mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
4892585b46
I think i've added exhaustive test coverage, and i have verified that alive2 is happy with all the tests,
so in principle i'm fine with landing this without review, but just in case..
This adds support for the "count active bits" pattern, i.e.:
```
int countActiveBits(unsigned val) {
int cnt = 0;
for( ; (val >> cnt) != 0; ++cnt)
;
return cnt;
}
```
but a somewhat more general one, since that is what i need:
```
int countActiveBits(unsigned val, int start, int off) {
int cnt;
for (cnt = start; val >> (cnt + off); cnt++)
;
return cnt;
}
```
I've followed in footstep of 'left-shift until bittest' idiom (D91038),
in the sense that iff the `ctlz` intrinsic is cheap, we'll transform,
regardless of all other factors.
This can have a shocking effect on certain benchmarks:
```
raw.pixls.us-unique/Olympus/XZ-1$ /repositories/googlebenchmark/tools/compare.py -a benchmarks ~/rawspeed/build-{old,new}/src/utilities/rsbench/rsbench --benchmark_counters_tabular=true --benchmark_min_time=0.00000001 --benchmark_repetitions=128 p1319978.orf
RUNNING: /home/lebedevri/rawspeed/build-old/src/utilities/rsbench/rsbench --benchmark_counters_tabular=true --benchmark_min_time=0.00000001 --benchmark_repetitions=128 p1319978.orf --benchmark_display_aggregates_only=true --benchmark_out=/tmp/tmp49_28zcm
2021-05-09T01:06:05+03:00
Running /home/lebedevri/rawspeed/build-old/src/utilities/rsbench/rsbench
Run on (32 X 3600.24 MHz CPU s)
CPU Caches:
L1 Data 32 KiB (x16)
L1 Instruction 32 KiB (x16)
L2 Unified 512 KiB (x16)
L3 Unified 32768 KiB (x2)
Load Average: 5.26, 6.29, 3.49
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations CPUTime,s CPUTime/WallTime Pixels Pixels/CPUTime Pixels/WallTime Raws/CPUTime Raws/WallTime WallTime,s
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
p1319978.orf/threads:32/process_time/real_time_mean 145 ms 145 ms 128 0.145319 0.999981 10.1568M 69.8949M 69.8936M 6.88159 6.88146 0.145322
p1319978.orf/threads:32/process_time/real_time_median 145 ms 145 ms 128 0.145317 0.999986 10.1568M 69.8941M 69.8931M 6.88151 6.88141 0.145319
p1319978.orf/threads:32/process_time/real_time_stddev 0.766 ms 0.766 ms 128 766.586u 15.1302u 0 354.167k 354.098k 0.0348699 0.0348631 766.469u
RUNNING: /home/lebedevri/rawspeed/build-new/src/utilities/rsbench/rsbench --benchmark_counters_tabular=true --benchmark_min_time=0.00000001 --benchmark_repetitions=128 p1319978.orf --benchmark_display_aggregates_only=true --benchmark_out=/tmp/tmpwb9sw2x0
2021-05-09T01:06:24+03:00
Running /home/lebedevri/rawspeed/build-new/src/utilities/rsbench/rsbench
Run on (32 X 3599.95 MHz CPU s)
CPU Caches:
L1 Data 32 KiB (x16)
L1 Instruction 32 KiB (x16)
L2 Unified 512 KiB (x16)
L3 Unified 32768 KiB (x2)
Load Average: 4.05, 5.95, 3.43
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations CPUTime,s CPUTime/WallTime Pixels Pixels/CPUTime Pixels/WallTime Raws/CPUTime Raws/WallTime WallTime,s
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
p1319978.orf/threads:32/process_time/real_time_mean 99.8 ms 99.8 ms 128 0.0997758 0.999972 10.1568M 101.797M 101.794M 10.0225 10.0222 0.0997786
p1319978.orf/threads:32/process_time/real_time_median 99.7 ms 99.7 ms 128 0.0997165 0.999985 10.1568M 101.857M 101.854M 10.0284 10.0281 0.0997195
p1319978.orf/threads:32/process_time/real_time_stddev 0.224 ms 0.224 ms 128 224.166u 34.345u 0 226.81k 227.231k 0.0223309 0.0223723 224.586u
Comparing /home/lebedevri/rawspeed/build-old/src/utilities/rsbench/rsbench to /home/lebedevri/rawspeed/build-new/src/utilities/rsbench/rsbench
Benchmark Time CPU Time Old Time New CPU Old CPU New
----------------------------------------------------------------------------------------------------------------------------------------------------
p1319978.orf/threads:32/process_time/real_time_pvalue 0.0000 0.0000 U Test, Repetitions: 128 vs 128
p1319978.orf/threads:32/process_time/real_time_mean -0.3134 -0.3134 145 100 145 100
p1319978.orf/threads:32/process_time/real_time_median -0.3138 -0.3138 145 100 145 100
p1319978.orf/threads:32/process_time/real_time_stddev -0.7073 -0.7078 1 0 1 0
```
Reviewed By: craig.topper, zhuhan0
Differential Revision: https://reviews.llvm.org/D102116
72 lines
4.9 KiB
LLVM
72 lines
4.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -debugify -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s
|
|
|
|
declare void @escape_inner(i8, i8, i8, i1, i8)
|
|
declare void @escape_outer(i8, i8, i8, i1, i8)
|
|
|
|
define i8 @p(i8 %val, i8 %start, i8 %extraoffset) {
|
|
; CHECK-LABEL: @p(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[VAL_NUMLEADINGZEROS:%.*]] = call i8 @llvm.ctlz.i8(i8 [[VAL:%.*]], i1 false), !dbg [[DBG20:![0-9]+]]
|
|
; CHECK-NEXT: [[VAL_NUMACTIVEBITS:%.*]] = sub nuw nsw i8 8, [[VAL_NUMLEADINGZEROS]], !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = sub i8 0, [[EXTRAOFFSET:%.*]], !dbg [[DBG21:![0-9]+]]
|
|
; CHECK-NEXT: [[VAL_NUMACTIVEBITS_OFFSET:%.*]] = add nsw i8 [[VAL_NUMACTIVEBITS]], [[TMP0]], !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[IV_FINAL:%.*]] = call i8 @llvm.smax.i8(i8 [[VAL_NUMACTIVEBITS_OFFSET]], i8 [[START:%.*]]), !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[LOOP_BACKEDGETAKENCOUNT:%.*]] = sub nsw i8 [[IV_FINAL]], [[START]], !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[LOOP_TRIPCOUNT:%.*]] = add nuw nsw i8 [[LOOP_BACKEDGETAKENCOUNT]], 1, !dbg [[DBG20]]
|
|
; CHECK-NEXT: br label [[LOOP:%.*]], !dbg [[DBG21]]
|
|
; CHECK: loop:
|
|
; CHECK-NEXT: [[LOOP_IV:%.*]] = phi i8 [ 0, [[ENTRY:%.*]] ], [ [[LOOP_IV_NEXT:%.*]], [[LOOP]] ], !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[LOOP_IV_NEXT]] = add nuw nsw i8 [[LOOP_IV]], 1, !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[LOOP_IVCHECK:%.*]] = icmp eq i8 [[LOOP_IV_NEXT]], [[LOOP_TRIPCOUNT]], !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[IV:%.*]] = add nsw i8 [[LOOP_IV]], [[START]], !dbg [[DBG20]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[IV]], metadata [[META9:![0-9]+]], metadata !DIExpression()), !dbg [[DBG20]]
|
|
; CHECK-NEXT: [[NBITS:%.*]] = add nsw i8 [[IV]], [[EXTRAOFFSET]], !dbg [[DBG22:![0-9]+]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[NBITS]], metadata [[META11:![0-9]+]], metadata !DIExpression()), !dbg [[DBG22]]
|
|
; CHECK-NEXT: [[VAL_SHIFTED:%.*]] = lshr i8 [[VAL]], [[NBITS]], !dbg [[DBG23:![0-9]+]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[VAL_SHIFTED]], metadata [[META12:![0-9]+]], metadata !DIExpression()), !dbg [[DBG23]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[LOOP_IVCHECK]], metadata [[META13:![0-9]+]], metadata !DIExpression()), !dbg [[DBG24:![0-9]+]]
|
|
; CHECK-NEXT: [[IV_NEXT:%.*]] = add i8 [[IV]], 1, !dbg [[DBG25:![0-9]+]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[IV_NEXT]], metadata [[META14:![0-9]+]], metadata !DIExpression()), !dbg [[DBG25]]
|
|
; CHECK-NEXT: call void @escape_inner(i8 [[IV]], i8 [[NBITS]], i8 [[VAL_SHIFTED]], i1 [[LOOP_IVCHECK]], i8 [[IV_NEXT]]), !dbg [[DBG26:![0-9]+]]
|
|
; CHECK-NEXT: br i1 [[LOOP_IVCHECK]], label [[END:%.*]], label [[LOOP]], !dbg [[DBG27:![0-9]+]]
|
|
; CHECK: end:
|
|
; CHECK-NEXT: [[IV_RES:%.*]] = phi i8 [ [[IV_FINAL]], [[LOOP]] ], !dbg [[DBG28:![0-9]+]]
|
|
; CHECK-NEXT: [[NBITS_RES:%.*]] = phi i8 [ [[NBITS]], [[LOOP]] ], !dbg [[DBG29:![0-9]+]]
|
|
; CHECK-NEXT: [[VAL_SHIFTED_RES:%.*]] = phi i8 [ [[VAL_SHIFTED]], [[LOOP]] ], !dbg [[DBG30:![0-9]+]]
|
|
; CHECK-NEXT: [[VAL_SHIFTED_ISZERO_RES:%.*]] = phi i1 [ [[LOOP_IVCHECK]], [[LOOP]] ], !dbg [[DBG31:![0-9]+]]
|
|
; CHECK-NEXT: [[IV_NEXT_RES:%.*]] = phi i8 [ [[IV_NEXT]], [[LOOP]] ], !dbg [[DBG32:![0-9]+]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[IV_RES]], metadata [[META15:![0-9]+]], metadata !DIExpression()), !dbg [[DBG28]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[NBITS_RES]], metadata [[META16:![0-9]+]], metadata !DIExpression()), !dbg [[DBG29]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[VAL_SHIFTED_RES]], metadata [[META17:![0-9]+]], metadata !DIExpression()), !dbg [[DBG30]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[VAL_SHIFTED_ISZERO_RES]], metadata [[META18:![0-9]+]], metadata !DIExpression()), !dbg [[DBG31]]
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[IV_NEXT_RES]], metadata [[META19:![0-9]+]], metadata !DIExpression()), !dbg [[DBG32]]
|
|
; CHECK-NEXT: call void @escape_outer(i8 [[IV_RES]], i8 [[NBITS_RES]], i8 [[VAL_SHIFTED_RES]], i1 [[VAL_SHIFTED_ISZERO_RES]], i8 [[IV_NEXT_RES]]), !dbg [[DBG33:![0-9]+]]
|
|
; CHECK-NEXT: ret i8 [[IV_RES]], !dbg [[DBG34:![0-9]+]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i8 [ %start, %entry ], [ %iv.next, %loop ]
|
|
%nbits = add nsw i8 %iv, %extraoffset
|
|
%val.shifted = lshr i8 %val, %nbits
|
|
%val.shifted.iszero = icmp eq i8 %val.shifted, 0
|
|
%iv.next = add i8 %iv, 1
|
|
|
|
call void @escape_inner(i8 %iv, i8 %nbits, i8 %val.shifted, i1 %val.shifted.iszero, i8 %iv.next)
|
|
|
|
br i1 %val.shifted.iszero, label %end, label %loop
|
|
|
|
end:
|
|
%iv.res = phi i8 [ %iv, %loop ]
|
|
%nbits.res = phi i8 [ %nbits, %loop ]
|
|
%val.shifted.res = phi i8 [ %val.shifted, %loop ]
|
|
%val.shifted.iszero.res = phi i1 [ %val.shifted.iszero, %loop ]
|
|
%iv.next.res = phi i8 [ %iv.next, %loop ]
|
|
|
|
call void @escape_outer(i8 %iv.res, i8 %nbits.res, i8 %val.shifted.res, i1 %val.shifted.iszero.res, i8 %iv.next.res)
|
|
|
|
ret i8 %iv.res
|
|
}
|