Skip to content

[AMDGPU] Add gfx1250 run lines to gfx12_dasm_vop3_dpp8.txt. NFC. #145778

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
rampitec merged 1 commit into from
Jun 25, 2025
Merged

[AMDGPU] Add gfx1250 run lines to gfx12_dasm_vop3_dpp8.txt. NFC. #145778

rampitec merged 1 commit into from
Jun 25, 2025

Conversation

@rampitec
Copy link
Collaborator

@rampitec rampitec commented Jun 25, 2025

No description provided.

@rampitec Graphite App
Copy link
Collaborator Author

rampitec commented Jun 25, 2025

This stack of pull requests is managed by Graphite. Learn more about stacking.

@rampitec rampitec requested review from changpeng and shiltian June 25, 2025 20:27
shiltian
shiltian approved these changes Jun 25, 2025
View reviewed changes
Copy link
Contributor

@shiltian shiltian left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Still draft?

changpeng
changpeng approved these changes Jun 25, 2025
View reviewed changes
Copy link
Contributor

@changpeng changpeng left a comment •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt
# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W64,W64-REAL16,GFX1200,GFX1200-W64,GFX1200-W64-REAL16 %s
# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W64,W64-FAKE16,GFX1200,GFX1200-W64,GFX1200-W64-FAKE16 %s
# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-REAL16,GFX1250,GFX1250-W32,GFX1250-W32-REAL16 %s
# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-FAKE16,GFX1250,GFX1250-W32,GFX1250-W32-FAKE16 %s
Copy link
Contributor

@changpeng changpeng Jun 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(the very first prefix) Use GFX1200 instead of GFX12 to be consistent?

Copy link
Contributor

@changpeng changpeng Jun 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

My bad. GFX12 is (GFX1200 + GFX1250 here. So its fine

@rampitec rampitec marked this pull request as ready for review June 25, 2025 20:51
@llvmbot llvmbot added backend:AMDGPU llvm:mc Machine (object) code labels Jun 25, 2025
@rampitec
Copy link
Collaborator Author

rampitec commented Jun 25, 2025

Still draft?

No, thanks!

@llvmbot
Copy link
Member

llvmbot commented Jun 25, 2025 •
edited
Loading

@llvm/pr-subscribers-mc

@llvm/pr-subscribers-backend-amdgpu

Author: Stanislav Mekhanoshin (rampitec)

Changes

Patch is 28.20 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/145778.diff

1 Files Affected:

  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt (+65-43)
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt
index 8688410a8c9b2..ad20788081c94 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt
@@ -1,8 +1,10 @@
 # NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --version 5
-# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-REAL16 %s
-# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-FAKE16 %s
-# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W64,W64-REAL16 %s
-# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W64,W64-FAKE16 %s
+# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-REAL16,GFX1200,GFX1200-W32,GFX1200-W32-REAL16 %s
+# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-FAKE16,GFX1200,GFX1200-W32,GFX1200-W32-FAKE16 %s
+# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W64,W64-REAL16,GFX1200,GFX1200-W64,GFX1200-W64-REAL16 %s
+# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W64,W64-FAKE16,GFX1200,GFX1200-W64,GFX1200-W64-FAKE16 %s
+# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-REAL16,GFX1250,GFX1250-W32,GFX1250-W32-REAL16 %s
+# RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12,W32,W32-FAKE16,GFX1250,GFX1250-W32,GFX1250-W32-FAKE16 %s
 
 0x05,0x00,0x55,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05
 # GFX12: v_add3_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
@@ -681,32 +683,32 @@
 # GFX12: v_cubetc_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x87,0x0e,0xd6,0xea,0xfe,0xf7,0xfb,0xff,0x00,0x00,0x00]
 
 0x05,0x00,0x69,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0xa9,0x21
-# W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, v1, v2 dpp8:[7,6,5,4,2,3,0,1] ; encoding: [0x05,0x00,0x69,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0xa9,0x21]
 # W32-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,2,3,0,1] ; encoding: [0x05,0x00,0x69,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0xa9,0x21]
+# GFX1200-W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, v1, v2 dpp8:[7,6,5,4,2,3,0,1] ; encoding: [0x05,0x00,0x69,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0xa9,0x21]
 # W64-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, v1, v2 dpp8:[7,6,5,4,2,3,0,1] ; encoding: [0x05,0x00,0x69,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0xa9,0x21]
 # W64-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,2,3,0,1] ; encoding: [0x05,0x00,0x69,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0xa9,0x21]
 
 0x05,0x01,0x69,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05
-# W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x69,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
 # W32-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x69,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
+# GFX1200-W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x69,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
 # W64-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x69,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
 # W64-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x69,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
 
 0x05,0x02,0x69,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05
-# W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x02,0x69,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
 # W32-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x02,0x69,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
+# GFX1200-W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x02,0x69,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
 # W64-REAL16: v_cvt_pk_fp8_f32_e64_dpp v5.l, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x02,0x69,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
 # W64-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x02,0x69,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
 
 0xff,0x03,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00
-# W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v255.l, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x03,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 # W32-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x03,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
+# GFX1200-W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v255.l, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x03,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 # W64-REAL16: v_cvt_pk_fp8_f32_e64_dpp v255.l, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x03,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 # W64-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x03,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 
 0xff,0x43,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00
-# W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v255.h, -|v255|, -|v255| op_sel:[0,0,1] dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x43,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 # W32-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v255, -|v255|, -|v255| op_sel:[0,0,1] dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x43,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
+# GFX1200-W32-REAL16: v_cvt_pk_fp8_f32_e64_dpp v255.h, -|v255|, -|v255| op_sel:[0,0,1] dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x43,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 # W64-REAL16: v_cvt_pk_fp8_f32_e64_dpp v255.h, -|v255|, -|v255| op_sel:[0,0,1] dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x43,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 # W64-FAKE16: v_cvt_pk_fp8_f32_e64_dpp v255, -|v255|, -|v255| op_sel:[0,0,1] dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x43,0x69,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
 
@@ -3754,7 +3756,6 @@
 # W64-REAL16: v_max3_num_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x2c,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05]
 # W64-FAKE16: v_max3_num_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x2c,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05]
 
-
 0x05,0x00,0x4d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05
 # W32-REAL16: v_max3_i16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x4d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
 # W32-FAKE16: v_max3_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x4d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
@@ -4565,7 +4566,6 @@
 # W64-REAL16: v_min3_num_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x2b,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05]
 # W64-FAKE16: v_min3_num_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x2b,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05]
 
-
 0x05,0x00,0x4a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05
 # W32-REAL16: v_min3_i16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x4a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
 # W32-FAKE16: v_min3_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x4a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
@@ -5047,100 +5047,112 @@
 # W64-FAKE16: v_sub_nc_u16_e64_dpp v255, v255, v255 op_sel:[0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc0,0x04,0xd7,0xea,0xfe,0x03,0x00,0xff,0x00,0x00,0x00]
 
 0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v0.l, v1, v2, v3.l dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1250: s_or_not1_b32 s70, s1, 8                ; encoding: [0x01,0x88,0x46,0x92]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v0.l, v1, v2, v3.l dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v0.l, v1, v2, v3.l dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 
 # op_sel[1:0] are ignored
 0x00,0x78,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1250: s_or_not1_b32 s70, s1, 8                ; encoding: [0x01,0x88,0x46,0x92]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 
 0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1250: s_or_not1_b32 s70, s1, 8                ; encoding: [0x01,0x88,0x46,0x92]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 
 0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v0.h, |v1|, -v2, -|s3| op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, |v1|, -v2, -|s3| op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92]
+# GFX1250: s_or_not1_b32 s70, s1, 8                ; encoding: [0x01,0x88,0x46,0x92]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v0.h, |v1|, -v2, -|s3| op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v0, |v1|, -v2, -|s3| op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v0.h, |v1|, -v2, -|s3| op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v0, |v1|, -v2, -|s3| op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x65,0x66,0xd6,0xe9,0x04,0x0e,0xc0,0x01,0x88,0x46,0x92]
 
 0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v5.l, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+# GFX1250: v_add_f32_dpp v255, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v5.l, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v5.l, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 
 0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v255.h, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v255.h, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v255.h, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
 
 0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v5.l, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+# GFX1250: v_add_f32_dpp v255, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v5.l, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v5.l, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x66,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 
 0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00
-# W32-REAL16: v_dot2_f16_f16_e64_dpp v255.h, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
-# W32-FAKE16: v_dot2_f16_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
+# GFX1200-W32-REAL16: v_dot2_f16_f16_e64_dpp v255.h, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
+# GFX1200-W32-FAKE16: v_dot2_f16_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
 # W64-REAL16: v_dot2_f16_f16_e64_dpp v255.h, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
 # W64-FAKE16: v_dot2_f16_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x47,0x66,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00]
 
 0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92
-# W32-REAL16: v_dot2_bf16_bf16_e64_dpp v0.l, v1, v2, v3.l dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
-# W32-FAKE16: v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1250: s_or_not1_b32 s70, s1, 8                ; encoding: [0x01,0x88,0x46,0x92]
+# GFX1200-W32-REAL16: v_dot2_bf16_bf16_e64_dpp v0.l, v1, v2, v3.l dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1200-W32-FAKE16: v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-REAL16: v_dot2_bf16_bf16_e64_dpp v0.l, v1, v2, v3.l dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-FAKE16: v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 
 # op_sel[1:0] are ignored
 0x00,0x78,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92
-# W32-REAL16: v_dot2_bf16_bf16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
-# W32-FAKE16: v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1250: s_or_not1_b32 s70, s1, 8                ; encoding: [0x01,0x88,0x46,0x92]
+# GFX1200-W32-REAL16: v_dot2_bf16_bf16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
+# GFX1200-W32-FAKE16: v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-REAL16: v_dot2_bf16_bf16_e64_dpp v0.h, v1, v2, v3.h op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [0x00,0x60,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92]
 # W64-FAKE16: v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] ; encoding: [...
[truncated]

@rampitec rampitec merged commit 17f91a2 into main Jun 25, 2025
12 checks passed
@rampitec rampitec deleted the users/rampitec/06-25-_amdgpu_add_gfx1250_run_lines_to_gfx12_dasm_vop3_dpp8.txt._nfc branch June 25, 2025 21:34
anthonyhatran pushed a commit to anthonyhatran/llvm-project that referenced this pull request Jun 26, 2025
@rampitec
[AMDGPU] Add gfx1250 run lines to gfx12_dasm_vop3_dpp8.txt. NFC. (llv…
55ff9e7 
…m#145778)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@changpeng changpeng changpeng approved these changes

@shiltian shiltian shiltian approved these changes

Assignees

No one assigned

Labels

backend:AMDGPU llvm:mc Machine (object) code

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@rampitec @llvmbot @changpeng @shiltian