AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

aco/ra: Fix register allocation for subdword operands

Browse Source 
ACO attempts to store the output of an instruction in the same register
occupied by its operands where possible. Importantly this only works if
the operands are large enough to store the result register size. The code
failed to consider subdword operands when checking for this, causing
entire register slots to be freed up even though subdword parts were still
used.

In Mafia 3, this affected the following code:
v2b: %363:v[2][0:16],  v2b: %362:v[2][16:32] = p_split_vector %360:v[2]
v1:  %116:v[2] = v_cvt_f32_f16 %362:v[2][16:32]
v1:  %117:v[2] = v_cvt_f32_f16 %363:v[2][0:16]
where v[2] is allocated to %116 even though its original lower 16 bits are
still used in the instruction after.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3717
Fixes: 031edbc4a5
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7461>
This commit is contained in:
Tony Wasserka
2020-12-02 18:35:55 +01:00
committed by Marge Bot
parent 187b185502
commit 6b538506f2
1 changed files with 19 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/amd/compiler/aco_register_allocation.cpp
+19 -12
View File
@@ -158,6 +158,7 @@ public:
return res;
}
/* Returns true if any of the bytes in the given range are allocated or blocked */
bool test(PhysReg start, unsigned num_bytes) {
for (PhysReg i = start; i.reg_b < start.reg_b + num_bytes; i = PhysReg(i + 1)) {
if (regs[i] & 0x0FFFFFFF)
@@ -968,15 +969,21 @@ std::pair<PhysReg, bool> get_reg_impl(ra_ctx& ctx,
/* mark and count killed operands */
unsigned killed_ops = 0;
std::bitset<256> is_killed_operand; /* per-register */
for (unsigned j = 0; !is_phi(instr) && j < instr->operands.size(); j++) {
if (instr->operands[j].isTemp() &&
instr->operands[j].isFirstKillBeforeDef() &&
instr->operands[j].physReg() >= lb &&
instr->operands[j].physReg() < ub &&
!reg_file.test(instr->operands[j].physReg(), instr->operands[j].bytes())) {
assert(instr->operands[j].isFixed());
tmp_file.block(instr->operands[j].physReg(), instr->operands[j].regClass());
killed_ops += instr->operands[j].getTemp().size();
Operand& op = instr->operands[j];
if (op.isTemp() &&
op.isFirstKillBeforeDef() &&
op.physReg() >= lb &&
op.physReg() < ub &&
!reg_file.test(PhysReg{op.physReg().reg()}, align(op.bytes() + op.physReg().byte(), 4))) {
assert(op.isFixed());
for (unsigned i = 0; i < op.size(); ++i) {
is_killed_operand[(op.physReg() & 0xff) + i] = true;
}
killed_ops += op.getTemp().size();
}
}
@@ -1015,11 +1022,8 @@ std::pair<PhysReg, bool> get_reg_impl(ra_ctx& ctx,
bool found = true;
bool aligned = rc == RegClass::v4 && reg_lo % 4 == 0;
for (unsigned j = reg_lo; found && j <= reg_hi; j++) {
if (tmp_file[j] == 0 || tmp_file[j] == last_var)
continue;
/* dead operands effectively reduce the number of estimated moves */
if (tmp_file.is_blocked(PhysReg{j})) {
if (is_killed_operand[j & 0xFF]) {
if (remaining_op_moves) {
k--;
remaining_op_moves--;
@@ -1027,6 +1031,9 @@ std::pair<PhysReg, bool> get_reg_impl(ra_ctx& ctx,
continue;
}
if (tmp_file[j] == 0 || tmp_file[j] == last_var)
continue;
if (tmp_file[j] == 0xF0000000) {
k += 1;
n++;