blob: 1eebd98bfe24f50c249f8cea64fbf83f0c7c5259 [file] [log] [blame]
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 -show-encoding %s | FileCheck --check-prefixes=GFX11,W32 %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -show-encoding %s | FileCheck --check-prefixes=GFX11,W64 %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 %s 2>&1 | FileCheck --check-prefix=W32-ERR --implicit-check-not=error: %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 %s 2>&1 | FileCheck --check-prefix=W64-ERR --implicit-check-not=error: %s
// =========================================================
// dpp8
// =========================================================
// 32 bit
v_cmp_le_u16_dpp v1, v2 dpp8:[7,7,7,3,4,4,6,7] fi:1
// GFX11: encoding: [0xea,0x04,0x76,0x7c,0x01,0xff,0x47,0xfa]
v_cmp_le_i16_dpp v1, v2 dpp8:[7,7,7,3,4,4,6,7]
// GFX11: encoding: [0xe9,0x04,0x66,0x7c,0x01,0xff,0x47,0xfa]
// w32
v_cmp_le_i32_dpp vcc_lo, v1, v255 dpp8:[0,2,1,3,4,5,6,7]
// W32: encoding: [0xe9,0xfe,0x87,0x7c,0x01,0x50,0xc6,0xfa]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_tru_f32_dpp vcc_lo, v1, v2 dpp8:[0,2,1,3,4,5,6,7]
// W32: encoding: [0xe9,0x04,0x3e,0x7c,0x01,0x50,0xc6,0xfa]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// check vcc/vcc_lo have been added
v_cmp_lt_f32_dpp v1, v2 dpp8:[2,3,4,1,3,3,3,3]
// W32: v_cmp_lt_f32 vcc_lo, v1, v2 dpp8:[2,3,4,1,3,3,3,3] ; encoding: [0xe9,0x04,0x22,0x7c,0x01,0x1a,0xb3,0x6d]
// W64: v_cmp_lt_f32 vcc, v1, v2 dpp8:[2,3,4,1,3,3,3,3] ; encoding: [0xe9,0x04,0x22,0x7c,0x01,0x1a,0xb3,0x6d]
// w64
v_cmp_lt_u16_dpp vcc, v1, v2 dpp8:[7,6,5,3,4,2,1,0] fi:1
// W64: encoding: [0xea,0x04,0x72,0x7c,0x01,0x77,0x47,0x05]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmp class
v_cmp_class_f16_dpp vcc, v1, v2 dpp8:[7,6,5,3,4,2,1,0] fi:1
// W64: encoding: [0xea,0x04,0xfa,0x7c,0x01,0x77,0x47,0x05]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmpx
v_cmpx_f_i32_dpp v0, v2 dpp8:[7,6,5,3,4,2,1,0] fi:1
// GFX11: encoding: [0xea,0x04,0x80,0x7d,0x00,0x77,0x47,0x05]
v_cmpx_t_f32_dpp v255, v2 dpp8:[7,6,5,3,4,2,1,0]
// GFX11: encoding: [0xe9,0x04,0x3e,0x7d,0xff,0x77,0x47,0x05]
// cmpx class
v_cmpx_class_f16_dpp v12, v101 dpp8:[7,6,5,3,4,2,1,0]
// GFX11: encoding: [0xe9,0xca,0xfa,0x7d,0x0c,0x77,0x47,0x05]
// =========================================================
// 64 bit
v_cmp_lt_i16_e64_dpp s[50:51], v1, v22 dpp8:[7,6,5,3,4,2,1,0]
// W64: encoding: [0x32,0x00,0x31,0xd4,0xe9,0x2c,0x02,0x00,0x01,0x77,0x47,0x05]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_lt_i16_e64_dpp s10, v10, v2 dpp8:[7,6,5,3,4,2,1,0]
// W32: encoding: [0x0a,0x00,0x31,0xd4,0xe9,0x04,0x02,0x00,0x0a,0x77,0x47,0x05]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w32
v_cmp_gt_i32_e64_dpp s10, v1, v50 dpp8:[0,1,2,3,4,5,6,7] fi:1
// W32: encoding: [0x0a,0x00,0x44,0xd4,0xea,0x64,0x02,0x00,0x01,0x88,0xc6,0xfa]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_ngt_f32_e64_dpp s10, -v1, v2 dpp8:[0,1,2,3,4,5,6,7] fi:1
// W32: encoding: [0x0a,0x00,0x1b,0xd4,0xea,0x04,0x02,0x20,0x01,0x88,0xc6,0xfa]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w64
v_cmp_f_f32_e64_dpp s[10:11], v1, v2 dpp8:[0,1,2,3,4,5,6,7] fi:1
// W64: encoding: [0x0a,0x00,0x10,0xd4,0xea,0x04,0x02,0x00,0x01,0x88,0xc6,0xfa]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_nle_f32_e64_dpp s[10:11], v2, v201 dpp8:[0,1,6,3,4,5,6,7]
// W64: encoding: [0x0a,0x00,0x1c,0xd4,0xe9,0x92,0x03,0x00,0x02,0x88,0xc7,0xfa]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_lt_f16_e64_dpp s[10:11], v240, -v2 dpp8:[0,1,6,3,4,5,6,7]
// W64: encoding: [0x0a,0x00,0x01,0xd4,0xe9,0x04,0x02,0x40,0xf0,0x88,0xc7,0xfa]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmp class
// w32
v_cmp_class_f32_e64_dpp s10, v10, v2 dpp8:[0,1,6,3,4,5,6,7]
// W32: encoding: [0x0a,0x00,0x7e,0xd4,0xe9,0x04,0x02,0x00,0x0a,0x88,0xc7,0xfa]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w64
v_cmp_class_f16_e64_dpp vcc, v1, v2 dpp8:[0,1,6,3,4,5,6,7]
// W64: encoding: [0x6a,0x00,0x7d,0xd4,0xe9,0x04,0x02,0x00,0x01,0x88,0xc7,0xfa]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmpx
v_cmpx_eq_i16_e64_dpp v5, v25 dpp8:[0,1,6,3,4,5,6,7] fi:1
// GFX11: encoding: [0x7e,0x00,0xb2,0xd4,0xea,0x32,0x02,0x00,0x05,0x88,0xc7,0xfa]
v_cmpx_ge_i32_e64_dpp v0, v3 dpp8:[0,1,6,3,4,5,6,7] fi:1
// GFX11: encoding: [0x7e,0x00,0xc6,0xd4,0xea,0x06,0x02,0x00,0x00,0x88,0xc7,0xfa]
// cmpx class
v_cmpx_class_f32_e64_dpp v1, v20 dpp8:[0,1,6,3,4,5,6,7] fi:1
// GFX11: encoding: [0x7e,0x00,0xfe,0xd4,0xea,0x28,0x02,0x00,0x01,0x88,0xc7,0xfa]
// ================================================================
// dpp
// ================================================================
// 32 bit
v_cmp_gt_u16_dpp v1, v2 row_shl:0x7 row_mask:0x0 bank_mask:0x0 fi:1
// GFX11: encoding: [0xfa,0x04,0x78,0x7c,0x01,0x07,0x05,0x00]
v_cmp_gt_i16_dpp v1, v2 quad_perm:[1,3,1,0] row_mask:0x7
// GFX11: encoding: [0xfa,0x04,0x68,0x7c,0x01,0x1d,0x00,0x7f]
v_cmp_lt_f32 v1, -v2 quad_perm:[0,1,2,2]
// GFX11: encoding: [0xfa,0x04,0x22,0x7c,0x01,0xa4,0x40,0xff]
// w32
v_cmp_gt_i32_dpp vcc_lo, v1, v255 row_mirror bank_mask:0x2 fi:1
// W32: encoding: [0xfa,0xfe,0x89,0x7c,0x01,0x40,0x05,0xf2]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_f_f32_dpp vcc_lo, v1, v2 row_shl:0x7 row_mask:0x0 bank_mask:0x0
// W32: encoding: [0xfa,0x04,0x20,0x7c,0x01,0x07,0x01,0x00]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w64
v_cmp_ge_u16_dpp vcc, v1, v2 row_share:0xa bound_ctrl:0
// W64: encoding: [0xfa,0x04,0x7c,0x7c,0x01,0x5a,0x09,0xff]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmp class
v_cmp_class_f16_dpp vcc, v1, v2 row_half_mirror bound_ctrl:0
// W64: encoding: [0xfa,0x04,0xfa,0x7c,0x01,0x41,0x09,0xff]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmpx
v_cmpx_t_i32_dpp v0, v2 row_shr:0xe row_mask:0x3 bank_mask:0xa bound_ctrl:0
// GFX11: encoding: [0xfa,0x04,0x8e,0x7d,0x00,0x1e,0x09,0x3a]
v_cmpx_f_f32_dpp v255, v2 quad_perm:[2,3,0,0]
// GFX11: encoding: [0xfa,0x04,0x20,0x7d,0xff,0x0e,0x00,0xff]
// cmpx class
v_cmpx_class_f16_dpp v12, v101 quad_perm:[2,3,0,0] fi:1
// GFX11: encoding: [0xfa,0xca,0xfa,0x7d,0x0c,0x0e,0x04,0xff]
v_cmpx_class_f16_dpp abs(v12), v101 quad_perm:[2,3,0,0]
// GFX11: encoding: [0xfa,0xca,0xfa,0x7d,0x0c,0x0e,0x20,0xff]
// =========================================================
// 64 bit
v_cmp_ge_i16_e64_dpp s[50:51], v1, v22 quad_perm:[2,2,3,1]
// W64: encoding: [0x32,0x00,0x36,0xd4,0xfa,0x2c,0x02,0x00,0x01,0x7a,0x00,0xff]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_ge_i16_e64_dpp s10, v10, v2 quad_perm:[0,2,3,1] row_mask:0x0
// W32: encoding: [0x0a,0x00,0x36,0xd4,0xfa,0x04,0x02,0x00,0x0a,0x78,0x00,0x0f]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w32
v_cmp_le_i32_e64_dpp s10, v1, v50 quad_perm:[0,2,3,1] row_mask:0x0
// W32: encoding: [0x0a,0x00,0x43,0xd4,0xfa,0x64,0x02,0x00,0x01,0x78,0x00,0x0f]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_nle_f32_e64_dpp s10, -v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0
// W32: encoding: [0x0a,0x00,0x1c,0xd4,0xfa,0x04,0x02,0x20,0x01,0x1b,0x00,0x00]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w64
v_cmp_t_f32_e64_dpp s[10:11], v1, v2 quad_perm:[3,2,1,0] bank_mask:0xe
// W64: encoding: [0x0a,0x00,0x1f,0xd4,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xfe]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_ngt_f32_e64_dpp s[10:11], v2, v201 row_ror:7 bank_mask:0x1 bound_ctrl:0
// W64: encoding: [0x0a,0x00,0x1b,0xd4,0xfa,0x92,0x03,0x00,0x02,0x27,0x09,0xf1]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
v_cmp_lt_f16_e64_dpp s[10:11], v240, -v2 row_xmask:0x6 row_mask:0x0 fi:1
// W64: encoding: [0x0a,0x00,0x01,0xd4,0xfa,0x04,0x02,0x40,0xf0,0x66,0x05,0x0f]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmp class
// w32
v_cmp_class_f32_e64_dpp s10, v10, v2 quad_perm:[2,2,3,1] bound_ctrl:0 fi:1
// W32: encoding: [0x0a,0x00,0x7e,0xd4,0xfa,0x04,0x02,0x00,0x0a,0x7a,0x0c,0xff]
// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// w64
v_cmp_class_f16_e64_dpp vcc, v1, v2 quad_perm:[1,2,3,1] bank_mask: 0x5 fi:1
// W64: encoding: [0x6a,0x00,0x7d,0xd4,0xfa,0x04,0x02,0x00,0x01,0x79,0x04,0xf5]
// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error
// cmpx
v_cmpx_eq_i16_e64_dpp v5, v25 quad_perm:[2,2,3,1] bound_ctrl:0 fi:1
// GFX11: encoding: [0x7e,0x00,0xb2,0xd4,0xfa,0x32,0x02,0x00,0x05,0x7a,0x0c,0xff]
v_cmpx_lt_i32_e64_dpp v0, v3 quad_perm:[3,2,1,0] bank_mask:0xe
// GFX11: encoding: [0x7e,0x00,0xc1,0xd4,0xfa,0x06,0x02,0x00,0x00,0x1b,0x00,0xfe]
// cmpx class
v_cmpx_class_f32_e64_dpp v1, v20 row_ror:7 bank_mask:0x1 bound_ctrl:0
// GFX11: encoding: [0x7e,0x00,0xfe,0xd4,0xfa,0x28,0x02,0x00,0x01,0x27,0x09,0xf1]