[llvm] [AMDGPU][True16][MC] duplicate vop1 tests to fake16 and update real-true16 flags for GFX12 (PR #100849)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jul 26 18:56:53 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Brox Chen (broxigarchen)
<details>
<summary>Changes</summary>
duplicate vop1 tests to fake16 and update real-true16 flags for GFX12
creating duplications here to avoid bulk copy in the following true16 patches
---
Patch is 284.32 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/100849.diff
8 Files Affected:
- (added) llvm/test/MC/AMDGPU/gfx12_asm_vop1-fake16.s (+3597)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1.s (+4-4)
- (added) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16-fake16.s (+2828)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s (+2-2)
- (added) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8-fake16.s (+617)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s (+2-2)
- (added) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err-fake16.s (+505)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s (+1-1)
``````````diff
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop1-fake16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop1-fake16.s
new file mode 100644
index 0000000000000..8fef2ab26dfdd
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop1-fake16.s
@@ -0,0 +1,3597 @@
+// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32,-real-true16 -show-encoding %s | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-ASM %s
+// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32,-real-true16 -show-encoding %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-DIS %s
+// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,-real-true16 -show-encoding %s | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-ASM %s
+// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,-real-true16 -show-encoding %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-DIS %s
+
+v_bfrev_b32_e32 v5, v1
+// GFX12: v_bfrev_b32_e32 v5, v1 ; encoding: [0x01,0x71,0x0a,0x7e]
+
+v_bfrev_b32 v5, v255
+// GFX12: v_bfrev_b32_e32 v5, v255 ; encoding: [0xff,0x71,0x0a,0x7e]
+
+v_bfrev_b32 v5, s1
+// GFX12: v_bfrev_b32_e32 v5, s1 ; encoding: [0x01,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, s105
+// GFX12: v_bfrev_b32_e32 v5, s105 ; encoding: [0x69,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, vcc_lo
+// GFX12: v_bfrev_b32_e32 v5, vcc_lo ; encoding: [0x6a,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, vcc_hi
+// GFX12: v_bfrev_b32_e32 v5, vcc_hi ; encoding: [0x6b,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, ttmp15
+// GFX12: v_bfrev_b32_e32 v5, ttmp15 ; encoding: [0x7b,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, m0
+// GFX12: v_bfrev_b32_e32 v5, m0 ; encoding: [0x7d,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, exec_lo
+// GFX12: v_bfrev_b32_e32 v5, exec_lo ; encoding: [0x7e,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, exec_hi
+// GFX12: v_bfrev_b32_e32 v5, exec_hi ; encoding: [0x7f,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, null
+// GFX12: v_bfrev_b32_e32 v5, null ; encoding: [0x7c,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, -1
+// GFX12: v_bfrev_b32_e32 v5, -1 ; encoding: [0xc1,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, 0.5
+// GFX12: v_bfrev_b32_e32 v5, 0.5 ; encoding: [0xf0,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v5, src_scc
+// GFX12: v_bfrev_b32_e32 v5, src_scc ; encoding: [0xfd,0x70,0x0a,0x7e]
+
+v_bfrev_b32 v255, 0xaf123456
+// GFX12: v_bfrev_b32_e32 v255, 0xaf123456 ; encoding: [0xff,0x70,0xfe,0x7f,0x56,0x34,0x12,0xaf]
+
+v_ceil_f16 v5, v1
+// GFX12: v_ceil_f16_e32 v5, v1 ; encoding: [0x01,0xb9,0x0a,0x7e]
+
+v_ceil_f16 v5, v127
+// GFX12: v_ceil_f16_e32 v5, v127 ; encoding: [0x7f,0xb9,0x0a,0x7e]
+
+v_ceil_f16 v5, s1
+// GFX12: v_ceil_f16_e32 v5, s1 ; encoding: [0x01,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, s105
+// GFX12: v_ceil_f16_e32 v5, s105 ; encoding: [0x69,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, vcc_lo
+// GFX12: v_ceil_f16_e32 v5, vcc_lo ; encoding: [0x6a,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, vcc_hi
+// GFX12: v_ceil_f16_e32 v5, vcc_hi ; encoding: [0x6b,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, ttmp15
+// GFX12: v_ceil_f16_e32 v5, ttmp15 ; encoding: [0x7b,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, m0
+// GFX12: v_ceil_f16_e32 v5, m0 ; encoding: [0x7d,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, exec_lo
+// GFX12: v_ceil_f16_e32 v5, exec_lo ; encoding: [0x7e,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, exec_hi
+// GFX12: v_ceil_f16_e32 v5, exec_hi ; encoding: [0x7f,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, null
+// GFX12: v_ceil_f16_e32 v5, null ; encoding: [0x7c,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, -1
+// GFX12: v_ceil_f16_e32 v5, -1 ; encoding: [0xc1,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, 0.5
+// GFX12: v_ceil_f16_e32 v5, 0.5 ; encoding: [0xf0,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v5, src_scc
+// GFX12: v_ceil_f16_e32 v5, src_scc ; encoding: [0xfd,0xb8,0x0a,0x7e]
+
+v_ceil_f16 v127, 0xfe0b
+// GFX12: v_ceil_f16_e32 v127, 0xfe0b ; encoding: [0xff,0xb8,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_ceil_f32 v5, v1
+// GFX12: v_ceil_f32_e32 v5, v1 ; encoding: [0x01,0x45,0x0a,0x7e]
+
+v_ceil_f32 v5, v255
+// GFX12: v_ceil_f32_e32 v5, v255 ; encoding: [0xff,0x45,0x0a,0x7e]
+
+v_ceil_f32 v5, s1
+// GFX12: v_ceil_f32_e32 v5, s1 ; encoding: [0x01,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, s105
+// GFX12: v_ceil_f32_e32 v5, s105 ; encoding: [0x69,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, vcc_lo
+// GFX12: v_ceil_f32_e32 v5, vcc_lo ; encoding: [0x6a,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, vcc_hi
+// GFX12: v_ceil_f32_e32 v5, vcc_hi ; encoding: [0x6b,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, ttmp15
+// GFX12: v_ceil_f32_e32 v5, ttmp15 ; encoding: [0x7b,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, m0
+// GFX12: v_ceil_f32_e32 v5, m0 ; encoding: [0x7d,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, exec_lo
+// GFX12: v_ceil_f32_e32 v5, exec_lo ; encoding: [0x7e,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, exec_hi
+// GFX12: v_ceil_f32_e32 v5, exec_hi ; encoding: [0x7f,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, null
+// GFX12: v_ceil_f32_e32 v5, null ; encoding: [0x7c,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, -1
+// GFX12: v_ceil_f32_e32 v5, -1 ; encoding: [0xc1,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, 0.5
+// GFX12: v_ceil_f32_e32 v5, 0.5 ; encoding: [0xf0,0x44,0x0a,0x7e]
+
+v_ceil_f32 v5, src_scc
+// GFX12: v_ceil_f32_e32 v5, src_scc ; encoding: [0xfd,0x44,0x0a,0x7e]
+
+v_ceil_f32 v255, 0xaf123456
+// GFX12: v_ceil_f32_e32 v255, 0xaf123456 ; encoding: [0xff,0x44,0xfe,0x7f,0x56,0x34,0x12,0xaf]
+
+v_ceil_f64 v[5:6], v[1:2]
+// GFX12: v_ceil_f64_e32 v[5:6], v[1:2] ; encoding: [0x01,0x31,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], v[254:255]
+// GFX12: v_ceil_f64_e32 v[5:6], v[254:255] ; encoding: [0xfe,0x31,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], s[2:3]
+// GFX12: v_ceil_f64_e32 v[5:6], s[2:3] ; encoding: [0x02,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], s[104:105]
+// GFX12: v_ceil_f64_e32 v[5:6], s[104:105] ; encoding: [0x68,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], vcc
+// GFX12: v_ceil_f64_e32 v[5:6], vcc ; encoding: [0x6a,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], ttmp[14:15]
+// GFX12: v_ceil_f64_e32 v[5:6], ttmp[14:15] ; encoding: [0x7a,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], exec
+// GFX12: v_ceil_f64_e32 v[5:6], exec ; encoding: [0x7e,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], null
+// GFX12: v_ceil_f64_e32 v[5:6], null ; encoding: [0x7c,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], -1
+// GFX12: v_ceil_f64_e32 v[5:6], -1 ; encoding: [0xc1,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], 0.5
+// GFX12: v_ceil_f64_e32 v[5:6], 0.5 ; encoding: [0xf0,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[5:6], src_scc
+// GFX12: v_ceil_f64_e32 v[5:6], src_scc ; encoding: [0xfd,0x30,0x0a,0x7e]
+
+v_ceil_f64 v[254:255], 0xaf123456
+// GFX12: v_ceil_f64_e32 v[254:255], 0xaf123456 ; encoding: [0xff,0x30,0xfc,0x7f,0x56,0x34,0x12,0xaf]
+
+v_cls_i32 v5, v1
+// GFX12: v_cls_i32_e32 v5, v1 ; encoding: [0x01,0x77,0x0a,0x7e]
+
+v_cls_i32 v5, v255
+// GFX12: v_cls_i32_e32 v5, v255 ; encoding: [0xff,0x77,0x0a,0x7e]
+
+v_cls_i32 v5, s1
+// GFX12: v_cls_i32_e32 v5, s1 ; encoding: [0x01,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, s105
+// GFX12: v_cls_i32_e32 v5, s105 ; encoding: [0x69,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, vcc_lo
+// GFX12: v_cls_i32_e32 v5, vcc_lo ; encoding: [0x6a,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, vcc_hi
+// GFX12: v_cls_i32_e32 v5, vcc_hi ; encoding: [0x6b,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, ttmp15
+// GFX12: v_cls_i32_e32 v5, ttmp15 ; encoding: [0x7b,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, m0
+// GFX12: v_cls_i32_e32 v5, m0 ; encoding: [0x7d,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, exec_lo
+// GFX12: v_cls_i32_e32 v5, exec_lo ; encoding: [0x7e,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, exec_hi
+// GFX12: v_cls_i32_e32 v5, exec_hi ; encoding: [0x7f,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, null
+// GFX12: v_cls_i32_e32 v5, null ; encoding: [0x7c,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, -1
+// GFX12: v_cls_i32_e32 v5, -1 ; encoding: [0xc1,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, 0.5
+// GFX12: v_cls_i32_e32 v5, 0.5 ; encoding: [0xf0,0x76,0x0a,0x7e]
+
+v_cls_i32 v5, src_scc
+// GFX12: v_cls_i32_e32 v5, src_scc ; encoding: [0xfd,0x76,0x0a,0x7e]
+
+v_cls_i32 v255, 0xaf123456
+// GFX12: v_cls_i32_e32 v255, 0xaf123456 ; encoding: [0xff,0x76,0xfe,0x7f,0x56,0x34,0x12,0xaf]
+
+v_clz_i32_u32 v5, v1
+// GFX12: v_clz_i32_u32_e32 v5, v1 ; encoding: [0x01,0x73,0x0a,0x7e]
+
+v_clz_i32_u32 v5, v255
+// GFX12: v_clz_i32_u32_e32 v5, v255 ; encoding: [0xff,0x73,0x0a,0x7e]
+
+v_clz_i32_u32 v5, s1
+// GFX12: v_clz_i32_u32_e32 v5, s1 ; encoding: [0x01,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, s105
+// GFX12: v_clz_i32_u32_e32 v5, s105 ; encoding: [0x69,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, vcc_lo
+// GFX12: v_clz_i32_u32_e32 v5, vcc_lo ; encoding: [0x6a,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, vcc_hi
+// GFX12: v_clz_i32_u32_e32 v5, vcc_hi ; encoding: [0x6b,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, ttmp15
+// GFX12: v_clz_i32_u32_e32 v5, ttmp15 ; encoding: [0x7b,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, m0
+// GFX12: v_clz_i32_u32_e32 v5, m0 ; encoding: [0x7d,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, exec_lo
+// GFX12: v_clz_i32_u32_e32 v5, exec_lo ; encoding: [0x7e,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, exec_hi
+// GFX12: v_clz_i32_u32_e32 v5, exec_hi ; encoding: [0x7f,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, null
+// GFX12: v_clz_i32_u32_e32 v5, null ; encoding: [0x7c,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, -1
+// GFX12: v_clz_i32_u32_e32 v5, -1 ; encoding: [0xc1,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, 0.5
+// GFX12: v_clz_i32_u32_e32 v5, 0.5 ; encoding: [0xf0,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v5, src_scc
+// GFX12: v_clz_i32_u32_e32 v5, src_scc ; encoding: [0xfd,0x72,0x0a,0x7e]
+
+v_clz_i32_u32 v255, 0xaf123456
+// GFX12: v_clz_i32_u32_e32 v255, 0xaf123456 ; encoding: [0xff,0x72,0xfe,0x7f,0x56,0x34,0x12,0xaf]
+
+v_cos_f16 v5, v1
+// GFX12: v_cos_f16_e32 v5, v1 ; encoding: [0x01,0xc3,0x0a,0x7e]
+
+v_cos_f16 v5, v127
+// GFX12: v_cos_f16_e32 v5, v127 ; encoding: [0x7f,0xc3,0x0a,0x7e]
+
+v_cos_f16 v5, s1
+// GFX12: v_cos_f16_e32 v5, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, s105
+// GFX12: v_cos_f16_e32 v5, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, vcc_lo
+// GFX12: v_cos_f16_e32 v5, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, vcc_hi
+// GFX12: v_cos_f16_e32 v5, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, ttmp15
+// GFX12: v_cos_f16_e32 v5, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, m0
+// GFX12: v_cos_f16_e32 v5, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, exec_lo
+// GFX12: v_cos_f16_e32 v5, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, exec_hi
+// GFX12: v_cos_f16_e32 v5, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, null
+// GFX12: v_cos_f16_e32 v5, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, -1
+// GFX12: v_cos_f16_e32 v5, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, 0.5
+// GFX12: v_cos_f16_e32 v5, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
+
+v_cos_f16 v5, src_scc
+// GFX12: v_cos_f16_e32 v5, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
+
+v_cos_f16 v127, 0xfe0b
+// GFX12: v_cos_f16_e32 v127, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_cos_f32 v5, v1
+// GFX12: v_cos_f32_e32 v5, v1 ; encoding: [0x01,0x6d,0x0a,0x7e]
+
+v_cos_f32 v5, v255
+// GFX12: v_cos_f32_e32 v5, v255 ; encoding: [0xff,0x6d,0x0a,0x7e]
+
+v_cos_f32 v5, s1
+// GFX12: v_cos_f32_e32 v5, s1 ; encoding: [0x01,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, s105
+// GFX12: v_cos_f32_e32 v5, s105 ; encoding: [0x69,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, vcc_lo
+// GFX12: v_cos_f32_e32 v5, vcc_lo ; encoding: [0x6a,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, vcc_hi
+// GFX12: v_cos_f32_e32 v5, vcc_hi ; encoding: [0x6b,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, ttmp15
+// GFX12: v_cos_f32_e32 v5, ttmp15 ; encoding: [0x7b,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, m0
+// GFX12: v_cos_f32_e32 v5, m0 ; encoding: [0x7d,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, exec_lo
+// GFX12: v_cos_f32_e32 v5, exec_lo ; encoding: [0x7e,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, exec_hi
+// GFX12: v_cos_f32_e32 v5, exec_hi ; encoding: [0x7f,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, null
+// GFX12: v_cos_f32_e32 v5, null ; encoding: [0x7c,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, -1
+// GFX12: v_cos_f32_e32 v5, -1 ; encoding: [0xc1,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, 0.5
+// GFX12: v_cos_f32_e32 v5, 0.5 ; encoding: [0xf0,0x6c,0x0a,0x7e]
+
+v_cos_f32 v5, src_scc
+// GFX12: v_cos_f32_e32 v5, src_scc ; encoding: [0xfd,0x6c,0x0a,0x7e]
+
+v_cos_f32 v255, 0xaf123456
+// GFX12: v_cos_f32_e32 v255, 0xaf123456 ; encoding: [0xff,0x6c,0xfe,0x7f,0x56,0x34,0x12,0xaf]
+
+v_ctz_i32_b32 v5, v1
+// GFX12: v_ctz_i32_b32_e32 v5, v1 ; encoding: [0x01,0x75,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, v255
+// GFX12: v_ctz_i32_b32_e32 v5, v255 ; encoding: [0xff,0x75,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, s1
+// GFX12: v_ctz_i32_b32_e32 v5, s1 ; encoding: [0x01,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, s105
+// GFX12: v_ctz_i32_b32_e32 v5, s105 ; encoding: [0x69,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, vcc_lo
+// GFX12: v_ctz_i32_b32_e32 v5, vcc_lo ; encoding: [0x6a,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, vcc_hi
+// GFX12: v_ctz_i32_b32_e32 v5, vcc_hi ; encoding: [0x6b,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, ttmp15
+// GFX12: v_ctz_i32_b32_e32 v5, ttmp15 ; encoding: [0x7b,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, m0
+// GFX12: v_ctz_i32_b32_e32 v5, m0 ; encoding: [0x7d,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, exec_lo
+// GFX12: v_ctz_i32_b32_e32 v5, exec_lo ; encoding: [0x7e,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, exec_hi
+// GFX12: v_ctz_i32_b32_e32 v5, exec_hi ; encoding: [0x7f,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, null
+// GFX12: v_ctz_i32_b32_e32 v5, null ; encoding: [0x7c,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, -1
+// GFX12: v_ctz_i32_b32_e32 v5, -1 ; encoding: [0xc1,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, 0.5
+// GFX12: v_ctz_i32_b32_e32 v5, 0.5 ; encoding: [0xf0,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v5, src_scc
+// GFX12: v_ctz_i32_b32_e32 v5, src_scc ; encoding: [0xfd,0x74,0x0a,0x7e]
+
+v_ctz_i32_b32 v255, 0xaf123456
+// GFX12: v_ctz_i32_b32_e32 v255, 0xaf123456 ; encoding: [0xff,0x74,0xfe,0x7f,0x56,0x34,0x12,0xaf]
+
+v_cvt_f32_bf8_e32 v1, s3
+// GFX12: v_cvt_f32_bf8_e32 v1, s3 ; encoding: [0x03,0xda,0x02,0x7e]
+
+v_cvt_f32_bf8_e32 v1, 3
+// GFX12: v_cvt_f32_bf8_e32 v1, 3 ; encoding: [0x83,0xda,0x02,0x7e]
+
+v_cvt_f32_bf8_e32 v1, v3
+// GFX12: v_cvt_f32_bf8_e32 v1, v3 ; encoding: [0x03,0xdb,0x02,0x7e]
+
+v_cvt_f32_fp8_e32 v1, s3
+// GFX12: v_cvt_f32_fp8_e32 v1, s3 ; encoding: [0x03,0xd8,0x02,0x7e]
+
+v_cvt_f32_fp8_e32 v1, 3
+// GFX12: v_cvt_f32_fp8_e32 v1, 3 ; encoding: [0x83,0xd8,0x02,0x7e]
+
+v_cvt_f32_fp8_e32 v1, v3
+// GFX12: v_cvt_f32_fp8_e32 v1, v3 ; encoding: [0x03,0xd9,0x02,0x7e]
+
+v_cvt_pk_f32_bf8_e32 v[2:3], s3
+// GFX12: v_cvt_pk_f32_bf8_e32 v[2:3], s3 ; encoding: [0x03,0xde,0x04,0x7e]
+
+v_cvt_pk_f32_bf8_e32 v[3:4], s5
+// GFX12: v_cvt_pk_f32_bf8_e32 v[3:4], s5 ; encoding: [0x05,0xde,0x06,0x7e]
+
+v_cvt_pk_f32_bf8_e32 v[2:3], 3
+// GFX12: v_cvt_pk_f32_bf8_e32 v[2:3], 3 ; encoding: [0x83,0xde,0x04,0x7e]
+
+v_cvt_pk_f32_bf8_e32 v[3:4], 3
+// GFX12: v_cvt_pk_f32_bf8_e32 v[3:4], 3 ; encoding: [0x83,0xde,0x06,0x7e]
+
+v_cvt_pk_f32_bf8_e32 v[2:3], v3
+// GFX12: v_cvt_pk_f32_bf8_e32 v[2:3], v3 ; encoding: [0x03,0xdf,0x04,0x7e]
+
+v_cvt_pk_f32_bf8_e32 v[3:4], v3
+// GFX12: v_cvt_pk_f32_bf8_e32 v[3:4], v3 ; encoding: [0x03,0xdf,0x06,0x7e]
+
+v_cvt_pk_f32_fp8_e32 v[2:3], s3
+// GFX12: v_cvt_pk_f32_fp8_e32 v[2:3], s3 ; encoding: [0x03,0xdc,0x04,0x7e]
+
+v_cvt_pk_f32_fp8_e32 v[2:3], 3
+// GFX12: v_cvt_pk_f32_fp8_e32 v[2:3], 3 ; encoding: [0x83,0xdc,0x04,0x7e]
+
+v_cvt_pk_f32_fp8_e32 v[2:3], v3
+// GFX12: v_cvt_pk_f32_fp8_e32 v[2:3], v3 ; encoding: [0x03,0xdd,0x04,0x7e]
+
+v_cvt_f16_f32 v5, v1
+// GFX12: v_cvt_f16_f32_e32 v5, v1 ; encoding: [0x01,0x15,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, v255
+// GFX12: v_cvt_f16_f32_e32 v5, v255 ; encoding: [0xff,0x15,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, s1
+// GFX12: v_cvt_f16_f32_e32 v5, s1 ; encoding: [0x01,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, s105
+// GFX12: v_cvt_f16_f32_e32 v5, s105 ; encoding: [0x69,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, vcc_lo
+// GFX12: v_cvt_f16_f32_e32 v5, vcc_lo ; encoding: [0x6a,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, vcc_hi
+// GFX12: v_cvt_f16_f32_e32 v5, vcc_hi ; encoding: [0x6b,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, ttmp15
+// GFX12: v_cvt_f16_f32_e32 v5, ttmp15 ; encoding: [0x7b,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, m0
+// GFX12: v_cvt_f16_f32_e32 v5, m0 ; encoding: [0x7d,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, exec_lo
+// GFX12: v_cvt_f16_f32_e32 v5, exec_lo ; encoding: [0x7e,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, exec_hi
+// GFX12: v_cvt_f16_f32_e32 v5, exec_hi ; encoding: [0x7f,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, null
+// GFX12: v_cvt_f16_f32_e32 v5, null ; encoding: [0x7c,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, -1
+// GFX12: v_cvt_f16_f32_e32 v5, -1 ; encoding: [0xc1,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, 0.5
+// GFX12: v_cvt_f16_f32_e32 v5, 0.5 ; encoding: [0xf0,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v5, src_scc
+// GFX12: v_cvt_f16_f32_e32 v5, src_scc ; encoding: [0xfd,0x14,0x0a,0x7e]
+
+v_cvt_f16_f32 v127, 0xaf123456
+// GFX12: v_cvt_f16_f32_e32 v127, 0xaf123456 ; encoding: [0xff,0x14,0xfe,0x7e,0x56,0x34,0x12,0xaf]
+
+v_cvt_f16_i16 v5, v1
+// GFX12: v_cvt_f16_i16_e32 v5, v1 ; encoding: [0x01,0xa3,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, v127
+// GFX12: v_cvt_f16_i16_e32 v5, v127 ; encoding: [0x7f,0xa3,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, s1
+// GFX12: v_cvt_f16_i16_e32 v5, s1 ; encoding: [0x01,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, s105
+// GFX12: v_cvt_f16_i16_e32 v5, s105 ; encoding: [0x69,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, vcc_lo
+// GFX12: v_cvt_f16_i16_e32 v5, vcc_lo ; encoding: [0x6a,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, vcc_hi
+// GFX12: v_cvt_f16_i16_e32 v5, vcc_hi ; encoding: [0x6b,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, ttmp15
+// GFX12: v_cvt_f16_i16_e32 v5, ttmp15 ; encoding: [0x7b,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, m0
+// GFX12: v_cvt_f16_i16_e32 v5, m0 ; encoding: [0x7d,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, exec_lo
+// GFX12: v_cvt_f16_i16_e32 v5, exec_lo ; encoding: [0x7e,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, exec_hi
+// GFX12: v_cvt_f16_i16_e32 v5, exec_hi ; encoding: [0x7f,0xa2,0x0a,0x7e]
+
+v_cvt_f16_i16 v5, null
+// GFX12: v_cvt_f16_i16_e32 v5, null ; encodin...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/100849
More information about the llvm-commits
mailing list