2013-03-13 00:27:52 +08:00
|
|
|
; REQUIRES: asserts
|
[X86] Custom lower UINT_TO_FP from v4f32 to v4i32, and for v8f32 to v8i32 if
AVX2 is available.
According to IACA, the new lowering has a throughput of 8 cycles instead of 13
with the previous one.
Althought this lowering kicks in some SPECs benchmarks, the performance
improvement was within the noise.
Correctness testing has been done for the whole range of uint32_t with the
following program:
uint4 v = (uint4) {0,1,2,3};
uint32_t i;
//Check correctness over entire range for uint4 -> float4 conversion
for( i = 0; i < 1U << (32-2); i++ )
{
float4 t = test(v);
float4 c = correct(v);
if( 0xf != _mm_movemask_ps( t == c ))
{
printf( "Error @ %vx: %vf vs. %vf\n", v, c, t);
return -1;
}
v += 4;
}
Where "correct" is the old lowering and "test" the new one.
The patch adds a test case for the two custom lowering instruction.
It also modifies the vector cost model, which is why cast.ll and uitofp.ll are
modified.
2009-02-26-MachineLICMBug.ll is also modified because we now hoist 7
instructions instead of 4 (3 more constant loads).
rdar://problem/18153096>
llvm-svn: 221657
2014-11-11 10:23:47 +08:00
|
|
|
; RUN: llc < %s -march=x86-64 -mattr=+sse3,+sse4.1 -mcpu=penryn -stats 2>&1 | grep "7 machine-licm"
|
2013-08-24 04:39:19 +08:00
|
|
|
; RUN: llc < %s -march=x86-64 -mattr=+sse3,+sse4.1 -mcpu=penryn | FileCheck %s
|
2009-02-27 08:02:22 +08:00
|
|
|
; rdar://6627786
|
2010-03-26 08:07:25 +08:00
|
|
|
; rdar://7792037
|
2009-02-27 08:02:22 +08:00
|
|
|
|
|
|
|
|
target triple = "x86_64-apple-darwin10.0"
|
|
|
|
|
%struct.Key = type { i64 }
|
|
|
|
|
%struct.__Rec = type opaque
|
|
|
|
|
%struct.__vv = type { }
|
|
|
|
|
|
2010-01-12 01:23:56 +08:00
|
|
|
define %struct.__vv* @t(%struct.Key* %desc, i64 %p) nounwind ssp {
|
2009-02-27 08:02:22 +08:00
|
|
|
entry:
|
|
|
|
|
br label %bb4
|
|
|
|
|
|
|
|
|
|
bb4: ; preds = %bb.i, %bb26, %bb4, %entry
|
2010-03-26 08:07:25 +08:00
|
|
|
; CHECK: %bb4
|
2013-05-30 21:19:42 +08:00
|
|
|
; CHECK: xorl
|
2010-03-26 08:07:25 +08:00
|
|
|
; CHECK: callq
|
|
|
|
|
; CHECK: xorl
|
2013-05-30 21:19:42 +08:00
|
|
|
; CHECK: xorl
|
2013-10-16 07:33:07 +08:00
|
|
|
; CHECK: movq
|
2010-03-26 08:07:25 +08:00
|
|
|
|
2009-02-27 08:02:22 +08:00
|
|
|
%0 = call i32 (...)* @xxGetOffsetForCode(i32 undef) nounwind ; <i32> [#uses=0]
|
2010-01-12 01:23:56 +08:00
|
|
|
%ins = or i64 %p, 2097152 ; <i64> [#uses=1]
|
2009-02-27 08:02:22 +08:00
|
|
|
%1 = call i32 (...)* @xxCalculateMidType(%struct.Key* %desc, i32 0) nounwind ; <i32> [#uses=1]
|
|
|
|
|
%cond = icmp eq i32 %1, 1 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cond, label %bb26, label %bb4
|
|
|
|
|
|
|
|
|
|
bb26: ; preds = %bb4
|
|
|
|
|
%2 = and i64 %ins, 15728640 ; <i64> [#uses=1]
|
|
|
|
|
%cond.i = icmp eq i64 %2, 1048576 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cond.i, label %bb.i, label %bb4
|
|
|
|
|
|
|
|
|
|
bb.i: ; preds = %bb26
|
|
|
|
|
%3 = load i32* null, align 4 ; <i32> [#uses=1]
|
|
|
|
|
%4 = uitofp i32 %3 to float ; <float> [#uses=1]
|
|
|
|
|
%.sum13.i = add i64 0, 4 ; <i64> [#uses=1]
|
|
|
|
|
%5 = getelementptr i8* null, i64 %.sum13.i ; <i8*> [#uses=1]
|
|
|
|
|
%6 = bitcast i8* %5 to i32* ; <i32*> [#uses=1]
|
|
|
|
|
%7 = load i32* %6, align 4 ; <i32> [#uses=1]
|
|
|
|
|
%8 = uitofp i32 %7 to float ; <float> [#uses=1]
|
|
|
|
|
%.sum.i = add i64 0, 8 ; <i64> [#uses=1]
|
|
|
|
|
%9 = getelementptr i8* null, i64 %.sum.i ; <i8*> [#uses=1]
|
|
|
|
|
%10 = bitcast i8* %9 to i32* ; <i32*> [#uses=1]
|
|
|
|
|
%11 = load i32* %10, align 4 ; <i32> [#uses=1]
|
|
|
|
|
%12 = uitofp i32 %11 to float ; <float> [#uses=1]
|
|
|
|
|
%13 = insertelement <4 x float> undef, float %4, i32 0 ; <<4 x float>> [#uses=1]
|
|
|
|
|
%14 = insertelement <4 x float> %13, float %8, i32 1 ; <<4 x float>> [#uses=1]
|
|
|
|
|
%15 = insertelement <4 x float> %14, float %12, i32 2 ; <<4 x float>> [#uses=1]
|
|
|
|
|
store <4 x float> %15, <4 x float>* null, align 16
|
|
|
|
|
br label %bb4
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i32 @xxGetOffsetForCode(...)
|
|
|
|
|
|
|
|
|
|
declare i32 @xxCalculateMidType(...)
|