ViperEkura
/
video-promo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: merge D,E,F into one batch (gated by F at t=8) to show worse static idle

This commit is contained in:
ViperEkura 2026-05-07 22:47:21 +08:00
parent 29007c7b97
commit e594d02d31
1 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
continuous_batching.py
View File

@ -392,13 +392,13 @@ class ContinuousBatching(Scene):
gpu_l.move_to([L_OX - 0.55, GY - ROW, 0]) gpu_l.move_to([L_OX - 0.55, GY - ROW, 0])
self.play(Write(gpu_l)) self.play(Write(gpu_l))
# Static GPU: idle [0-2], batch 1 [2-6], batch 2 [6-10], idle [10-12] # Static GPU: idle [0-2], batch 1 [2-6], idle [6-8], batch 2 [8-12]
s_y_gpu = GY - ROW s_y_gpu = GY - ROW
s_gpu_idle1 = gbox(L_OX, s_y_gpu, 0, 2, RED, 0.45) s_gpu_idle1 = gbox(L_OX, s_y_gpu, 0, 2, RED, 0.45)
s_gpu_batch1 = gbox(L_OX, s_y_gpu, 2, 4, GREEN) s_gpu_batch1 = gbox(L_OX, s_y_gpu, 2, 4, GREEN)
s_gpu_batch2 = gbox(L_OX, s_y_gpu, 6, 4, GREEN) s_gpu_idle2 = gbox(L_OX, s_y_gpu, 6, 2, RED, 0.45)
s_gpu_idle2 = gbox(L_OX, s_y_gpu, 10, 2, RED, 0.45) s_gpu_batch2 = gbox(L_OX, s_y_gpu, 8, 4, GREEN)
s_gpu_bars = [s_gpu_idle1, s_gpu_batch1, s_gpu_batch2, s_gpu_idle2] s_gpu_bars = [s_gpu_idle1, s_gpu_batch1, s_gpu_idle2, s_gpu_batch2]
for seg in s_gpu_bars: for seg in s_gpu_bars:
self.play(GrowFromEdge(seg, LEFT), run_time=0.09) self.play(GrowFromEdge(seg, LEFT), run_time=0.09)
@ -406,18 +406,19 @@ class ContinuousBatching(Scene):
s_idle1 = Text("IDLE", font_size=10, color=RED) \ s_idle1 = Text("IDLE", font_size=10, color=RED) \
.move_to([L_OX + 1 * CELL, s_y_gpu, 0]) .move_to([L_OX + 1 * CELL, s_y_gpu, 0])
s_idle2 = Text("IDLE", font_size=10, color=RED) \ s_idle2 = Text("IDLE", font_size=10, color=RED) \
.move_to([L_OX + 11 * CELL, s_y_gpu, 0]) .move_to([L_OX + 7 * CELL, s_y_gpu, 0])
self.play(Write(s_idle1), Write(s_idle2)) self.play(Write(s_idle1), Write(s_idle2))
# Same 5 requests as continuous — but scheduled in batches # Same 6 requests as continuous — but scheduled in batches
# each gets a gray WAIT bar before its coloured RUN bar # D, E, F grouped into one batch (gated by F's arrival at t=8)
# (name, color, wait_start, wait_end, run_start, run_end) # (name, color, wait_start, wait_end, run_start, run_end)
s_req_defs = [ s_req_defs = [
("A", ORANGE, 0, 2, 2, 6), # arrives t=0, waits for C → batch 1 ("A", ORANGE, 0, 2, 2, 6), # arrives t=0, waits for C → batch 1
("B", BLUE, 1, 2, 2, 6), # arrives t=1, waits for C ("B", BLUE, 1, 2, 2, 6), # arrives t=1, waits for C
("C", PINK, 2, 2, 2, 6), # arrives t=2, no wait (last to arrive) ("C", PINK, 2, 2, 2, 6), # arrives t=2, no wait
("D", ORANGE, 4, 6, 6, 10), # arrives t=4, waits for batch 1 to free GPU ("D", ORANGE, 4, 8, 8, 12), # arrives t=4, waits for F → batch 2
("E", BLUE, 6, 6, 6, 10), # arrives t=6, no wait (GPU just freed) ("E", BLUE, 6, 8, 8, 12), # arrives t=6, waits for F
("F", PINK, 8, 8, 8, 12), # arrives t=8, no wait
] ]
s_bars = [] s_bars = []
for i, (name, col, ws, we, rs, re) in enumerate(s_req_defs): for i, (name, col, ws, we, rs, re) in enumerate(s_req_defs):
@ -438,9 +439,9 @@ class ContinuousBatching(Scene):
# batch boxes — connect GPU busy segments to the requests they serve # batch boxes — connect GPU busy segments to the requests they serve
s_y_last3 = s_y_gpu - 3 * ROW # Req C is the 3rd request row s_y_last3 = s_y_gpu - 3 * ROW # Req C is the 3rd request row
s_y_last5 = s_y_gpu - 5 * ROW # Req E is the 5th request row s_y_last6 = s_y_gpu - 6 * ROW # Req F is the 6th request row
b1_rect, b1_lbl = batch_box(L_OX, s_y_gpu, s_y_last3, 2, 4, RED, "Batch 1") b1_rect, b1_lbl = batch_box(L_OX, s_y_gpu, s_y_last3, 2, 4, RED, "Batch 1")
b2_rect, b2_lbl = batch_box(L_OX, s_y_gpu, s_y_last5, 6, 4, RED, "Batch 2") b2_rect, b2_lbl = batch_box(L_OX, s_y_gpu, s_y_last6, 8, 4, RED, "Batch 2")
self.play(Create(b1_rect), Write(b1_lbl)) self.play(Create(b1_rect), Write(b1_lbl))
self.play(Create(b2_rect), Write(b2_lbl)) self.play(Create(b2_rect), Write(b2_lbl))
self.wait(0.8) self.wait(0.8)
@ -466,13 +467,14 @@ class ContinuousBatching(Scene):
c_gpu = gbox(R_OX, c_y_gpu, 0, 12, GREEN, 0.75) c_gpu = gbox(R_OX, c_y_gpu, 0, 12, GREEN, 0.75)
self.play(GrowFromEdge(c_gpu, LEFT), run_time=0.5) self.play(GrowFromEdge(c_gpu, LEFT), run_time=0.5)
# Same 5 requests — start immediately, no wait, staggered naturally # Same 6 requests — start immediately, no wait, staggered naturally
c_reqs = [ c_reqs = [
("A", ORANGE, 0, 4), ("A", ORANGE, 0, 4),
("B", BLUE, 1, 4), ("B", BLUE, 1, 4),
("C", PINK, 2, 4), ("C", PINK, 2, 4),
("D", ORANGE, 4, 4), ("D", ORANGE, 4, 4),
("E", BLUE, 6, 4), ("E", BLUE, 6, 4),
("F", PINK, 8, 4),
] ]
c_bars = [] c_bars = []
c_n_reqs = len(c_reqs) c_n_reqs = len(c_reqs)
@ -492,10 +494,10 @@ class ContinuousBatching(Scene):
self.wait(1.0) self.wait(1.0)
# count annotation # count annotation
s_count = Text("5 reqs · 2 batches · GPU idle gaps", s_count = Text("6 reqs · 2 batches · GPU idle gaps",
font_size=16, color=RED) \ font_size=16, color=RED) \
.next_to(s_gpu_batch1, DOWN, buff=1.0).align_to(s_gpu_batch1, LEFT) .next_to(s_gpu_batch1, DOWN, buff=1.0).align_to(s_gpu_batch1, LEFT)
c_count = Text("5 reqs · continuous · GPU never idle", c_count = Text("6 reqs · continuous · GPU never idle",
font_size=16, color=GREEN) \ font_size=16, color=GREEN) \
.next_to(c_gpu, DOWN, buff=1.0).align_to(c_gpu, LEFT) .next_to(c_gpu, DOWN, buff=1.0).align_to(c_gpu, LEFT)
self.play(Write(s_note), Write(c_note)) self.play(Write(s_note), Write(c_note))