From 5664b87a28bfce8b6baaa565449c14bcec351ab1 Mon Sep 17 00:00:00 2001 From: Ed_ Date: Tue, 25 Aug 2026 22:34:05 -0400 Subject: [PATCH] 989001065893801984 --- ...-up-q-a-is-algorithm-on-hw-fastpath-asm.md | 53 +++++++++++++++++++ ...et-it-for-cheaper-as-addition-byproduct.md | 37 +++++++++++++ ...1-2-3-4-5-6-6-6-the-number-of-the-beast.md | 39 ++++++++++++++ ...jplc-i-like-the-aproximate-results-line.md | 37 +++++++++++++ ..._1-use-a-small-fifo-what-does-this-mean.md | 37 +++++++++++++ .../index.md | 46 ++++++++++++++++ archive/threads/mike_acton/index.md | 1 + 7 files changed, 250 insertions(+) create mode 100644 archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-JBrooksBSI-more-speed-up-q-a-is-algorithm-on-hw-fastpath-asm.md create mode 100644 archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-Oberje-can-we-get-it-for-cheaper-as-addition-byproduct.md create mode 100644 archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-PaperBirdMaster-1-2-3-4-5-6-6-6-the-number-of-the-beast.md create mode 100644 archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-bonzajplc-i-like-the-aproximate-results-line.md create mode 100644 archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-t_cheng_1-use-a-small-fifo-what-does-this-mean.md create mode 100644 archive/threads/mike_acton/2018-04-25-mike-acton-approximator/index.md diff --git a/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-JBrooksBSI-more-speed-up-q-a-is-algorithm-on-hw-fastpath-asm.md b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-JBrooksBSI-more-speed-up-q-a-is-algorithm-on-hw-fastpath-asm.md new file mode 100644 index 0000000..f55fc0d --- /dev/null +++ b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-JBrooksBSI-more-speed-up-q-a-is-algorithm-on-hw-fastpath-asm.md @@ -0,0 +1,53 @@ +--- +title: "@mike_acton More speed-up Q" +type: archive +source: twitter +source_url: "https://x.com/JBrooksBSI/status/989170547694059520" +author: "John Brooks" +handle: JBrooksBSI +post_id: "989170547694059520" +date: 2018-04-25 +archived: 2026-08-25 +draft: false +tags: + - archive + - twitter + - mike_acton +description: "@mike_acton More speed-up Q" +in_reply_to: "" +parent_post_id: "989001065893801984" +--- + +## Source + +- URL: https://x.com/JBrooksBSI/status/989170547694059520 +- Author: John Brooks (@JBrooksBSI) +- Posted: 2018-04-25 15:53:31 + +## Branch + +**1/** **@JBrooksBSI** ^989170547694059520 + +**@mike_acton** + +More speed-up Q + +A. Is algorithm on HW fastpath? + ASM: reg cnt, int vs fp, on-chip ram, lzcnt, movemask + GPU: vec4, tess vs VS vs FS vs Blend vs Stencil, bandwidth + +B. Can we increase parallelism? + SoC SMP + SIMD + GPU + Cloud SMP + +C. Can we fix stalls? + Locks + Cache + Reg spill + Mem + +## Related + +- Spine: [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator]] diff --git a/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-Oberje-can-we-get-it-for-cheaper-as-addition-byproduct.md b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-Oberje-can-we-get-it-for-cheaper-as-addition-byproduct.md new file mode 100644 index 0000000..40b4759 --- /dev/null +++ b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-Oberje-can-we-get-it-for-cheaper-as-addition-byproduct.md @@ -0,0 +1,37 @@ +--- +title: "@mike_acton Can we get it for cheaper as addition/byproduct to something else we're doing." +type: archive +source: twitter +source_url: "https://x.com/Oberje/status/989116637939929088" +author: "Oberje" +handle: Oberje +post_id: "989116637939929088" +date: 2018-04-25 +archived: 2026-08-25 +draft: false +tags: + - archive + - twitter + - mike_acton +description: "@mike_acton Can we get it for cheaper as addition/byproduct to something else we're doing." +in_reply_to: "" +parent_post_id: "989001065893801984" +--- + +## Source + +- URL: https://x.com/Oberje/status/989116637939929088 +- Author: Oberje (@Oberje) +- Posted: 2018-04-25 12:19:18 + +## Branch + +**1/** **@Oberje** ^989116637939929088 + +**@mike_acton** + +Can we get it for cheaper as addition/byproduct to something else we're doing. + +## Related + +- Spine: [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator]] diff --git a/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-PaperBirdMaster-1-2-3-4-5-6-6-6-the-number-of-the-beast.md b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-PaperBirdMaster-1-2-3-4-5-6-6-6-the-number-of-the-beast.md new file mode 100644 index 0000000..b844f39 --- /dev/null +++ b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-PaperBirdMaster-1-2-3-4-5-6-6-6-the-number-of-the-beast.md @@ -0,0 +1,39 @@ +--- +title: "@mike_acton @ID_AA_Carmack 1, 2, 3, 4, 5, 6, 6…" +type: archive +source: twitter +source_url: "https://x.com/PaperBirdMaster/status/989117219576610816" +author: "Pau Montequi" +handle: PaperBirdMaster +post_id: "989117219576610816" +date: 2018-04-25 +archived: 2026-08-25 +draft: false +tags: + - archive + - twitter + - mike_acton +description: "@mike_acton @ID_AA_Carmack 1, 2, 3, 4, 5, 6, 6…" +in_reply_to: "" +parent_post_id: "989001065893801984" +--- + +## Source + +- URL: https://x.com/PaperBirdMaster/status/989117219576610816 +- Author: Pau Montequi (@PaperBirdMaster) +- Posted: 2018-04-25 12:21:36 + +## Branch + +**1/** **@PaperBirdMaster** ^989117219576610816 + +**@mike_acton** **@ID_AA_Carmack** + +1, 2, 3, 4, 5, 6, 6… + +… 6, the number of the beast. + +## Related + +- Spine: [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator]] diff --git a/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-bonzajplc-i-like-the-aproximate-results-line.md b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-bonzajplc-i-like-the-aproximate-results-line.md new file mode 100644 index 0000000..0e1a393 --- /dev/null +++ b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-bonzajplc-i-like-the-aproximate-results-line.md @@ -0,0 +1,37 @@ +--- +title: "@mike_acton I like the aproximate results line :)" +type: archive +source: twitter +source_url: "https://x.com/bonzajplc/status/989031363369144320" +author: "bonzaj/plastic" +handle: bonzajplc +post_id: "989031363369144320" +date: 2018-04-25 +archived: 2026-08-25 +draft: false +tags: + - archive + - twitter + - mike_acton +description: "@mike_acton I like the aproximate results line :)" +in_reply_to: "" +parent_post_id: "989001065893801984" +--- + +## Source + +- URL: https://x.com/bonzajplc/status/989031363369144320 +- Author: bonzaj/plastic (@bonzajplc) +- Posted: 2018-04-25 06:40:26 + +## Branch + +**1/** **@bonzajplc** ^989031363369144320 + +**@mike_acton** + +I like the aproximate results line :) + +## Related + +- Spine: [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator]] diff --git a/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-t_cheng_1-use-a-small-fifo-what-does-this-mean.md b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-t_cheng_1-use-a-small-fifo-what-does-this-mean.md new file mode 100644 index 0000000..bff1e8a --- /dev/null +++ b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-t_cheng_1-use-a-small-fifo-what-does-this-mean.md @@ -0,0 +1,37 @@ +--- +title: "@mike_acton 'use a small fifo'? What does this mean?" +type: archive +source: twitter +source_url: "https://x.com/t_cheng_1/status/989156948070330374" +author: "Tom Cheng" +handle: t_cheng_1 +post_id: "989156948070330374" +date: 2018-04-25 +archived: 2026-08-25 +draft: false +tags: + - archive + - twitter + - mike_acton +description: "@mike_acton 'use a small fifo'? What does this mean?" +in_reply_to: "" +parent_post_id: "989001065893801984" +--- + +## Source + +- URL: https://x.com/t_cheng_1/status/989156948070330374 +- Author: Tom Cheng (@t_cheng_1) +- Posted: 2018-04-25 14:59:28 + +## Branch + +**1/** **@t_cheng_1** ^989156948070330374 + +**@mike_acton** + +'use a small fifo'? What does this mean? + +## Related + +- Spine: [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator]] diff --git a/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/index.md b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/index.md new file mode 100644 index 0000000..a06645d --- /dev/null +++ b/archive/threads/mike_acton/2018-04-25-mike-acton-approximator/index.md @@ -0,0 +1,46 @@ +--- +title: "Mike Acton approximator:" +type: archive +source: twitter +source_url: "https://x.com/mike_acton/status/989001065893801984" +author: "Mike Acton" +handle: mike_acton +post_id: "989001065893801984" +date: 2018-04-25 +archived: 2026-08-25 +draft: false +tags: + - archive + - twitter + - mike_acton +description: "Mike Acton approximator:" +in_reply_to: "" +--- + +## Source + +- URL: https://x.com/mike_acton/status/989001065893801984 +- Author: Mike Acton (@mike_acton) +- Posted: 2018-04-25 04:40:03 + +## Thread + +**1/** **@mike_acton** ^989001065893801984 + +Mike Acton approximator: +1. Can we not do this at all? +2. Can we do this only once? +3. Can we do this fewer times? +4. Can we approximate the results so no one notices? +5. Can we use a small lookup table? +6. Can we use a small FIFO? +6. Can we constrain the problem further? +RECURSE https://x.com/niinegames/status/988718667188854784 + +Branches: [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-bonzajplc-i-like-the-aproximate-results-line]], [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-Oberje-can-we-get-it-for-cheaper-as-addition-byproduct]], [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-PaperBirdMaster-1-2-3-4-5-6-6-6-the-number-of-the-beast]], [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-t_cheng_1-use-a-small-fifo-what-does-this-mean]], [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator/2018-04-25-JBrooksBSI-more-speed-up-q-a-is-algorithm-on-hw-fastpath-asm]] + +**2/** **@aras_p** ^989007374387204096 + +**@mike_acton** + +Aras approximator: can we delete that code already? :) diff --git a/archive/threads/mike_acton/index.md b/archive/threads/mike_acton/index.md index 9ffcccb..54fa802 100644 --- a/archive/threads/mike_acton/index.md +++ b/archive/threads/mike_acton/index.md @@ -9,4 +9,5 @@ tags: - mike_acton --- +- [[archive/threads/mike_acton/2018-04-25-mike-acton-approximator]] - [[archive/threads/mike_acton/2024-06-21-the-biggest-flaw-in-most-systems-designs-is-the]]