indent loop so it stands out
Change-Id: Iea0f804b1b2fed9e663e45c33fb54a91b10fd07b Reviewed-on: https://skia-review.googlesource.com/c/skia/+/252652 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
This commit is contained in:
Mike Klein
parent
f3d4109a79
commit
e8356ad35d
18
gm/skvm.cpp
18
gm/skvm.cpp
@ -94,7 +94,7 @@ DEF_SIMPLE_GM(SkVMBlitter, canvas, 100, 100) {
|
||||
r1 = pack r0 r1 8
|
||||
r1 = pack r3 r1 16
|
||||
loop:
|
||||
store32 arg(1) r1
|
||||
store32 arg(1) r1
|
||||
*/
|
||||
p.setShader(SkShaders::Color(SK_ColorBLUE));
|
||||
canvas->drawRect({0,0, 50,50}, p);
|
||||
@ -120,14 +120,14 @@ DEF_SIMPLE_GM(SkVMBlitter, canvas, 100, 100) {
|
||||
r4 = extract r4 16 r3 // extract blue
|
||||
r3 = pack r4 r3 8 // r3 = blue and alpha from color shader
|
||||
loop:
|
||||
r4 = index
|
||||
r4 = sub_i32 r0 r4 // r4 = x
|
||||
r4 = to_f32 r4
|
||||
r4 = mul_f32 r4 r2
|
||||
r4 = to_i32 r4 // r4 = green channel, depends on x, is varying
|
||||
r4 = pack r1 r4 8
|
||||
r4 = pack r4 r3 16
|
||||
store32 arg(1) r4
|
||||
r4 = index
|
||||
r4 = sub_i32 r0 r4 // r4 = x
|
||||
r4 = to_f32 r4
|
||||
r4 = mul_f32 r4 r2
|
||||
r4 = to_i32 r4 // r4 = green channel, depends on x, is varying
|
||||
r4 = pack r1 r4 8
|
||||
r4 = pack r4 r3 16
|
||||
store32 arg(1) r4
|
||||
*/
|
||||
p.setShader(sk_make_sp<Fade>(SkShaders::Color(SK_ColorYELLOW)));
|
||||
canvas->drawRect({50,0, 100,50}, p);
|
||||
|
||||
@ -22,17 +22,17 @@ r1 = splat 3F800000 (1)
|
||||
r2 = splat 437F0000 (255)
|
||||
r3 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r4 = load8 arg(0)
|
||||
r4 = to_f32 r4
|
||||
r4 = mul_f32 r0 r4
|
||||
r5 = load8 arg(1)
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r6 = sub_f32 r1 r4
|
||||
r4 = mad_f32 r5 r6 r4
|
||||
r4 = mad_f32 r4 r2 r3
|
||||
r4 = to_i32 r4
|
||||
store8 arg(1) r4
|
||||
r4 = load8 arg(0)
|
||||
r4 = to_f32 r4
|
||||
r4 = mul_f32 r0 r4
|
||||
r5 = load8 arg(1)
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r6 = sub_f32 r1 r4
|
||||
r4 = mad_f32 r5 r6 r4
|
||||
r4 = mad_f32 r4 r2 r3
|
||||
r4 = to_i32 r4
|
||||
store8 arg(1) r4
|
||||
|
||||
A8 over G8
|
||||
21 values:
|
||||
@ -67,20 +67,20 @@ r4 = splat 3D93DD98 (0.0722)
|
||||
r5 = splat 437F0000 (255)
|
||||
r6 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r7 = load8 arg(1)
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r8 = load8 arg(0)
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r8 = sub_f32 r1 r8
|
||||
r8 = mul_f32 r7 r8
|
||||
r7 = mul_f32 r8 r4
|
||||
r7 = mad_f32 r8 r3 r7
|
||||
r7 = mad_f32 r8 r2 r7
|
||||
r7 = mad_f32 r7 r5 r6
|
||||
r7 = to_i32 r7
|
||||
store8 arg(1) r7
|
||||
r7 = load8 arg(1)
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r8 = load8 arg(0)
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r8 = sub_f32 r1 r8
|
||||
r8 = mul_f32 r7 r8
|
||||
r7 = mul_f32 r8 r4
|
||||
r7 = mad_f32 r8 r3 r7
|
||||
r7 = mad_f32 r8 r2 r7
|
||||
r7 = mad_f32 r7 r5 r6
|
||||
r7 = to_i32 r7
|
||||
store8 arg(1) r7
|
||||
|
||||
A8 over RGBA_8888
|
||||
38 values:
|
||||
@ -130,39 +130,39 @@ r2 = splat 3F800000 (1)
|
||||
r3 = splat 437F0000 (255)
|
||||
r4 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r5 = load32 arg(1)
|
||||
r6 = extract r5 0 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = load8 arg(0)
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r8 = sub_f32 r2 r7
|
||||
r6 = mul_f32 r6 r8
|
||||
r6 = mad_f32 r6 r3 r4
|
||||
r6 = to_i32 r6
|
||||
r9 = extract r5 8 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r9 = mul_f32 r9 r8
|
||||
r9 = mad_f32 r9 r3 r4
|
||||
r9 = to_i32 r9
|
||||
r9 = pack r6 r9 8
|
||||
r6 = extract r5 16 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r6 = mul_f32 r6 r8
|
||||
r6 = mad_f32 r6 r3 r4
|
||||
r6 = to_i32 r6
|
||||
r5 = extract r5 24 r1
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r7 = mad_f32 r5 r8 r7
|
||||
r7 = mad_f32 r7 r3 r4
|
||||
r7 = to_i32 r7
|
||||
r7 = pack r6 r7 8
|
||||
r7 = pack r9 r7 16
|
||||
store32 arg(1) r7
|
||||
r5 = load32 arg(1)
|
||||
r6 = extract r5 0 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = load8 arg(0)
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r8 = sub_f32 r2 r7
|
||||
r6 = mul_f32 r6 r8
|
||||
r6 = mad_f32 r6 r3 r4
|
||||
r6 = to_i32 r6
|
||||
r9 = extract r5 8 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r9 = mul_f32 r9 r8
|
||||
r9 = mad_f32 r9 r3 r4
|
||||
r9 = to_i32 r9
|
||||
r9 = pack r6 r9 8
|
||||
r6 = extract r5 16 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r6 = mul_f32 r6 r8
|
||||
r6 = mad_f32 r6 r3 r4
|
||||
r6 = to_i32 r6
|
||||
r5 = extract r5 24 r1
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r7 = mad_f32 r5 r8 r7
|
||||
r7 = mad_f32 r7 r3 r4
|
||||
r7 = to_i32 r7
|
||||
r7 = pack r6 r7 8
|
||||
r7 = pack r9 r7 16
|
||||
store32 arg(1) r7
|
||||
|
||||
G8 over A8
|
||||
12 values:
|
||||
@ -186,13 +186,13 @@ r2 = sub_f32 r0 r0
|
||||
r3 = splat 437F0000 (255)
|
||||
r4 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r5 = load8 arg(1)
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r1 r5
|
||||
r5 = mad_f32 r5 r2 r0
|
||||
r5 = mad_f32 r5 r3 r4
|
||||
r5 = to_i32 r5
|
||||
store8 arg(1) r5
|
||||
r5 = load8 arg(1)
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r1 r5
|
||||
r5 = mad_f32 r5 r2 r0
|
||||
r5 = mad_f32 r5 r3 r4
|
||||
r5 = to_i32 r5
|
||||
store8 arg(1) r5
|
||||
|
||||
G8 over G8
|
||||
21 values:
|
||||
@ -228,19 +228,19 @@ r4 = splat 3D93DD98 (0.0722)
|
||||
r5 = splat 437F0000 (255)
|
||||
r6 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r7 = load8 arg(0)
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r8 = load8 arg(1)
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r7 = mad_f32 r8 r1 r7
|
||||
r8 = mul_f32 r7 r4
|
||||
r8 = mad_f32 r7 r3 r8
|
||||
r8 = mad_f32 r7 r2 r8
|
||||
r8 = mad_f32 r8 r5 r6
|
||||
r8 = to_i32 r8
|
||||
store8 arg(1) r8
|
||||
r7 = load8 arg(0)
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r8 = load8 arg(1)
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r7 = mad_f32 r8 r1 r7
|
||||
r8 = mul_f32 r7 r4
|
||||
r8 = mad_f32 r7 r3 r8
|
||||
r8 = mad_f32 r7 r2 r8
|
||||
r8 = mad_f32 r8 r5 r6
|
||||
r8 = to_i32 r8
|
||||
store8 arg(1) r8
|
||||
|
||||
G8 over RGBA_8888
|
||||
38 values:
|
||||
@ -291,38 +291,38 @@ r3 = sub_f32 r2 r2
|
||||
r4 = splat 437F0000 (255)
|
||||
r5 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r6 = load8 arg(0)
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = load32 arg(1)
|
||||
r8 = extract r7 0 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r8 = mad_f32 r8 r3 r6
|
||||
r8 = mad_f32 r8 r4 r5
|
||||
r8 = to_i32 r8
|
||||
r9 = extract r7 8 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r9 = mad_f32 r9 r3 r6
|
||||
r9 = mad_f32 r9 r4 r5
|
||||
r9 = to_i32 r9
|
||||
r9 = pack r8 r9 8
|
||||
r8 = extract r7 16 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r6 = mad_f32 r8 r3 r6
|
||||
r6 = mad_f32 r6 r4 r5
|
||||
r6 = to_i32 r6
|
||||
r7 = extract r7 24 r1
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r7 = mad_f32 r7 r3 r2
|
||||
r7 = mad_f32 r7 r4 r5
|
||||
r7 = to_i32 r7
|
||||
r7 = pack r6 r7 8
|
||||
r7 = pack r9 r7 16
|
||||
store32 arg(1) r7
|
||||
r6 = load8 arg(0)
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = load32 arg(1)
|
||||
r8 = extract r7 0 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r8 = mad_f32 r8 r3 r6
|
||||
r8 = mad_f32 r8 r4 r5
|
||||
r8 = to_i32 r8
|
||||
r9 = extract r7 8 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r9 = mad_f32 r9 r3 r6
|
||||
r9 = mad_f32 r9 r4 r5
|
||||
r9 = to_i32 r9
|
||||
r9 = pack r8 r9 8
|
||||
r8 = extract r7 16 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r6 = mad_f32 r8 r3 r6
|
||||
r6 = mad_f32 r6 r4 r5
|
||||
r6 = to_i32 r6
|
||||
r7 = extract r7 24 r1
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r7 = mad_f32 r7 r3 r2
|
||||
r7 = mad_f32 r7 r4 r5
|
||||
r7 = to_i32 r7
|
||||
r7 = pack r6 r7 8
|
||||
r7 = pack r9 r7 16
|
||||
store32 arg(1) r7
|
||||
|
||||
RGBA_8888 over A8
|
||||
17 values:
|
||||
@ -351,18 +351,18 @@ r2 = splat 3F800000 (1)
|
||||
r3 = splat 437F0000 (255)
|
||||
r4 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r5 = load32 arg(0)
|
||||
r5 = extract r5 24 r1
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r6 = load8 arg(1)
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = sub_f32 r2 r5
|
||||
r5 = mad_f32 r6 r7 r5
|
||||
r5 = mad_f32 r5 r3 r4
|
||||
r5 = to_i32 r5
|
||||
store8 arg(1) r5
|
||||
r5 = load32 arg(0)
|
||||
r5 = extract r5 24 r1
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r6 = load8 arg(1)
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = sub_f32 r2 r5
|
||||
r5 = mad_f32 r6 r7 r5
|
||||
r5 = mad_f32 r5 r3 r4
|
||||
r5 = to_i32 r5
|
||||
store8 arg(1) r5
|
||||
|
||||
RGBA_8888 over G8
|
||||
34 values:
|
||||
@ -411,32 +411,32 @@ r5 = splat 3D93DD98 (0.0722)
|
||||
r6 = splat 437F0000 (255)
|
||||
r7 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r8 = load32 arg(0)
|
||||
r9 = extract r8 0 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r10 = load8 arg(1)
|
||||
r10 = to_f32 r10
|
||||
r10 = mul_f32 r0 r10
|
||||
r11 = extract r8 24 r1
|
||||
r11 = to_f32 r11
|
||||
r11 = mul_f32 r0 r11
|
||||
r11 = sub_f32 r2 r11
|
||||
r9 = mad_f32 r10 r11 r9
|
||||
r12 = extract r8 8 r1
|
||||
r12 = to_f32 r12
|
||||
r12 = mul_f32 r0 r12
|
||||
r12 = mad_f32 r10 r11 r12
|
||||
r8 = extract r8 16 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r8 = mad_f32 r10 r11 r8
|
||||
r8 = mul_f32 r8 r5
|
||||
r8 = mad_f32 r12 r4 r8
|
||||
r8 = mad_f32 r9 r3 r8
|
||||
r8 = mad_f32 r8 r6 r7
|
||||
r8 = to_i32 r8
|
||||
store8 arg(1) r8
|
||||
r8 = load32 arg(0)
|
||||
r9 = extract r8 0 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r10 = load8 arg(1)
|
||||
r10 = to_f32 r10
|
||||
r10 = mul_f32 r0 r10
|
||||
r11 = extract r8 24 r1
|
||||
r11 = to_f32 r11
|
||||
r11 = mul_f32 r0 r11
|
||||
r11 = sub_f32 r2 r11
|
||||
r9 = mad_f32 r10 r11 r9
|
||||
r12 = extract r8 8 r1
|
||||
r12 = to_f32 r12
|
||||
r12 = mul_f32 r0 r12
|
||||
r12 = mad_f32 r10 r11 r12
|
||||
r8 = extract r8 16 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r8 = mad_f32 r10 r11 r8
|
||||
r8 = mul_f32 r8 r5
|
||||
r8 = mad_f32 r12 r4 r8
|
||||
r8 = mad_f32 r9 r3 r8
|
||||
r8 = mad_f32 r8 r6 r7
|
||||
r8 = to_i32 r8
|
||||
store8 arg(1) r8
|
||||
|
||||
RGBA_8888 over RGBA_8888
|
||||
48 values:
|
||||
@ -496,49 +496,49 @@ r2 = splat 3F800000 (1)
|
||||
r3 = splat 437F0000 (255)
|
||||
r4 = splat 3F000000 (0.5)
|
||||
loop:
|
||||
r5 = load32 arg(0)
|
||||
r6 = extract r5 0 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = load32 arg(1)
|
||||
r8 = extract r7 0 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r9 = extract r5 24 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r10 = sub_f32 r2 r9
|
||||
r6 = mad_f32 r8 r10 r6
|
||||
r6 = mad_f32 r6 r3 r4
|
||||
r6 = to_i32 r6
|
||||
r8 = extract r5 8 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r11 = extract r7 8 r1
|
||||
r11 = to_f32 r11
|
||||
r11 = mul_f32 r0 r11
|
||||
r8 = mad_f32 r11 r10 r8
|
||||
r8 = mad_f32 r8 r3 r4
|
||||
r8 = to_i32 r8
|
||||
r8 = pack r6 r8 8
|
||||
r5 = extract r5 16 r1
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r6 = extract r7 16 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r5 = mad_f32 r6 r10 r5
|
||||
r5 = mad_f32 r5 r3 r4
|
||||
r5 = to_i32 r5
|
||||
r7 = extract r7 24 r1
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r9 = mad_f32 r7 r10 r9
|
||||
r9 = mad_f32 r9 r3 r4
|
||||
r9 = to_i32 r9
|
||||
r9 = pack r5 r9 8
|
||||
r9 = pack r8 r9 16
|
||||
store32 arg(1) r9
|
||||
r5 = load32 arg(0)
|
||||
r6 = extract r5 0 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r7 = load32 arg(1)
|
||||
r8 = extract r7 0 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r9 = extract r5 24 r1
|
||||
r9 = to_f32 r9
|
||||
r9 = mul_f32 r0 r9
|
||||
r10 = sub_f32 r2 r9
|
||||
r6 = mad_f32 r8 r10 r6
|
||||
r6 = mad_f32 r6 r3 r4
|
||||
r6 = to_i32 r6
|
||||
r8 = extract r5 8 r1
|
||||
r8 = to_f32 r8
|
||||
r8 = mul_f32 r0 r8
|
||||
r11 = extract r7 8 r1
|
||||
r11 = to_f32 r11
|
||||
r11 = mul_f32 r0 r11
|
||||
r8 = mad_f32 r11 r10 r8
|
||||
r8 = mad_f32 r8 r3 r4
|
||||
r8 = to_i32 r8
|
||||
r8 = pack r6 r8 8
|
||||
r5 = extract r5 16 r1
|
||||
r5 = to_f32 r5
|
||||
r5 = mul_f32 r0 r5
|
||||
r6 = extract r7 16 r1
|
||||
r6 = to_f32 r6
|
||||
r6 = mul_f32 r0 r6
|
||||
r5 = mad_f32 r6 r10 r5
|
||||
r5 = mad_f32 r5 r3 r4
|
||||
r5 = to_i32 r5
|
||||
r7 = extract r7 24 r1
|
||||
r7 = to_f32 r7
|
||||
r7 = mul_f32 r0 r7
|
||||
r9 = mad_f32 r7 r10 r9
|
||||
r9 = mad_f32 r9 r3 r4
|
||||
r9 = to_i32 r9
|
||||
r9 = pack r5 r9 8
|
||||
r9 = pack r8 r9 16
|
||||
store32 arg(1) r9
|
||||
|
||||
I32 (Naive) 8888 over 8888
|
||||
29 values:
|
||||
@ -576,33 +576,33 @@ I32 (Naive) 8888 over 8888
|
||||
r0 = splat FF (3.5733111e-43)
|
||||
r1 = splat 100 (3.5873241e-43)
|
||||
loop:
|
||||
r2 = load32 arg(0)
|
||||
r3 = extract r2 0 r0
|
||||
r4 = load32 arg(1)
|
||||
r5 = extract r4 0 r0
|
||||
r6 = extract r2 24 r0
|
||||
r7 = sub_i32 r1 r6
|
||||
r5 = mul_i32 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r3 r5
|
||||
r3 = extract r2 8 r0
|
||||
r8 = extract r4 8 r0
|
||||
r8 = mul_i32 r8 r7
|
||||
r8 = shr_i32 r8 8
|
||||
r8 = add_i32 r3 r8
|
||||
r8 = pack r5 r8 8
|
||||
r2 = extract r2 16 r0
|
||||
r5 = extract r4 16 r0
|
||||
r5 = mul_i32 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r2 r5
|
||||
r4 = extract r4 24 r0
|
||||
r7 = mul_i32 r4 r7
|
||||
r7 = shr_i32 r7 8
|
||||
r7 = add_i32 r6 r7
|
||||
r7 = pack r5 r7 8
|
||||
r7 = pack r8 r7 16
|
||||
store32 arg(1) r7
|
||||
r2 = load32 arg(0)
|
||||
r3 = extract r2 0 r0
|
||||
r4 = load32 arg(1)
|
||||
r5 = extract r4 0 r0
|
||||
r6 = extract r2 24 r0
|
||||
r7 = sub_i32 r1 r6
|
||||
r5 = mul_i32 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r3 r5
|
||||
r3 = extract r2 8 r0
|
||||
r8 = extract r4 8 r0
|
||||
r8 = mul_i32 r8 r7
|
||||
r8 = shr_i32 r8 8
|
||||
r8 = add_i32 r3 r8
|
||||
r8 = pack r5 r8 8
|
||||
r2 = extract r2 16 r0
|
||||
r5 = extract r4 16 r0
|
||||
r5 = mul_i32 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r2 r5
|
||||
r4 = extract r4 24 r0
|
||||
r7 = mul_i32 r4 r7
|
||||
r7 = shr_i32 r7 8
|
||||
r7 = add_i32 r6 r7
|
||||
r7 = pack r5 r7 8
|
||||
r7 = pack r8 r7 16
|
||||
store32 arg(1) r7
|
||||
|
||||
I32 8888 over 8888
|
||||
29 values:
|
||||
@ -640,33 +640,33 @@ I32 8888 over 8888
|
||||
r0 = splat FF (3.5733111e-43)
|
||||
r1 = splat 100 (3.5873241e-43)
|
||||
loop:
|
||||
r2 = load32 arg(0)
|
||||
r3 = bit_and r2 r0
|
||||
r4 = load32 arg(1)
|
||||
r5 = bit_and r4 r0
|
||||
r6 = shr_i32 r2 24
|
||||
r7 = sub_i32 r1 r6
|
||||
r5 = mul_i16x2 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r3 r5
|
||||
r3 = bytes r2 2
|
||||
r8 = bytes r4 2
|
||||
r8 = mul_i16x2 r8 r7
|
||||
r8 = shr_i32 r8 8
|
||||
r8 = add_i32 r3 r8
|
||||
r8 = pack r5 r8 8
|
||||
r2 = bytes r2 3
|
||||
r5 = bytes r4 3
|
||||
r5 = mul_i16x2 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r2 r5
|
||||
r4 = shr_i32 r4 24
|
||||
r7 = mul_i16x2 r4 r7
|
||||
r7 = shr_i32 r7 8
|
||||
r7 = add_i32 r6 r7
|
||||
r7 = pack r5 r7 8
|
||||
r7 = pack r8 r7 16
|
||||
store32 arg(1) r7
|
||||
r2 = load32 arg(0)
|
||||
r3 = bit_and r2 r0
|
||||
r4 = load32 arg(1)
|
||||
r5 = bit_and r4 r0
|
||||
r6 = shr_i32 r2 24
|
||||
r7 = sub_i32 r1 r6
|
||||
r5 = mul_i16x2 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r3 r5
|
||||
r3 = bytes r2 2
|
||||
r8 = bytes r4 2
|
||||
r8 = mul_i16x2 r8 r7
|
||||
r8 = shr_i32 r8 8
|
||||
r8 = add_i32 r3 r8
|
||||
r8 = pack r5 r8 8
|
||||
r2 = bytes r2 3
|
||||
r5 = bytes r4 3
|
||||
r5 = mul_i16x2 r5 r7
|
||||
r5 = shr_i32 r5 8
|
||||
r5 = add_i32 r2 r5
|
||||
r4 = shr_i32 r4 24
|
||||
r7 = mul_i16x2 r4 r7
|
||||
r7 = shr_i32 r7 8
|
||||
r7 = add_i32 r6 r7
|
||||
r7 = pack r5 r7 8
|
||||
r7 = pack r8 r7 16
|
||||
store32 arg(1) r7
|
||||
|
||||
I32 (SWAR) 8888 over 8888
|
||||
15 values:
|
||||
@ -690,19 +690,19 @@ I32 (SWAR) 8888 over 8888
|
||||
r0 = splat 1000100 (2.3510604e-38)
|
||||
r1 = splat FF00FF (2.3418409e-38)
|
||||
loop:
|
||||
r2 = load32 arg(0)
|
||||
r3 = bytes r2 404
|
||||
r3 = sub_i16x2 r0 r3
|
||||
r4 = load32 arg(1)
|
||||
r5 = bit_and r4 r1
|
||||
r5 = mul_i16x2 r5 r3
|
||||
r5 = shr_i16x2 r5 8
|
||||
r4 = shr_i16x2 r4 8
|
||||
r3 = mul_i16x2 r4 r3
|
||||
r3 = bit_clear r3 r1
|
||||
r3 = bit_or r5 r3
|
||||
r3 = add_i32 r2 r3
|
||||
store32 arg(1) r3
|
||||
r2 = load32 arg(0)
|
||||
r3 = bytes r2 404
|
||||
r3 = sub_i16x2 r0 r3
|
||||
r4 = load32 arg(1)
|
||||
r5 = bit_and r4 r1
|
||||
r5 = mul_i16x2 r5 r3
|
||||
r5 = shr_i16x2 r5 8
|
||||
r4 = shr_i16x2 r4 8
|
||||
r3 = mul_i16x2 r4 r3
|
||||
r3 = bit_clear r3 r1
|
||||
r3 = bit_or r5 r3
|
||||
r3 = add_i32 r2 r3
|
||||
store32 arg(1) r3
|
||||
|
||||
6 values:
|
||||
↟ v0 = splat 1 (1.4012985e-45)
|
||||
@ -717,9 +717,9 @@ r0 = splat 1 (1.4012985e-45)
|
||||
r1 = splat 2 (2.8025969e-45)
|
||||
r1 = add_i32 r0 r1
|
||||
loop:
|
||||
r0 = load32 arg(0)
|
||||
r0 = mul_i32 r0 r1
|
||||
store32 arg(0) r0
|
||||
r0 = load32 arg(0)
|
||||
r0 = mul_i32 r0 r1
|
||||
store32 arg(0) r0
|
||||
|
||||
19 values:
|
||||
↑ v0 = splat FF (3.5733111e-43)
|
||||
@ -745,22 +745,22 @@ store32 arg(0) r0
|
||||
6 registers, 19 instructions:
|
||||
r0 = splat FF (3.5733111e-43)
|
||||
loop:
|
||||
r1 = load32 arg(0)
|
||||
r2 = extract r1 0 r0
|
||||
r3 = load32 arg(1)
|
||||
r4 = extract r3 0 r0
|
||||
r4 = add_i32 r2 r4
|
||||
r2 = extract r1 8 r0
|
||||
r5 = extract r3 8 r0
|
||||
r5 = add_i32 r2 r5
|
||||
r5 = pack r4 r5 8
|
||||
r4 = extract r1 16 r0
|
||||
r2 = extract r3 16 r0
|
||||
r2 = add_i32 r4 r2
|
||||
r1 = extract r1 24 r0
|
||||
r3 = extract r3 24 r0
|
||||
r3 = add_i32 r1 r3
|
||||
r3 = pack r2 r3 8
|
||||
r3 = pack r5 r3 16
|
||||
store32 arg(1) r3
|
||||
r1 = load32 arg(0)
|
||||
r2 = extract r1 0 r0
|
||||
r3 = load32 arg(1)
|
||||
r4 = extract r3 0 r0
|
||||
r4 = add_i32 r2 r4
|
||||
r2 = extract r1 8 r0
|
||||
r5 = extract r3 8 r0
|
||||
r5 = add_i32 r2 r5
|
||||
r5 = pack r4 r5 8
|
||||
r4 = extract r1 16 r0
|
||||
r2 = extract r3 16 r0
|
||||
r2 = add_i32 r4 r2
|
||||
r1 = extract r1 24 r0
|
||||
r3 = extract r3 24 r0
|
||||
r3 = add_i32 r1 r3
|
||||
r3 = pack r2 r3 8
|
||||
r3 = pack r5 r3 16
|
||||
store32 arg(1) r3
|
||||
|
||||
|
||||
@ -203,9 +203,8 @@ namespace skvm {
|
||||
o->writeDecAsText(fInstructions.size());
|
||||
o->writeText(" instructions:\n");
|
||||
for (int i = 0; i < (int)fInstructions.size(); i++) {
|
||||
if (i == fLoop) {
|
||||
write(o, "loop:\n");
|
||||
}
|
||||
if (i == fLoop) { write(o, "loop:\n"); }
|
||||
if (i >= fLoop) { write(o, " "); }
|
||||
const Program::Instruction& inst = fInstructions[i];
|
||||
Op op = inst.op;
|
||||
Reg d = inst.d,
|
||||
|
||||
Loading…
Reference in New Issue
Block a user