[llvm] Main merge true16 mc clean up 3 (PR #135588)

via llvm-commits llvm-commits at lists.llvm.org
Tue Apr 15 07:18:04 PDT 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Brox Chen (broxigarchen)

<details>
<summary>Changes</summary>



---

Patch is 353.07 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/135588.diff


10 Files Affected:

- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s (+770-308) 
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s (+273-210) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1.s (+84) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s (+238-196) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s (+84-42) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s (+294) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s (+770-308) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s (+274-208) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s (+259-196) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s (+119-56) 


``````````diff
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
index 5cb81c640f413..6facd4dca01bf 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
@@ -2,71 +2,137 @@
 // RUN: llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,+real-true16 -show-encoding %s | FileCheck --check-prefix=GFX11 --implicit-check-not=_e32 %s
 // RUN: llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64,+real-true16 -show-encoding %s | FileCheck --check-prefix=GFX11 --implicit-check-not=_e32 %s
 
-v_ceil_f16 v128, 0xfe0b
-// GFX11: v_ceil_f16_e64 v128, 0xfe0b             ; encoding: [0x80,0x00,0xdc,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_ceil_f16 v128.h, 0xfe0b
+// GFX11: v_ceil_f16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xdc,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
 
-v_ceil_f16 v255, -1
-// GFX11: v_ceil_f16_e64 v255, -1                 ; encoding: [0xff,0x00,0xdc,0xd5,0xc1,0x00,0x00,0x00]
+v_ceil_f16 v128.l, 0xfe0b
+// GFX11: v_ceil_f16_e64 v128.l, 0xfe0b           ; encoding: [0x80,0x00,0xdc,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
 
-v_ceil_f16 v255, 0.5
-// GFX11: v_ceil_f16_e64 v255, 0.5                ; encoding: [0xff,0x00,0xdc,0xd5,0xf0,0x00,0x00,0x00]
+v_ceil_f16 v255.h, -1
+// GFX11: v_ceil_f16_e64 v255.h, -1 op_sel:[0,1]  ; encoding: [0xff,0x40,0xdc,0xd5,0xc1,0x00,0x00,0x00]
 
-v_ceil_f16 v255, exec_hi
-// GFX11: v_ceil_f16_e64 v255, exec_hi            ; encoding: [0xff,0x00,0xdc,0xd5,0x7f,0x00,0x00,0x00]
+v_ceil_f16 v255.h, 0.5
+// GFX11: v_ceil_f16_e64 v255.h, 0.5 op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0xf0,0x00,0x00,0x00]
 
-v_ceil_f16 v255, exec_lo
-// GFX11: v_ceil_f16_e64 v255, exec_lo            ; encoding: [0xff,0x00,0xdc,0xd5,0x7e,0x00,0x00,0x00]
+v_ceil_f16 v255.h, exec_hi
+// GFX11: v_ceil_f16_e64 v255.h, exec_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x7f,0x00,0x00,0x00]
 
-v_ceil_f16 v255, m0
-// GFX11: v_ceil_f16_e64 v255, m0                 ; encoding: [0xff,0x00,0xdc,0xd5,0x7d,0x00,0x00,0x00]
+v_ceil_f16 v255.h, exec_lo
+// GFX11: v_ceil_f16_e64 v255.h, exec_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x7e,0x00,0x00,0x00]
 
-v_ceil_f16 v255, null
-// GFX11: v_ceil_f16_e64 v255, null               ; encoding: [0xff,0x00,0xdc,0xd5,0x7c,0x00,0x00,0x00]
+v_ceil_f16 v255.h, m0
+// GFX11: v_ceil_f16_e64 v255.h, m0 op_sel:[0,1]  ; encoding: [0xff,0x40,0xdc,0xd5,0x7d,0x00,0x00,0x00]
 
-v_ceil_f16 v255, s1
-// GFX11: v_ceil_f16_e64 v255, s1                 ; encoding: [0xff,0x00,0xdc,0xd5,0x01,0x00,0x00,0x00]
+v_ceil_f16 v255.h, null
+// GFX11: v_ceil_f16_e64 v255.h, null op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x7c,0x00,0x00,0x00]
 
-v_ceil_f16 v255, s105
-// GFX11: v_ceil_f16_e64 v255, s105               ; encoding: [0xff,0x00,0xdc,0xd5,0x69,0x00,0x00,0x00]
+v_ceil_f16 v255.h, s1
+// GFX11: v_ceil_f16_e64 v255.h, s1 op_sel:[0,1]  ; encoding: [0xff,0x40,0xdc,0xd5,0x01,0x00,0x00,0x00]
 
-v_ceil_f16 v255, src_scc
-// GFX11: v_ceil_f16_e64 v255, src_scc            ; encoding: [0xff,0x00,0xdc,0xd5,0xfd,0x00,0x00,0x00]
+v_ceil_f16 v255.h, s105
+// GFX11: v_ceil_f16_e64 v255.h, s105 op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x69,0x00,0x00,0x00]
 
-v_ceil_f16 v255, ttmp15
-// GFX11: v_ceil_f16_e64 v255, ttmp15             ; encoding: [0xff,0x00,0xdc,0xd5,0x7b,0x00,0x00,0x00]
+v_ceil_f16 v255.h, src_scc
+// GFX11: v_ceil_f16_e64 v255.h, src_scc op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0xfd,0x00,0x00,0x00]
 
-v_ceil_f16 v255, v1
-// GFX11: v_ceil_f16_e64 v255, v1                 ; encoding: [0xff,0x00,0xdc,0xd5,0x01,0x01,0x00,0x00]
+v_ceil_f16 v255.h, ttmp15
+// GFX11: v_ceil_f16_e64 v255.h, ttmp15 op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x7b,0x00,0x00,0x00]
 
-v_ceil_f16 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_ceil_f16_e64_dpp v255, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xdc,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_ceil_f16 v255.h, v1.h
+// GFX11: v_ceil_f16_e64 v255.h, v1.h op_sel:[1,1] ; encoding: [0xff,0x48,0xdc,0xd5,0x01,0x01,0x00,0x00]
 
-v_ceil_f16 v255, v1 quad_perm:[3,2,1,0]
-// GFX11: v_ceil_f16_e64_dpp v255, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_ceil_f16 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.h, v1.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xdc,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
 
-v_ceil_f16 v255, v127
-// GFX11: v_ceil_f16_e64 v255, v127               ; encoding: [0xff,0x00,0xdc,0xd5,0x7f,0x01,0x00,0x00]
+v_ceil_f16 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.h, v1.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xdc,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
 
-v_ceil_f16 v255, v127 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_ceil_f16_e64_dpp v255, v127 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xdc,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+v_ceil_f16 v255.h, v127.h
+// GFX11: v_ceil_f16_e64 v255.h, v127.h op_sel:[1,1] ; encoding: [0xff,0x48,0xdc,0xd5,0x7f,0x01,0x00,0x00]
 
-v_ceil_f16 v255, v127 quad_perm:[3,2,1,0]
-// GFX11: v_ceil_f16_e64_dpp v255, v127 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+v_ceil_f16 v255.h, v127.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.h, v127.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xdc,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
 
-v_ceil_f16 v255, vcc_hi
-// GFX11: v_ceil_f16_e64 v255, vcc_hi             ; encoding: [0xff,0x00,0xdc,0xd5,0x6b,0x00,0x00,0x00]
+v_ceil_f16 v255.h, v127.h quad_perm:[3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.h, v127.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xdc,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
 
-v_ceil_f16 v255, vcc_lo
-// GFX11: v_ceil_f16_e64 v255, vcc_lo             ; encoding: [0xff,0x00,0xdc,0xd5,0x6a,0x00,0x00,0x00]
+v_ceil_f16 v255.h, vcc_hi
+// GFX11: v_ceil_f16_e64 v255.h, vcc_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x6b,0x00,0x00,0x00]
 
-v_ceil_f16 v5, v199
-// GFX11: v_ceil_f16_e64 v5, v199                 ; encoding: [0x05,0x00,0xdc,0xd5,0xc7,0x01,0x00,0x00]
+v_ceil_f16 v255.h, vcc_lo
+// GFX11: v_ceil_f16_e64 v255.h, vcc_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xdc,0xd5,0x6a,0x00,0x00,0x00]
 
-v_ceil_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_ceil_f16_e64_dpp v5, v199 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xdc,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+v_ceil_f16 v255.l, -1
+// GFX11: v_ceil_f16_e64 v255.l, -1               ; encoding: [0xff,0x00,0xdc,0xd5,0xc1,0x00,0x00,0x00]
 
-v_ceil_f16 v5, v199 quad_perm:[3,2,1,0]
-// GFX11: v_ceil_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+v_ceil_f16 v255.l, 0.5
+// GFX11: v_ceil_f16_e64 v255.l, 0.5              ; encoding: [0xff,0x00,0xdc,0xd5,0xf0,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, exec_hi
+// GFX11: v_ceil_f16_e64 v255.l, exec_hi          ; encoding: [0xff,0x00,0xdc,0xd5,0x7f,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, exec_lo
+// GFX11: v_ceil_f16_e64 v255.l, exec_lo          ; encoding: [0xff,0x00,0xdc,0xd5,0x7e,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, m0
+// GFX11: v_ceil_f16_e64 v255.l, m0               ; encoding: [0xff,0x00,0xdc,0xd5,0x7d,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, null
+// GFX11: v_ceil_f16_e64 v255.l, null             ; encoding: [0xff,0x00,0xdc,0xd5,0x7c,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, s1
+// GFX11: v_ceil_f16_e64 v255.l, s1               ; encoding: [0xff,0x00,0xdc,0xd5,0x01,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, s105
+// GFX11: v_ceil_f16_e64 v255.l, s105             ; encoding: [0xff,0x00,0xdc,0xd5,0x69,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, src_scc
+// GFX11: v_ceil_f16_e64 v255.l, src_scc          ; encoding: [0xff,0x00,0xdc,0xd5,0xfd,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, ttmp15
+// GFX11: v_ceil_f16_e64 v255.l, ttmp15           ; encoding: [0xff,0x00,0xdc,0xd5,0x7b,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, v1.l
+// GFX11: v_ceil_f16_e64 v255.l, v1.l             ; encoding: [0xff,0x00,0xdc,0xd5,0x01,0x01,0x00,0x00]
+
+v_ceil_f16 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xdc,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+
+v_ceil_f16 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+
+v_ceil_f16 v255.l, v127.l
+// GFX11: v_ceil_f16_e64 v255.l, v127.l           ; encoding: [0xff,0x00,0xdc,0xd5,0x7f,0x01,0x00,0x00]
+
+v_ceil_f16 v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xdc,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+
+v_ceil_f16 v255.l, v127.l quad_perm:[3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v255.l, v127.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+
+v_ceil_f16 v255.l, vcc_hi
+// GFX11: v_ceil_f16_e64 v255.l, vcc_hi           ; encoding: [0xff,0x00,0xdc,0xd5,0x6b,0x00,0x00,0x00]
+
+v_ceil_f16 v255.l, vcc_lo
+// GFX11: v_ceil_f16_e64 v255.l, vcc_lo           ; encoding: [0xff,0x00,0xdc,0xd5,0x6a,0x00,0x00,0x00]
+
+v_ceil_f16 v5.h, v199.h
+// GFX11: v_ceil_f16_e64 v5.h, v199.h op_sel:[1,1] ; encoding: [0x05,0x48,0xdc,0xd5,0xc7,0x01,0x00,0x00]
+
+v_ceil_f16 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v5.h, v199.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xdc,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+
+v_ceil_f16 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v5.h, v199.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x48,0xdc,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+
+v_ceil_f16 v5.l, v199.l
+// GFX11: v_ceil_f16_e64 v5.l, v199.l             ; encoding: [0x05,0x00,0xdc,0xd5,0xc7,0x01,0x00,0x00]
+
+v_ceil_f16 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xdc,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+
+v_ceil_f16 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX11: v_ceil_f16_e64_dpp v5.l, v199.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
 
 v_cos_f16 v128.h, 0xfe0b
 // GFX11: v_cos_f16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
@@ -1160,137 +1226,269 @@ v_cvt_u32_u16 v5, v199.l dpp8:[7,6,5,4,3,2,1,0]
 v_cvt_u32_u16 v5, v199.l quad_perm:[3,2,1,0]
 // GFX11: v_cvt_u32_u16_e64_dpp v5, v199.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xeb,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
 
-v_exp_f16 v128, 0xfe0b
-// GFX11: v_exp_f16_e64 v128, 0xfe0b              ; encoding: [0x80,0x00,0xd8,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_exp_f16 v128.h, 0xfe0b
+// GFX11: v_exp_f16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xd8,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+
+v_exp_f16 v128.l, 0xfe0b
+// GFX11: v_exp_f16_e64 v128.l, 0xfe0b            ; encoding: [0x80,0x00,0xd8,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+
+v_exp_f16 v255.h, -1
+// GFX11: v_exp_f16_e64 v255.h, -1 op_sel:[0,1]   ; encoding: [0xff,0x40,0xd8,0xd5,0xc1,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, 0.5
+// GFX11: v_exp_f16_e64 v255.h, 0.5 op_sel:[0,1]  ; encoding: [0xff,0x40,0xd8,0xd5,0xf0,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, exec_hi
+// GFX11: v_exp_f16_e64 v255.h, exec_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x7f,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, exec_lo
+// GFX11: v_exp_f16_e64 v255.h, exec_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x7e,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, m0
+// GFX11: v_exp_f16_e64 v255.h, m0 op_sel:[0,1]   ; encoding: [0xff,0x40,0xd8,0xd5,0x7d,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, null
+// GFX11: v_exp_f16_e64 v255.h, null op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x7c,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, s1
+// GFX11: v_exp_f16_e64 v255.h, s1 op_sel:[0,1]   ; encoding: [0xff,0x40,0xd8,0xd5,0x01,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, s105
+// GFX11: v_exp_f16_e64 v255.h, s105 op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x69,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, src_scc
+// GFX11: v_exp_f16_e64 v255.h, src_scc op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0xfd,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, ttmp15
+// GFX11: v_exp_f16_e64 v255.h, ttmp15 op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x7b,0x00,0x00,0x00]
+
+v_exp_f16 v255.h, v1.h
+// GFX11: v_exp_f16_e64 v255.h, v1.h op_sel:[1,1] ; encoding: [0xff,0x48,0xd8,0xd5,0x01,0x01,0x00,0x00]
+
+v_exp_f16 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.h, v1.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xd8,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+
+v_exp_f16 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.h, v1.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xd8,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+
+v_exp_f16 v255.h, v127.h
+// GFX11: v_exp_f16_e64 v255.h, v127.h op_sel:[1,1] ; encoding: [0xff,0x48,0xd8,0xd5,0x7f,0x01,0x00,0x00]
+
+v_exp_f16 v255.h, v127.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.h, v127.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xd8,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+
+v_exp_f16 v255.h, v127.h quad_perm:[3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.h, v127.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xd8,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
 
-v_exp_f16 v255, -1
-// GFX11: v_exp_f16_e64 v255, -1                  ; encoding: [0xff,0x00,0xd8,0xd5,0xc1,0x00,0x00,0x00]
+v_exp_f16 v255.h, vcc_hi
+// GFX11: v_exp_f16_e64 v255.h, vcc_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x6b,0x00,0x00,0x00]
 
-v_exp_f16 v255, 0.5
-// GFX11: v_exp_f16_e64 v255, 0.5                 ; encoding: [0xff,0x00,0xd8,0xd5,0xf0,0x00,0x00,0x00]
+v_exp_f16 v255.h, vcc_lo
+// GFX11: v_exp_f16_e64 v255.h, vcc_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xd8,0xd5,0x6a,0x00,0x00,0x00]
 
-v_exp_f16 v255, exec_hi
-// GFX11: v_exp_f16_e64 v255, exec_hi             ; encoding: [0xff,0x00,0xd8,0xd5,0x7f,0x00,0x00,0x00]
+v_exp_f16 v255.l, -1
+// GFX11: v_exp_f16_e64 v255.l, -1                ; encoding: [0xff,0x00,0xd8,0xd5,0xc1,0x00,0x00,0x00]
 
-v_exp_f16 v255, exec_lo
-// GFX11: v_exp_f16_e64 v255, exec_lo             ; encoding: [0xff,0x00,0xd8,0xd5,0x7e,0x00,0x00,0x00]
+v_exp_f16 v255.l, 0.5
+// GFX11: v_exp_f16_e64 v255.l, 0.5               ; encoding: [0xff,0x00,0xd8,0xd5,0xf0,0x00,0x00,0x00]
 
-v_exp_f16 v255, m0
-// GFX11: v_exp_f16_e64 v255, m0                  ; encoding: [0xff,0x00,0xd8,0xd5,0x7d,0x00,0x00,0x00]
+v_exp_f16 v255.l, exec_hi
+// GFX11: v_exp_f16_e64 v255.l, exec_hi           ; encoding: [0xff,0x00,0xd8,0xd5,0x7f,0x00,0x00,0x00]
 
-v_exp_f16 v255, null
-// GFX11: v_exp_f16_e64 v255, null                ; encoding: [0xff,0x00,0xd8,0xd5,0x7c,0x00,0x00,0x00]
+v_exp_f16 v255.l, exec_lo
+// GFX11: v_exp_f16_e64 v255.l, exec_lo           ; encoding: [0xff,0x00,0xd8,0xd5,0x7e,0x00,0x00,0x00]
 
-v_exp_f16 v255, s1
-// GFX11: v_exp_f16_e64 v255, s1                  ; encoding: [0xff,0x00,0xd8,0xd5,0x01,0x00,0x00,0x00]
+v_exp_f16 v255.l, m0
+// GFX11: v_exp_f16_e64 v255.l, m0                ; encoding: [0xff,0x00,0xd8,0xd5,0x7d,0x00,0x00,0x00]
 
-v_exp_f16 v255, s105
-// GFX11: v_exp_f16_e64 v255, s105                ; encoding: [0xff,0x00,0xd8,0xd5,0x69,0x00,0x00,0x00]
+v_exp_f16 v255.l, null
+// GFX11: v_exp_f16_e64 v255.l, null              ; encoding: [0xff,0x00,0xd8,0xd5,0x7c,0x00,0x00,0x00]
 
-v_exp_f16 v255, src_scc
-// GFX11: v_exp_f16_e64 v255, src_scc             ; encoding: [0xff,0x00,0xd8,0xd5,0xfd,0x00,0x00,0x00]
+v_exp_f16 v255.l, s1
+// GFX11: v_exp_f16_e64 v255.l, s1                ; encoding: [0xff,0x00,0xd8,0xd5,0x01,0x00,0x00,0x00]
 
-v_exp_f16 v255, ttmp15
-// GFX11: v_exp_f16_e64 v255, ttmp15              ; encoding: [0xff,0x00,0xd8,0xd5,0x7b,0x00,0x00,0x00]
+v_exp_f16 v255.l, s105
+// GFX11: v_exp_f16_e64 v255.l, s105              ; encoding: [0xff,0x00,0xd8,0xd5,0x69,0x00,0x00,0x00]
 
-v_exp_f16 v255, v1
-// GFX11: v_exp_f16_e64 v255, v1                  ; encoding: [0xff,0x00,0xd8,0xd5,0x01,0x01,0x00,0x00]
+v_exp_f16 v255.l, src_scc
+// GFX11: v_exp_f16_e64 v255.l, src_scc           ; encoding: [0xff,0x00,0xd8,0xd5,0xfd,0x00,0x00,0x00]
 
-v_exp_f16 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_exp_f16_e64_dpp v255, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xd8,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_exp_f16 v255.l, ttmp15
+// GFX11: v_exp_f16_e64 v255.l, ttmp15            ; encoding: [0xff,0x00,0xd8,0xd5,0x7b,0x00,0x00,0x00]
 
-v_exp_f16 v255, v1 quad_perm:[3,2,1,0]
-// GFX11: v_exp_f16_e64_dpp v255, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xd8,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_exp_f16 v255.l, v1.l
+// GFX11: v_exp_f16_e64 v255.l, v1.l              ; encoding: [0xff,0x00,0xd8,0xd5,0x01,0x01,0x00,0x00]
 
-v_exp_f16 v255, v127
-// GFX11: v_exp_f16_e64 v255, v127                ; encoding: [0xff,0x00,0xd8,0xd5,0x7f,0x01,0x00,0x00]
+v_exp_f16 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xd8,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
 
-v_exp_f16 v255, v127 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_exp_f16_e64_dpp v255, v127 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xd8,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+v_exp_f16 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xd8,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
 
-v_exp_f16 v255, v127 quad_perm:[3,2,1,0]
-// GFX11: v_exp_f16_e64_dpp v255, v127 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xd8,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+v_exp_f16 v255.l, v127.l
+// GFX11: v_exp_f16_e64 v255.l, v127.l            ; encoding: [0xff,0x00,0xd8,0xd5,0x7f,0x01,0x00,0x00]
 
-v_exp_f16 v255, vcc_hi
-// GFX11: v_exp_f16_e64 v255, vcc_hi              ; encoding: [0xff,0x00,0xd8,0xd5,0x6b,0x00,0x00,0x00]
+v_exp_f16 v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xd8,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
 
-v_exp_f16 v255, vcc_lo
-// GFX11: v_exp_f16_e64 v255, vcc_lo              ; encoding: [0xff,0x00,0xd8,0xd5,0x6a,0x00,0x00,0x00]
+v_exp_f16 v255.l, v127.l quad_perm:[3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v255.l, v127.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xd8,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
 
-v_exp_f16 v5, v199
-// GFX11: v_exp_f16_e64 v5, v199                  ; encoding: [0x05,0x00,0xd8,0xd5,0xc7,0x01,0x00,0x00]
+v_exp_f16 v255.l, vcc_hi
+// GFX11: v_exp_f16_e64 v255.l, vcc_hi            ; encoding: [0xff,0x00,0xd8,0xd5,0x6b,0x00,0x00,0x00]
 
-v_exp_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_exp_f16_e64_dpp v5, v199 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xd8,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+v_exp_f16 v255.l, vcc_lo
+// GFX11: v_exp_f16_e64 v255.l, vcc_lo            ; encoding: [0xff,0x00,0xd8,0xd5,0x6a,0x00,0x00,0x00]
 
-v_exp_f16 v5, v199 quad_perm:[3,2,1,0]
-// GFX11: v_exp_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xd8,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+v_exp_f16 v5.h, v199.h
+// GFX11: v_exp_f16_e64 v5.h, v199.h op_sel:[1,1] ; encoding: [0x05,0x48,0xd8,0xd5,0xc7,0x01,0x00,0x00]
 
-v_floor_f16 v128, 0xfe0b
-// GFX11: v_floor_f16_e64 v128, 0xfe0b            ; encoding: [0x80,0x00,0xdb,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_exp_f16 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_exp_f16_e64_dpp v5.h, v199.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xd8,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
 
-v_floor_f16 v255, -1
-// GFX11: v_...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/135588


More information about the llvm-commits mailing list