RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 11:42:57 +01:00
Code Issues Projects Releases Wiki Activity

[CostModel][X86] Fix AVX512BW vector shift costs for vXi16 types

Browse Source 
We already have patterns in place to support 128/256-bit shifts without AVX512VL

llvm-svn: 292077
This commit is contained in:
Simon Pilgrim 2017-01-15 20:44:00 +00:00
parent 1634b52e50
commit 8a670cd3d1
4 changed files with 28 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -323,6 +323,14 @@ int X86TTIImpl::getArithmeticInstrCost(
return LT.first * Entry->Cost; return LT.first * Entry->Cost;
static const CostTblEntry AVX512BWCostTable[] = { static const CostTblEntry AVX512BWCostTable[] = {
{ ISD::SHL, MVT::v8i16, 1 }, // vpsllvw
{ ISD::SRL, MVT::v8i16, 1 }, // vpsrlvw
{ ISD::SRA, MVT::v8i16, 1 }, // vpsravw
{ ISD::SHL, MVT::v16i16, 1 }, // vpsllvw
{ ISD::SRL, MVT::v16i16, 1 }, // vpsrlvw
{ ISD::SRA, MVT::v16i16, 1 }, // vpsravw
{ ISD::SHL, MVT::v32i16, 1 }, // vpsllvw { ISD::SHL, MVT::v32i16, 1 }, // vpsllvw
{ ISD::SRL, MVT::v32i16, 1 }, // vpsrlvw { ISD::SRL, MVT::v32i16, 1 }, // vpsrlvw
{ ISD::SRA, MVT::v32i16, 1 }, // vpsravw { ISD::SRA, MVT::v32i16, 1 }, // vpsravw

12
test/Analysis/CostModel/X86/vshift-ashr-cost.ll
View File

@ -98,7 +98,8 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) {
; SSE41: Found an estimated cost of 14 for instruction: %shift ; SSE41: Found an estimated cost of 14 for instruction: %shift
; AVX: Found an estimated cost of 14 for instruction: %shift ; AVX: Found an estimated cost of 14 for instruction: %shift
; AVX2: Found an estimated cost of 14 for instruction: %shift ; AVX2: Found an estimated cost of 14 for instruction: %shift
; AVX512: Found an estimated cost of 14 for instruction: %shift ; AVX512F: Found an estimated cost of 14 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 2 for instruction: %shift ; XOP: Found an estimated cost of 2 for instruction: %shift
%shift = ashr <8 x i16> %a, %b %shift = ashr <8 x i16> %a, %b
ret <8 x i16> %shift ret <8 x i16> %shift
@ -110,7 +111,8 @@ define <16 x i16> @var_shift_v16i16(<16 x i16> %a, <16 x i16> %b) {
; SSE41: Found an estimated cost of 28 for instruction: %shift ; SSE41: Found an estimated cost of 28 for instruction: %shift
; AVX: Found an estimated cost of 28 for instruction: %shift ; AVX: Found an estimated cost of 28 for instruction: %shift
; AVX2: Found an estimated cost of 10 for instruction: %shift ; AVX2: Found an estimated cost of 10 for instruction: %shift
; AVX512: Found an estimated cost of 10 for instruction: %shift ; AVX512F: Found an estimated cost of 10 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 4 for instruction: %shift ; XOP: Found an estimated cost of 4 for instruction: %shift
%shift = ashr <16 x i16> %a, %b %shift = ashr <16 x i16> %a, %b
ret <16 x i16> %shift ret <16 x i16> %shift
@ -432,7 +434,8 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) {
; SSE41: Found an estimated cost of 14 for instruction: %shift ; SSE41: Found an estimated cost of 14 for instruction: %shift
; AVX: Found an estimated cost of 14 for instruction: %shift ; AVX: Found an estimated cost of 14 for instruction: %shift
; AVX2: Found an estimated cost of 14 for instruction: %shift ; AVX2: Found an estimated cost of 14 for instruction: %shift
; AVX512: Found an estimated cost of 14 for instruction: %shift ; AVX512F: Found an estimated cost of 14 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 2 for instruction: %shift ; XOP: Found an estimated cost of 2 for instruction: %shift
%shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7> %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
ret <8 x i16> %shift ret <8 x i16> %shift
@ -444,7 +447,8 @@ define <16 x i16> @constant_shift_v16i16(<16 x i16> %a) {
; SSE41: Found an estimated cost of 28 for instruction: %shift ; SSE41: Found an estimated cost of 28 for instruction: %shift
; AVX: Found an estimated cost of 28 for instruction: %shift ; AVX: Found an estimated cost of 28 for instruction: %shift
; AVX2: Found an estimated cost of 10 for instruction: %shift ; AVX2: Found an estimated cost of 10 for instruction: %shift
; AVX512: Found an estimated cost of 10 for instruction: %shift ; AVX512F: Found an estimated cost of 10 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 4 for instruction: %shift ; XOP: Found an estimated cost of 4 for instruction: %shift
%shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7> %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
ret <16 x i16> %shift ret <16 x i16> %shift

12
test/Analysis/CostModel/X86/vshift-lshr-cost.ll
View File

@ -101,7 +101,8 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) {
; SSE41: Found an estimated cost of 14 for instruction: %shift ; SSE41: Found an estimated cost of 14 for instruction: %shift
; AVX: Found an estimated cost of 14 for instruction: %shift ; AVX: Found an estimated cost of 14 for instruction: %shift
; AVX2: Found an estimated cost of 14 for instruction: %shift ; AVX2: Found an estimated cost of 14 for instruction: %shift
; AVX512: Found an estimated cost of 14 for instruction: %shift ; AVX512F: Found an estimated cost of 14 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 2 for instruction: %shift ; XOP: Found an estimated cost of 2 for instruction: %shift
%shift = lshr <8 x i16> %a, %b %shift = lshr <8 x i16> %a, %b
ret <8 x i16> %shift ret <8 x i16> %shift
@ -113,7 +114,8 @@ define <16 x i16> @var_shift_v16i16(<16 x i16> %a, <16 x i16> %b) {
; SSE41: Found an estimated cost of 28 for instruction: %shift ; SSE41: Found an estimated cost of 28 for instruction: %shift
; AVX: Found an estimated cost of 28 for instruction: %shift ; AVX: Found an estimated cost of 28 for instruction: %shift
; AVX2: Found an estimated cost of 10 for instruction: %shift ; AVX2: Found an estimated cost of 10 for instruction: %shift
; AVX512: Found an estimated cost of 10 for instruction: %shift ; AVX512F: Found an estimated cost of 10 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 4 for instruction: %shift ; XOP: Found an estimated cost of 4 for instruction: %shift
%shift = lshr <16 x i16> %a, %b %shift = lshr <16 x i16> %a, %b
ret <16 x i16> %shift ret <16 x i16> %shift
@ -437,7 +439,8 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) {
; SSE41: Found an estimated cost of 14 for instruction: %shift ; SSE41: Found an estimated cost of 14 for instruction: %shift
; AVX: Found an estimated cost of 14 for instruction: %shift ; AVX: Found an estimated cost of 14 for instruction: %shift
; AVX2: Found an estimated cost of 14 for instruction: %shift ; AVX2: Found an estimated cost of 14 for instruction: %shift
; AVX512: Found an estimated cost of 14 for instruction: %shift ; AVX512F: Found an estimated cost of 14 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 2 for instruction: %shift ; XOP: Found an estimated cost of 2 for instruction: %shift
%shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7> %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
ret <8 x i16> %shift ret <8 x i16> %shift
@ -449,7 +452,8 @@ define <16 x i16> @constant_shift_v16i16(<16 x i16> %a) {
; SSE41: Found an estimated cost of 28 for instruction: %shift ; SSE41: Found an estimated cost of 28 for instruction: %shift
; AVX: Found an estimated cost of 28 for instruction: %shift ; AVX: Found an estimated cost of 28 for instruction: %shift
; AVX2: Found an estimated cost of 10 for instruction: %shift ; AVX2: Found an estimated cost of 10 for instruction: %shift
; AVX512: Found an estimated cost of 10 for instruction: %shift ; AVX512F: Found an estimated cost of 10 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 4 for instruction: %shift ; XOP: Found an estimated cost of 4 for instruction: %shift
%shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7> %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
ret <16 x i16> %shift ret <16 x i16> %shift

6
test/Analysis/CostModel/X86/vshift-shl-cost.ll
View File

@ -102,7 +102,8 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) {
; SSE41: Found an estimated cost of 14 for instruction: %shift ; SSE41: Found an estimated cost of 14 for instruction: %shift
; AVX: Found an estimated cost of 14 for instruction: %shift ; AVX: Found an estimated cost of 14 for instruction: %shift
; AVX2: Found an estimated cost of 14 for instruction: %shift ; AVX2: Found an estimated cost of 14 for instruction: %shift
; AVX512: Found an estimated cost of 14 for instruction: %shift ; AVX512F: Found an estimated cost of 14 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 1 for instruction: %shift ; XOP: Found an estimated cost of 1 for instruction: %shift
%shift = shl <8 x i16> %a, %b %shift = shl <8 x i16> %a, %b
ret <8 x i16> %shift ret <8 x i16> %shift
@ -114,7 +115,8 @@ define <16 x i16> @var_shift_v16i16(<16 x i16> %a, <16 x i16> %b) {
; SSE41: Found an estimated cost of 28 for instruction: %shift ; SSE41: Found an estimated cost of 28 for instruction: %shift
; AVX: Found an estimated cost of 28 for instruction: %shift ; AVX: Found an estimated cost of 28 for instruction: %shift
; AVX2: Found an estimated cost of 10 for instruction: %shift ; AVX2: Found an estimated cost of 10 for instruction: %shift
; AVX512: Found an estimated cost of 10 for instruction: %shift ; AVX512F: Found an estimated cost of 10 for instruction: %shift
; AVX512BW: Found an estimated cost of 1 for instruction: %shift
; XOP: Found an estimated cost of 2 for instruction: %shift ; XOP: Found an estimated cost of 2 for instruction: %shift
%shift = shl <16 x i16> %a, %b %shift = shl <16 x i16> %a, %b
ret <16 x i16> %shift ret <16 x i16> %shift