1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 11:42:57 +01:00

[X86][SSE] Improve cost model for i64 vector comparisons on pre-SSE42 targets

As discussed on PR24888, until SSE42 we don't have access to PCMPGTQ for v2i64 comparisons, but the cost models don't reflect this, resulting in over-optimistic vectorizaton.

This patch adds SSE2 'base level' costs that match what a typical target is capable of and only reduces the v2i64 costs at SSE42.

Technically SSE41 provides a PCMPEQQ v2i64 equality test, but as getCmpSelInstrCost doesn't give us a way to discriminate between comparison test types we can't easily make use of this, otherwise we could split the cost of integer equality and greater-than tests to give better costings of each.

Differential Revision: http://reviews.llvm.org/D20057

llvm-svn: 268972
This commit is contained in:
Simon Pilgrim 2016-05-09 21:14:38 +00:00
parent 0381dde382
commit 01729bd834
2 changed files with 19 additions and 11 deletions

View File

@ -857,13 +857,17 @@ int X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
static const CostTblEntry SSE2CostTbl[] = {
{ ISD::SETCC, MVT::v2i64, 8 },
{ ISD::SETCC, MVT::v4i32, 1 },
{ ISD::SETCC, MVT::v8i16, 1 },
{ ISD::SETCC, MVT::v16i8, 1 },
};
static const CostTblEntry SSE42CostTbl[] = {
{ ISD::SETCC, MVT::v2f64, 1 },
{ ISD::SETCC, MVT::v4f32, 1 },
{ ISD::SETCC, MVT::v2i64, 1 },
{ ISD::SETCC, MVT::v4i32, 1 },
{ ISD::SETCC, MVT::v8i16, 1 },
{ ISD::SETCC, MVT::v16i8, 1 },
};
static const CostTblEntry AVX1CostTbl[] = {
@ -906,6 +910,10 @@ int X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy) {
if (const auto *Entry = CostTableLookup(SSE42CostTbl, ISD, MTy))
return LT.first * Entry->Cost;
if (ST->hasSSE2())
if (const auto *Entry = CostTableLookup(SSE2CostTbl, ISD, MTy))
return LT.first * Entry->Cost;
return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy);
}

View File

@ -87,18 +87,18 @@ define i32 @cmp(i32 %arg) {
;AVX: cost of 1 {{.*}} icmp
%H = icmp eq <4 x i32> undef, undef
;SSE2: cost of 1 {{.*}} icmp
;SSE3: cost of 1 {{.*}} icmp
;SSSE3: cost of 1 {{.*}} icmp
;SSE41: cost of 1 {{.*}} icmp
;SSE2: cost of 8 {{.*}} icmp
;SSE3: cost of 8 {{.*}} icmp
;SSSE3: cost of 8 {{.*}} icmp
;SSE41: cost of 8 {{.*}} icmp
;SSE42: cost of 1 {{.*}} icmp
;AVX: cost of 1 {{.*}} icmp
%I = icmp eq <2 x i64> undef, undef
;SSE2: cost of 2 {{.*}} icmp
;SSE3: cost of 2 {{.*}} icmp
;SSSE3: cost of 2 {{.*}} icmp
;SSE41: cost of 2 {{.*}} icmp
;SSE2: cost of 16 {{.*}} icmp
;SSE3: cost of 16 {{.*}} icmp
;SSSE3: cost of 16 {{.*}} icmp
;SSE41: cost of 16 {{.*}} icmp
;SSE42: cost of 2 {{.*}} icmp
;AVX1: cost of 4 {{.*}} icmp
;AVX2: cost of 1 {{.*}} icmp