maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[CostModel][X86] Improve AVX1/AVX2 v16i32->v16i16/v16i8 truncation costs (PR51972) 

Based off worst case btver2 (AVX1) and haswell (AVX2) llvm-mca reports
This commit is contained in:
Simon Pilgrim 2021-09-26 13:43:46 +01:00
parent 9820dd970c
commit 3538ee763d
6 changed files with 49 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -1940,6 +1940,8 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
{ ISD::TRUNCATE, MVT::v8i1, MVT::v8i32, 2 },
{ ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, 4 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 4 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v8i16, 1 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v4i32, 1 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v2i64, 1 },
@ -2015,6 +2017,8 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
{ ISD::TRUNCATE, MVT::v8i1, MVT::v8i64, 9 },
{ ISD::TRUNCATE, MVT::v16i1, MVT::v16i64, 11 },
{ ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, 6 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 6 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v16i16, 2 }, // and+extract+packuswb
{ ISD::TRUNCATE, MVT::v16i8, MVT::v8i32, 5 },
{ ISD::TRUNCATE, MVT::v8i16, MVT::v8i32, 5 },

24
llvm/test/Analysis/CostModel/X86/arith-fix.ll
View File

@ -81,8 +81,8 @@ define i32 @smul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
@ -100,8 +100,8 @@ define i32 @smul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
@ -214,8 +214,8 @@ define i32 @smul(i32 %arg) {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
@ -315,8 +315,8 @@ define i32 @umul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
@ -334,8 +334,8 @@ define i32 @umul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)
@ -448,8 +448,8 @@ define i32 @umul(i32 %arg) {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3)

24
llvm/test/Analysis/CostModel/X86/arith-overflow.ll
View File

@ -1037,8 +1037,8 @@ define i32 @smul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
@ -1056,8 +1056,8 @@ define i32 @smul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
@ -1170,8 +1170,8 @@ define i32 @smul(i32 %arg) {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
@ -1275,8 +1275,8 @@ define i32 @umul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
@ -1294,8 +1294,8 @@ define i32 @umul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
@ -1408,8 +1408,8 @@ define i32 @umul(i32 %arg) {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; BTVER2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)

8
llvm/test/Analysis/CostModel/X86/cast.ll
View File

@ -167,8 +167,8 @@ define i32 @zext_sext(<8 x i1> %in) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %G = trunc <8 x i64> undef to <8 x i32>
; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'zext_sext'
@ -197,8 +197,8 @@ define i32 @zext_sext(<8 x i1> %in) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %G = trunc <8 x i64> undef to <8 x i32>
; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'zext_sext'

4
llvm/test/Analysis/CostModel/X86/min-legal-vector-width.ll
View File

@ -218,8 +218,8 @@ define void @trunc256() "min-legal-vector-width"="256" {
; VEC256-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %A = trunc <8 x i64> undef to <8 x i32>
; VEC256-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %B = trunc <8 x i64> undef to <8 x i16>
; VEC256-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C = trunc <8 x i64> undef to <8 x i8>
; VEC256-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %D = trunc <16 x i32> undef to <16 x i16>
; VEC256-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %E = trunc <16 x i32> undef to <16 x i8>
; VEC256-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D = trunc <16 x i32> undef to <16 x i16>
; VEC256-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %E = trunc <16 x i32> undef to <16 x i8>
; VEC256-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %F = trunc <32 x i16> undef to <32 x i8>
; VEC256-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;

30
llvm/test/Analysis/CostModel/X86/trunc.ll
View File

@ -117,8 +117,8 @@ define i32 @trunc_vXi16() {
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'trunc_vXi16'
@ -132,8 +132,8 @@ define i32 @trunc_vXi16() {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'trunc_vXi16'
@ -162,8 +162,8 @@ define i32 @trunc_vXi16() {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%i64 = trunc i64 undef to i16
@ -267,9 +267,9 @@ define i32 @trunc_vXi8() {
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %i16 = trunc i16 undef to i8
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = trunc <2 x i16> undef to <2 x i8>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = trunc <4 x i16> undef to <4 x i8>
@ -291,9 +291,9 @@ define i32 @trunc_vXi8() {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %i16 = trunc i16 undef to i8
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = trunc <2 x i16> undef to <2 x i8>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = trunc <4 x i16> undef to <4 x i8>
@ -363,9 +363,9 @@ define i32 @trunc_vXi8() {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %i16 = trunc i16 undef to i8
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = trunc <2 x i16> undef to <2 x i8>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = trunc <4 x i16> undef to <4 x i8>