T0b1/wasmtime
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add x86 SIMD implementation of float comparison

Browse Source
This commit is contained in:
Andrew Brown
2019-10-28 13:26:21 -07:00
parent e5a36e2c61
commit d32301854d
5 changed files with 122 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
cranelift/filetests/filetests/isa/x86/simd-comparison-binemit.clif
View File

@@ -52,3 +52,29 @@ ebb0(v0: i32x4 [%xmm2], v1: i32x4 [%xmm4]):
[-, %xmm2] v5 = x86_pminu v0, v1 ; bin: 66 0f 38 3b d4
return
}
function %fcmp_f32x4(f32x4, f32x4) {
ebb0(v0: f32x4 [%xmm2], v1: f32x4 [%xmm4]):
[-, %xmm2] v2 = fcmp eq v0, v1 ; bin: 40 0f c2 d4 00
[-, %xmm2] v3 = fcmp lt v0, v1 ; bin: 40 0f c2 d4 01
[-, %xmm2] v4 = fcmp le v0, v1 ; bin: 40 0f c2 d4 02
[-, %xmm2] v5 = fcmp uno v0, v1 ; bin: 40 0f c2 d4 03
[-, %xmm2] v6 = fcmp ne v0, v1 ; bin: 40 0f c2 d4 04
[-, %xmm2] v7 = fcmp ge v0, v1 ; bin: 40 0f c2 d4 05
[-, %xmm2] v8 = fcmp gt v0, v1 ; bin: 40 0f c2 d4 06
[-, %xmm2] v9 = fcmp ord v0, v1 ; bin: 40 0f c2 d4 07
return
}
function %fcmp_f64x2(f64x2, f64x2) {
ebb0(v0: f64x2 [%xmm2], v1: f64x2 [%xmm0]):
[-, %xmm2] v2 = fcmp eq v0, v1 ; bin: 66 40 0f c2 d0 00
[-, %xmm2] v3 = fcmp lt v0, v1 ; bin: 66 40 0f c2 d0 01
[-, %xmm2] v4 = fcmp le v0, v1 ; bin: 66 40 0f c2 d0 02
[-, %xmm2] v5 = fcmp uno v0, v1 ; bin: 66 40 0f c2 d0 03
[-, %xmm2] v6 = fcmp ne v0, v1 ; bin: 66 40 0f c2 d0 04
[-, %xmm2] v7 = fcmp ge v0, v1 ; bin: 66 40 0f c2 d0 05
[-, %xmm2] v8 = fcmp gt v0, v1 ; bin: 66 40 0f c2 d0 06
[-, %xmm2] v9 = fcmp ord v0, v1 ; bin: 66 40 0f c2 d0 07
return
}

40
cranelift/filetests/filetests/isa/x86/simd-comparison-run.clif
View File

@@ -177,3 +177,43 @@ ebb0:
return v8
}
; run
function %fcmp_eq_f32x4() -> b1 {
ebb0:
v0 = vconst.f32x4 [0.0 -0x4.2 0x0.33333 -0.0]
v1 = vconst.f32x4 [0.0 -0x4.2 0x0.33333 -0.0]
v2 = fcmp eq v0, v1
v8 = vall_true v2
return v8
}
; run
function %fcmp_lt_f32x4() -> b1 {
ebb0:
v0 = vconst.f32x4 [0.0 -0x4.2 0x0.0 -0.0]
v1 = vconst.f32x4 [0x0.001 0x4.2 0x0.33333 0x1.0]
v2 = fcmp lt v0, v1
v8 = vall_true v2
return v8
}
; run
function %fcmp_ge_f64x2() -> b1 {
ebb0:
v0 = vconst.f64x2 [0x0.0 0x4.2]
v1 = vconst.f64x2 [0.0 0x4.1]
v2 = fcmp ge v0, v1
v8 = vall_true v2
return v8
}
; run
function %fcmp_uno_f64x2() -> b1 {
ebb0:
v0 = vconst.f64x2 [0.0 NaN]
v1 = vconst.f64x2 [NaN 0x4.1]
v2 = fcmp uno v0, v1
v8 = vall_true v2
return v8
}
; run