# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -o - -run-pass=machine-cse %s | FileCheck %s
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -o - -passes=machine-cse %s | FileCheck %s
# LLVM's current definition of `isConvergent` does not necessarily prove that
# non-local CSE is illegal. The following test extends the definition of
# `isConvergent` to assume a convergent instruction is dependent not only on
# additional conditions, but also on fewer conditions. LLVM does not have a
# MachineInstr attribute which expresses this extended definition, so it's
# necessary to use `isConvergent` to prevent illegally CSE-ing the subset of
# `isConvergent` instructions which do fall into this extended definition.
# This is a coverage test for the MachineCSE change. It does not reproduce an
# actual bug in the AMDGPU backend. The current open source GPU backends as is
# do not appear to allow a reasonably simple test case that provably and
# undeniably functionally breaks without the associated MachineCSE changes.
# The test checks that we don't CSE non-local convergent instrs. Otherwise,
# reusing defs of convergent instrs from different control flow scopes can
# cause illegal codegen. Previously, the swizzle in bb2 would be CSE-ed in
# favor of using the swizzle in bb1 despite bb2 being a different BBs.
# CHECK-LABEL: name: no_cse
# CHECK: bb.1.if.then
# CHECK: [[SWIZZLE1:%[0-9]+]]:vgpr_32 = DS_SWIZZLE_B32 [[SRC:%[0-9]+]], 100, 0, implicit $exec
# CHECK-NEXT: V_ADD_CO_U32_e64 [[SWIZZLE1]], {{%[0-9]+}}, 0, implicit $exec
# CHECK-NEXT: S_CMP_LT_I32 {{.*}} implicit-def $scc
# CHECK-NEXT: S_CBRANCH_SCC1 %bb.3, implicit $scc
# CHECK-NEXT: S_BRANCH %bb.2
# CHECK: bb.2.if.then.if.then
# CHECK: [[SWIZZLE2:%[0-9]+]]:vgpr_32 = DS_SWIZZLE_B32 [[SRC]], 100, 0, implicit $exec
# CHECK-NEXT: V_ADD_CO_U32_e64 [[SWIZZLE2]], {{%[0-9]+}}, 0, implicit $exec
--- |
define amdgpu_kernel void @no_cse(ptr addrspace(1), i32, i1) {
entry:
unreachable
if.then:
unreachable
if.then.if.then:
unreachable
if.then.phi:
unreachable
exit:
unreachable
}
...
---
name: no_cse
tracksRegLiveness: true
body: |
bb.0.entry:
liveins: $sgpr4_sgpr5
%0:sgpr_64(p4) = COPY $sgpr4_sgpr5
%1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0(p4), 0, 0
%2:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0(p4), 2, 0
%3:sreg_64 = COPY %1
%4:sreg_32 = COPY %2.sub1
%5:sreg_32 = S_MOV_B32 42
S_CMP_EQ_U32 %4, %5, implicit-def $scc
%6:vgpr_32 = COPY %5, implicit $exec
S_CBRANCH_SCC1 %bb.4, implicit $scc
S_BRANCH %bb.1
bb.1.if.then:
%7:sreg_32 = COPY %2.sub0
%8:vgpr_32 = COPY %7
%9:vgpr_32 = DS_SWIZZLE_B32 %8, 100, 0, implicit $exec
%10:vgpr_32, %21:sreg_32 = V_ADD_CO_U32_e64 %9, %5, 0, implicit $exec
S_CMP_LT_I32 %7, %5, implicit-def $scc
S_CBRANCH_SCC1 %bb.3, implicit $scc
S_BRANCH %bb.2
bb.2.if.then.if.then:
%11:sreg_32 = S_MOV_B32 64
%12:vgpr_32 = DS_SWIZZLE_B32 %8, 100, 0, implicit $exec
%13:vgpr_32, %24:sreg_32 = V_ADD_CO_U32_e64 %12, %11, 0, implicit $exec
bb.3.if.then.phi:
%14:vgpr_32 = PHI %10, %bb.1, %13, %bb.2
bb.4.exit:
%15:vgpr_32 = PHI %6, %bb.0, %14, %bb.3
%16:vreg_64 = COPY %3
FLAT_STORE_DWORD %16, %15, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...
Codebase Browser
llvm