2014-09-16 15:57:37 +08:00
|
|
|
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=knl | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AVX512
|
2014-02-07 02:18:36 +08:00
|
|
|
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core-avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AVX2
|
|
|
|
|
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AVX
|
2012-11-06 06:20:53 +08:00
|
|
|
|
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
|
target triple = "x86_64-apple-macosx10.8.0"
|
|
|
|
|
|
|
|
|
|
define i32 @add(i32 %arg) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-LABEL: for function 'add'
|
2012-11-06 06:20:53 +08:00
|
|
|
; -- Same size registeres --
|
|
|
|
|
;CHECK: cost of 1 {{.*}} zext
|
|
|
|
|
%A = zext <4 x i1> undef to <4 x i32>
|
|
|
|
|
;CHECK: cost of 2 {{.*}} sext
|
|
|
|
|
%B = sext <4 x i1> undef to <4 x i32>
|
|
|
|
|
;CHECK: cost of 0 {{.*}} trunc
|
|
|
|
|
%C = trunc <4 x i32> undef to <4 x i1>
|
|
|
|
|
|
|
|
|
|
; -- Different size registers --
|
|
|
|
|
;CHECK-NOT: cost of 1 {{.*}} zext
|
|
|
|
|
%D = zext <8 x i1> undef to <8 x i32>
|
|
|
|
|
;CHECK-NOT: cost of 2 {{.*}} sext
|
|
|
|
|
%E = sext <8 x i1> undef to <8 x i32>
|
|
|
|
|
;CHECK-NOT: cost of 2 {{.*}} trunc
|
|
|
|
|
%F = trunc <8 x i32> undef to <8 x i1>
|
|
|
|
|
|
|
|
|
|
; -- scalars --
|
|
|
|
|
|
|
|
|
|
;CHECK: cost of 1 {{.*}} zext
|
|
|
|
|
%G = zext i1 undef to i32
|
|
|
|
|
;CHECK: cost of 0 {{.*}} trunc
|
|
|
|
|
%H = trunc i32 undef to i1
|
|
|
|
|
|
2012-12-06 05:21:26 +08:00
|
|
|
;CHECK: cost of 0 {{.*}} ret
|
2012-11-06 06:20:53 +08:00
|
|
|
ret i32 undef
|
|
|
|
|
}
|
|
|
|
|
|
2012-11-07 03:33:53 +08:00
|
|
|
define i32 @zext_sext(<8 x i1> %in) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-AVX2-LABEL: for function 'zext_sext'
|
|
|
|
|
; CHECK-AVX-LABEL: for function 'zext_sext'
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
2012-11-07 03:33:53 +08:00
|
|
|
%Z = zext <8 x i1> %in to <8 x i32>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 7 {{.*}} sext
|
2012-11-07 03:33:53 +08:00
|
|
|
%S = sext <8 x i1> %in to <8 x i32>
|
|
|
|
|
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 1 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
2013-10-24 05:06:07 +08:00
|
|
|
%A1 = zext <16 x i8> undef to <16 x i16>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 1 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} sext
|
2013-10-24 05:06:07 +08:00
|
|
|
%A2 = sext <16 x i8> undef to <16 x i16>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 1 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} sext
|
2012-11-07 03:33:53 +08:00
|
|
|
%A = sext <8 x i16> undef to <8 x i32>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 1 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
2012-11-07 03:33:53 +08:00
|
|
|
%B = zext <8 x i16> undef to <8 x i32>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 1 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} sext
|
2012-11-07 03:33:53 +08:00
|
|
|
%C = sext <4 x i32> undef to <4 x i64>
|
|
|
|
|
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
|
|
|
|
%C.v8i8.z = zext <8 x i8> undef to <8 x i32>
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 7 {{.*}} sext
|
|
|
|
|
%C.v8i8.s = sext <8 x i8> undef to <8 x i32>
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 3 {{.*}} zext
|
|
|
|
|
%C.v4i16.z = zext <4 x i16> undef to <4 x i64>
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 6 {{.*}} sext
|
|
|
|
|
%C.v4i16.s = sext <4 x i16> undef to <4 x i64>
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
|
|
|
|
%C.v4i8.z = zext <4 x i8> undef to <4 x i64>
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 6 {{.*}} sext
|
|
|
|
|
%C.v4i8.s = sext <4 x i8> undef to <4 x i64>
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX2: cost of 1 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
2012-11-07 03:33:53 +08:00
|
|
|
%D = zext <4 x i32> undef to <4 x i64>
|
|
|
|
|
|
2014-09-16 15:57:37 +08:00
|
|
|
;CHECK-AVX512: cost of 3 {{.*}} %D1 = zext
|
|
|
|
|
%D1 = zext <16 x i32> undef to <16 x i64>
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX512: cost of 3 {{.*}} %D2 = sext
|
|
|
|
|
%D2 = sext <16 x i32> undef to <16 x i64>
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX512: cost of 1 {{.*}} %D3 = zext
|
|
|
|
|
%D3 = zext <16 x i16> undef to <16 x i32>
|
|
|
|
|
;CHECK-AVX512: cost of 1 {{.*}} %D4 = zext
|
|
|
|
|
%D4 = zext <16 x i8> undef to <16 x i32>
|
|
|
|
|
;CHECK-AVX512: cost of 2 {{.*}} %D5 = zext
|
|
|
|
|
%D5 = zext <16 x i1> undef to <16 x i32>
|
|
|
|
|
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 2 {{.*}} trunc
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} trunc
|
2012-11-07 03:33:53 +08:00
|
|
|
%E = trunc <4 x i64> undef to <4 x i32>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 2 {{.*}} trunc
|
|
|
|
|
;CHECK-AVX: cost of 5 {{.*}} trunc
|
2012-11-07 03:33:53 +08:00
|
|
|
%F = trunc <8 x i32> undef to <8 x i16>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 4 {{.*}} trunc
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} trunc
|
2013-10-24 05:06:07 +08:00
|
|
|
%F1 = trunc <16 x i16> undef to <16 x i8>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 2 {{.*}} trunc
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} trunc
|
|
|
|
|
%F2 = trunc <8 x i32> undef to <8 x i8>
|
|
|
|
|
;CHECK-AVX2: cost of 2 {{.*}} trunc
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} trunc
|
|
|
|
|
%F3 = trunc <4 x i64> undef to <4 x i8>
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX2: cost of 4 {{.*}} trunc
|
|
|
|
|
;CHECK-AVX: cost of 9 {{.*}} trunc
|
2014-09-16 15:57:37 +08:00
|
|
|
;CHECK_AVX512: cost of 1 {{.*}} G = trunc
|
2012-11-07 05:17:17 +08:00
|
|
|
%G = trunc <8 x i64> undef to <8 x i32>
|
|
|
|
|
|
2014-09-16 15:57:37 +08:00
|
|
|
;CHECK-AVX512: cost of 4 {{.*}} %G1 = trunc
|
|
|
|
|
%G1 = trunc <16 x i64> undef to <16 x i32>
|
|
|
|
|
|
2012-11-07 03:33:53 +08:00
|
|
|
ret i32 undef
|
|
|
|
|
}
|
|
|
|
|
|
2013-02-20 20:42:54 +08:00
|
|
|
define i32 @masks8(<8 x i1> %in) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-AVX2-LABEL: for function 'masks8'
|
|
|
|
|
; CHECK-AVX-LABEL: for function 'masks8'
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
2012-11-07 03:33:53 +08:00
|
|
|
%Z = zext <8 x i1> %in to <8 x i32>
|
2014-02-07 02:18:36 +08:00
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 7 {{.*}} sext
|
2012-11-07 03:33:53 +08:00
|
|
|
%S = sext <8 x i1> %in to <8 x i32>
|
|
|
|
|
ret i32 undef
|
|
|
|
|
}
|
|
|
|
|
|
2013-02-20 20:42:54 +08:00
|
|
|
define i32 @masks4(<4 x i1> %in) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-AVX2-LABEL: for function 'masks4'
|
|
|
|
|
; CHECK-AVX-LABEL: for function 'masks4'
|
|
|
|
|
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} zext
|
|
|
|
|
;CHECK-AVX: cost of 4 {{.*}} zext
|
|
|
|
|
%Z = zext <4 x i1> %in to <4 x i64>
|
|
|
|
|
;CHECK-AVX2: cost of 3 {{.*}} sext
|
|
|
|
|
;CHECK-AVX: cost of 6 {{.*}} sext
|
2013-02-20 20:42:54 +08:00
|
|
|
%S = sext <4 x i1> %in to <4 x i64>
|
|
|
|
|
ret i32 undef
|
|
|
|
|
}
|
|
|
|
|
|
2013-04-01 18:23:49 +08:00
|
|
|
define void @sitofp4(<4 x i1> %a, <4 x i8> %b, <4 x i16> %c, <4 x i32> %d) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-LABEL: for function 'sitofp4'
|
2013-04-01 18:23:49 +08:00
|
|
|
; CHECK: cost of 3 {{.*}} sitofp
|
|
|
|
|
%A1 = sitofp <4 x i1> %a to <4 x float>
|
|
|
|
|
; CHECK: cost of 3 {{.*}} sitofp
|
|
|
|
|
%A2 = sitofp <4 x i1> %a to <4 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 3 {{.*}} sitofp
|
|
|
|
|
%B1 = sitofp <4 x i8> %b to <4 x float>
|
|
|
|
|
; CHECK: cost of 3 {{.*}} sitofp
|
|
|
|
|
%B2 = sitofp <4 x i8> %b to <4 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 3 {{.*}} sitofp
|
|
|
|
|
%C1 = sitofp <4 x i16> %c to <4 x float>
|
|
|
|
|
; CHECK: cost of 3 {{.*}} sitofp
|
|
|
|
|
%C2 = sitofp <4 x i16> %c to <4 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 1 {{.*}} sitofp
|
|
|
|
|
%D1 = sitofp <4 x i32> %d to <4 x float>
|
|
|
|
|
; CHECK: cost of 1 {{.*}} sitofp
|
|
|
|
|
%D2 = sitofp <4 x i32> %d to <4 x double>
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @sitofp8(<8 x i1> %a, <8 x i8> %b, <8 x i16> %c, <8 x i32> %d) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-LABEL: for function 'sitofp8'
|
2013-04-01 18:23:49 +08:00
|
|
|
; CHECK: cost of 8 {{.*}} sitofp
|
|
|
|
|
%A1 = sitofp <8 x i1> %a to <8 x float>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 8 {{.*}} sitofp
|
|
|
|
|
%B1 = sitofp <8 x i8> %b to <8 x float>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 5 {{.*}} sitofp
|
|
|
|
|
%C1 = sitofp <8 x i16> %c to <8 x float>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 1 {{.*}} sitofp
|
|
|
|
|
%D1 = sitofp <8 x i32> %d to <8 x float>
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @uitofp4(<4 x i1> %a, <4 x i8> %b, <4 x i16> %c, <4 x i32> %d) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-LABEL: for function 'uitofp4'
|
2013-04-01 18:23:49 +08:00
|
|
|
; CHECK: cost of 7 {{.*}} uitofp
|
|
|
|
|
%A1 = uitofp <4 x i1> %a to <4 x float>
|
|
|
|
|
; CHECK: cost of 7 {{.*}} uitofp
|
|
|
|
|
%A2 = uitofp <4 x i1> %a to <4 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 2 {{.*}} uitofp
|
|
|
|
|
%B1 = uitofp <4 x i8> %b to <4 x float>
|
|
|
|
|
; CHECK: cost of 2 {{.*}} uitofp
|
|
|
|
|
%B2 = uitofp <4 x i8> %b to <4 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 2 {{.*}} uitofp
|
|
|
|
|
%C1 = uitofp <4 x i16> %c to <4 x float>
|
|
|
|
|
; CHECK: cost of 2 {{.*}} uitofp
|
|
|
|
|
%C2 = uitofp <4 x i16> %c to <4 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 6 {{.*}} uitofp
|
|
|
|
|
%D1 = uitofp <4 x i32> %d to <4 x float>
|
|
|
|
|
; CHECK: cost of 6 {{.*}} uitofp
|
|
|
|
|
%D2 = uitofp <4 x i32> %d to <4 x double>
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @uitofp8(<8 x i1> %a, <8 x i8> %b, <8 x i16> %c, <8 x i32> %d) {
|
2014-02-07 02:18:36 +08:00
|
|
|
; CHECK-LABEL: for function 'uitofp8'
|
2013-04-01 18:23:49 +08:00
|
|
|
; CHECK: cost of 6 {{.*}} uitofp
|
|
|
|
|
%A1 = uitofp <8 x i1> %a to <8 x float>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 5 {{.*}} uitofp
|
|
|
|
|
%B1 = uitofp <8 x i8> %b to <8 x float>
|
|
|
|
|
|
|
|
|
|
; CHECK: cost of 5 {{.*}} uitofp
|
|
|
|
|
%C1 = uitofp <8 x i16> %c to <8 x float>
|
|
|
|
|
|
[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
|
|
|
; CHECK-AVX2: cost of 8 {{.*}} uitofp
|
|
|
|
|
; CHECK-AVX512: cost of 8 {{.*}} uitofp
|
|
|
|
|
; CHECK-AVX: cost of 9 {{.*}} uitofp
|
2013-04-01 18:23:49 +08:00
|
|
|
%D1 = uitofp <8 x i32> %d to <8 x float>
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2014-09-16 15:57:37 +08:00
|
|
|
|
|
|
|
|
define void @fp_conv(<8 x float> %a, <16 x float>%b) {
|
|
|
|
|
;CHECK-LABEL: for function 'fp_conv'
|
|
|
|
|
; CHECK-AVX512: cost of 1 {{.*}} fpext
|
|
|
|
|
%A1 = fpext <8 x float> %a to <8 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK-AVX512: cost of 3 {{.*}} fpext
|
|
|
|
|
%A2 = fpext <16 x float> %b to <16 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK-AVX2: cost of 3 {{.*}} %A3 = fpext
|
|
|
|
|
; CHECK-AVX512: cost of 1 {{.*}} %A3 = fpext
|
|
|
|
|
%A3 = fpext <8 x float> %a to <8 x double>
|
|
|
|
|
|
|
|
|
|
; CHECK-AVX2: cost of 3 {{.*}} %A4 = fptrunc
|
|
|
|
|
; CHECK-AVX512: cost of 1 {{.*}} %A4 = fptrunc
|
|
|
|
|
%A4 = fptrunc <8 x double> undef to <8 x float>
|
|
|
|
|
|
|
|
|
|
; CHECK-AVX512: cost of 3 {{.*}} %A5 = fptrunc
|
|
|
|
|
%A5 = fptrunc <16 x double> undef to <16 x float>
|
|
|
|
|
ret void
|
|
|
|
|
}
|