[llvm] [AMDGPU][True16][MC] true16 for v_cmp_class_f16 (PR #122984)

[Brox Chen via llvm-commits]

================
@@ -1,84 +1,160 @@
-; NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --sort --version 5
+// NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --sort --version 5
 // RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32,+real-true16 -show-encoding %s | FileCheck --check-prefix=W32 %s
 // RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 -show-encoding %s | FileCheck --check-prefix=W64 %s
 // RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32,+real-true16 %s 2>&1 > /dev/null | FileCheck --check-prefix=W32-ERR --implicit-check-not=error: %s
 // RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 %s 2>&1 > /dev/null | FileCheck --check-prefix=W64-ERR --implicit-check-not=error: %s
 
-v_cmp_class_f16 vcc, v1, v255
-// W64: v_cmp_class_f16_e64 vcc, v1, v255       ; encoding: [0x6a,0x00,0x7d,0xd4,0x01,0xff,0x03,0x00]
-// W32-ERR: :[[@LINE-2]]:1: error: operands are not valid for this GPU or mode
+v_cmp_class_f16 vcc, v1.h, v255.h
+// W64: v_cmp_class_f16_e64 vcc, v1.h, v255.h   ; encoding: [0x6a,0x18,0x7d,0xd4,0x01,0xff,0x03,0x00]
+// W32-ERR: :[[@LINE-2]]:17: error: invalid operand for instruction
 
-v_cmp_class_f16 vcc, v1, v255 dpp8:[7,6,5,4,3,2,1,0]
-// W64: v_cmp_class_f16_e64_dpp vcc, v1, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x6a,0x00,0x7d,0xd4,0xe9,0xfe,0x03,0x00,0x01,0x77,0x39,0x05]
+v_cmp_class_f16 vcc, v1.h, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// W64: v_cmp_class_f16_e64_dpp vcc, v1.h, v255.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x6a,0x18,0x7d,0xd4,0xe9,0xfe,0x03,0x00,0x01,0x77,0x39,0x05]
 // W32-ERR: :[[@LINE-2]]:17: error: invalid operand for instruction
 
-v_cmp_class_f16 vcc, v1, v255 quad_perm:[3,2,1,0]
-// W64: v_cmp_class_f16_e64_dpp vcc, v1, v255 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x6a,0x00,0x7d,0xd4,0xfa,0xfe,0x03,0x00,0x01,0x1b,0x00,0xff]
+v_cmp_class_f16 vcc, v1.h, v255.h quad_perm:[3,2,1,0]
+// W64: v_cmp_class_f16_e64_dpp vcc, v1.h, v255.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x6a,0x18,0x7d,0xd4,0xfa,0xfe,0x03,0x00,0x01,0x1b,0x00,0xff]
 // W32-ERR: :[[@LINE-2]]:17: error: invalid operand for instruction
 
-v_cmp_class_f16 vcc, v127, v255
-// W64: v_cmp_class_f16_e64 vcc, v127, v255     ; encoding: [0x6a,0x00,0x7d,0xd4,0x7f,0xff,0x03,0x00]
-// W32-ERR: :[[@LINE-2]]:1: error: operands are not valid for this GPU or mode
+v_cmp_class_f16 vcc, v1.l, v255.l
----------------
broxigarchen wrote:

The t16_promote and t16_error file are sorted in alphabetic order thus they have this difference.

https://github.com/llvm/llvm-project/pull/122984