Skip to content

[AMDGPU][True16][MC] update a few mc test for true16 #135816

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

Merged
merged 2 commits into from
Apr 16, 2025
Merged

[AMDGPU][True16][MC] update a few mc test for true16 #135816

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
25dc466
clean up of true16 mc changes
broxigarchen Apr 11, 2025
6d793ef
address comments
broxigarchen Apr 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
114 changes: 114 additions & 0 deletions llvm/test/MC/AMDGPU/bf16_imm-fake16.s
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,114 @@
// NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --unique --version 5
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -show-encoding %s | FileCheck %s
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -show-encoding %s | FileCheck %s

v_dot2_bf16_bf16 v5, v1, v2, 100.0
// CHECK: v_dot2_bf16_bf16 v5, v1, v2, 0x42c8 ; encoding: [0x05,0x00,0x67,0xd6,0x01,0x05,0xfe,0x03,0xc8,0x42,0x00,0x00]

v_dot2_bf16_bf16 v2, v0, 1.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 1.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe5,0x09,0x04]

v_dot2_bf16_bf16 v2, 1.0, v0, v2
// CHECK: v_dot2_bf16_bf16 v2, 1.0, v0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0xf2,0x00,0x0a,0x04]

v_dot2_bf16_bf16 v5, v1, v2, 1.0
// CHECK: v_dot2_bf16_bf16 v5, v1, v2, 1.0 ; encoding: [0x05,0x00,0x67,0xd6,0x01,0x05,0xca,0x03]

v_dot2_bf16_bf16 v2, v0, -1.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -1.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe7,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 0.5, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.5, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, -0.5, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -0.5, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe3,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 2.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 2.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe9,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, -2.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -2.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xeb,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 4.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 4.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xed,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, -4.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -4.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xef,0x09,0x04]

// Check 1/(2*pi) rounded value and ideomatic fp32 0.15915494 value
// which cannot be accurately represented in bf16.

v_dot2_bf16_bf16 v2, v0, 0.158203125, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.15915494, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 0.15915494, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.15915494, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 0x3e22, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.15915494, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, v2, 0.15915494
// CHECK: v_dot2_bf16_bf16 v2, v0, v2, 0.15915494 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0x05,0xe2,0x03]

v_dot2_f32_bf16 v2, v1, 0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0x01,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, 0.5, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 0.5, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xe1,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, -0.5, v2
// CHECK: v_dot2_f32_bf16 v2, v1, -0.5, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xe3,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, 1.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 1.0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xe5,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, -1.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, -1.0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xe7,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, 2.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 2.0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xe9,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, -2.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, -2.0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xeb,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, 4.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 4.0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xed,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, -4.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, -4.0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xef,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, 0.15915494, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 0.15915494, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xf1,0x09,0x1c]

v_dot2_f32_bf16 v2, v1, 0x3e22, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 0.15915494, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xf1,0x09,0x1c]

v_dot2_f32_bf16 v2, 0.5, v1, v2
// CHECK: v_dot2_f32_bf16 v2, 0.5, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf0,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, -0.5, v1, v2
// CHECK: v_dot2_f32_bf16 v2, -0.5, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf1,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, 1.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, 1.0, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf2,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, -1.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, -1.0, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf3,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, 2.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, 2.0, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf4,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, -2.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, -2.0, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf5,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, 4.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, 4.0, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf6,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, -4.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, -4.0, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xf7,0x02,0x0a,0x1c]

v_dot2_f32_bf16 v2, 100.0, v1, v2
// CHECK: v_dot2_f32_bf16 v2, 0x42c8, v1, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0xff,0x02,0x0a,0x1c,0xc8,0x42,0x00,0x00]

v_dot2_f32_bf16 v2, v1, 100.0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 0x42c8, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0xff,0x09,0x1c,0xc8,0x42,0x00,0x00]
64 changes: 32 additions & 32 deletions llvm/test/MC/AMDGPU/bf16_imm.s
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,54 +1,54 @@
// NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --unique --version 5
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1100 -show-encoding %s | FileCheck %s
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -show-encoding %s | FileCheck %s
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -show-encoding %s | FileCheck %s
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -show-encoding %s | FileCheck %s

v_dot2_bf16_bf16 v5, v1, v2, 100.0
// CHECK: v_dot2_bf16_bf16 v5, v1, v2, 0x42c8 ; encoding: [0x05,0x00,0x67,0xd6,0x01,0x05,0xfe,0x03,0xc8,0x42,0x00,0x00]
v_dot2_bf16_bf16 v5.l, v1, v2, 100.0
// CHECK: v_dot2_bf16_bf16 v5.l, v1, v2, 0x42c8 ; encoding: [0x05,0x00,0x67,0xd6,0x01,0x05,0xfe,0x03,0xc8,0x42,0x00,0x00]

v_dot2_bf16_bf16 v2, v0, 1.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 1.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe5,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 1.0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 1.0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe5,0x09,0x04]

v_dot2_bf16_bf16 v2, 1.0, v0, v2
// CHECK: v_dot2_bf16_bf16 v2, 1.0, v0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0xf2,0x00,0x0a,0x04]
v_dot2_bf16_bf16 v2.l, 1.0, v0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, 1.0, v0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0xf2,0x00,0x0a,0x04]

v_dot2_bf16_bf16 v5, v1, v2, 1.0
// CHECK: v_dot2_bf16_bf16 v5, v1, v2, 1.0 ; encoding: [0x05,0x00,0x67,0xd6,0x01,0x05,0xca,0x03]
v_dot2_bf16_bf16 v5.l, v1, v2, 1.0
// CHECK: v_dot2_bf16_bf16 v5.l, v1, v2, 1.0 ; encoding: [0x05,0x00,0x67,0xd6,0x01,0x05,0xca,0x03]

v_dot2_bf16_bf16 v2, v0, -1.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -1.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe7,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, -1.0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, -1.0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe7,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 0.5, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.5, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe1,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 0.5, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 0.5, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, -0.5, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -0.5, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe3,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, -0.5, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, -0.5, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe3,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 2.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 2.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe9,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 2.0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 2.0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xe9,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, -2.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -2.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xeb,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, -2.0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, -2.0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xeb,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 4.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 4.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xed,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 4.0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 4.0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xed,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, -4.0, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, -4.0, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xef,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, -4.0, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, -4.0, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xef,0x09,0x04]

// Check 1/(2*pi) rounded value and ideomatic fp32 0.15915494 value
// which cannot be accurately represented in bf16.

v_dot2_bf16_bf16 v2, v0, 0.158203125, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.15915494, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 0.158203125, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 0.15915494, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 0.15915494, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.15915494, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 0.15915494, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 0.15915494, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, 0x3e22, v2
// CHECK: v_dot2_bf16_bf16 v2, v0, 0.15915494, v2 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]
v_dot2_bf16_bf16 v2.l, v0, 0x3e22, v2.l
// CHECK: v_dot2_bf16_bf16 v2.l, v0, 0.15915494, v2.l ; encoding: [0x02,0x00,0x67,0xd6,0x00,0xf1,0x09,0x04]

v_dot2_bf16_bf16 v2, v0, v2, 0.15915494
// CHECK: v_dot2_bf16_bf16 v2, v0, v2, 0.15915494 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0x05,0xe2,0x03]
v_dot2_bf16_bf16 v2.l, v0, v2, 0.15915494
// CHECK: v_dot2_bf16_bf16 v2.l, v0, v2, 0.15915494 ; encoding: [0x02,0x00,0x67,0xd6,0x00,0x05,0xe2,0x03]

v_dot2_f32_bf16 v2, v1, 0, v2
// CHECK: v_dot2_f32_bf16 v2, v1, 0, v2 ; encoding: [0x02,0x40,0x1a,0xcc,0x01,0x01,0x09,0x1c]
Expand Down
Loading
Loading