RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity

[X86] Remove setOperationAction for FP_TO_SINT v8i16.

Browse Source 
This is no longer needed after widening legalization as we
custom legalize v8i8 ourselves.

Added entries to the cost model, but bumped the cost slightly
to account for the truncate shuffle that wasn't costed before.
This commit is contained in:
Craig Topper 2019-11-12 22:44:48 -08:00
parent d054b2dd05
commit e9ebc959cb
3 changed files with 15 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/X86/X86ISelLowering.cpp
View File

@ -937,14 +937,6 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
setOperationAction(ISD::FP_TO_UINT, MVT::v2i16, Custom);
setOperationAction(ISD::FP_TO_UINT, MVT::v4i16, Custom);
// By marking FP_TO_SINT v8i16 as Custom, will trick type legalization into
// promoting v8i8 FP_TO_UINT into FP_TO_SINT. When the v8i16 FP_TO_SINT is
// split again based on the input type, this will cause an AssertSExt i16 to
// be emitted instead of an AssertZExt. This will allow packssdw followed by
// packuswb to be used to truncate to v8i8. This is necessary since packusdw
// isn't available until sse4.1.
setOperationAction(ISD::FP_TO_SINT, MVT::v8i16, Custom);
setOperationAction(ISD::SINT_TO_FP, MVT::v4i32, Legal);
setOperationAction(ISD::SINT_TO_FP, MVT::v2i32, Custom);

3
lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -1576,6 +1576,9 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 6 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
{ ISD::FP_TO_SINT, MVT::v4i16, MVT::v4f32, 2 },
{ ISD::FP_TO_SINT, MVT::v2i16, MVT::v2f64, 2 },
{ ISD::FP_TO_SINT, MVT::v2i32, MVT::v2f64, 3 },
{ ISD::UINT_TO_FP, MVT::f64, MVT::i64, 6 },

24
test/Analysis/CostModel/X86/fptosi.ll
View File

@ -92,28 +92,28 @@ define i32 @fptosi_double_i32(i32 %arg) {
define i32 @fptosi_double_i16(i32 %arg) {
; SSE-LABEL: 'fptosi_double_i16'
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX-LABEL: 'fptosi_double_i16'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fptosi_double_i16'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fptosi_double_i16'
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@ -235,28 +235,28 @@ define i32 @fptosi_float_i32(i32 %arg) {
define i32 @fptosi_float_i16(i32 %arg) {
; SSE-LABEL: 'fptosi_float_i16'
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX-LABEL: 'fptosi_float_i16'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'fptosi_float_i16'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'fptosi_float_i16'
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef