:vgpr_32 = nsw V_MUL_LO_U32_e64 %5, %5, implicit $exec
GLOBAL_STORE_DWORD_SADDR %1, %6, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
S_ENDPGM 0
...
---
name: sched_barrier_1
tracksRegLiveness: true
body: |
bb.0:
; CHECK-LABEL: name: sched_barrier_1
; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
; CHECK-NEXT: SCHED_BARRIER 1
; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
; CHECK-NEXT: S_NOP 0
; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_1]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
; CHECK-NEXT: S_ENDPGM 0
%0:sreg_64 = IMPLICIT_DEF
%1:vgpr_32 = IMPLICIT_DEF
%3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
%4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
S_NOP 0
SCHED_BARRIER 1
%5:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
%6:vgpr_32 = nsw V_MUL_LO_U32_e64 %5, %5, implicit $exec
GLOBAL_STORE_DWORD_SADDR %1, %6, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
S_ENDPGM 0
...
Reference in New Issue View Git Blame Copy Permalink