diff options
Diffstat (limited to 'llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s')
-rw-r--r-- | llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s | 442 |
1 files changed, 440 insertions, 2 deletions
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s index 0e84765..25b13ac 100644 --- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s +++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s @@ -6,6 +6,12 @@ v_add3_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_add3_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_add3_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x55,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_add3_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x55,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -47,6 +53,10 @@ v_add_co_u32_e64_dpp v5, s105, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x69,0x00,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_add_co_u32_e64_dpp v5, s105, v1, s2 dpp8:[7,6,5,4,3,2,1,0] +// W32: [0x05,0x69,0x00,0xd7,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05] +// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_add_co_u32_e64_dpp v5, vcc_lo, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x6a,0x00,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -67,6 +77,10 @@ v_add_co_u32_e64_dpp v5, s[104:105], v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W64: [0x05,0x68,0x00,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_add_co_u32_e64_dpp v5, s[104:105], v1, s2 dpp8:[7,6,5,4,3,2,1,0] +// W64: [0x05,0x68,0x00,0xd7,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05] +// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_add_co_u32_e64_dpp v5, vcc, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W64: [0x05,0x6a,0x00,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -81,6 +95,12 @@ v_add_co_u32_e64_dpp v255, null, v255, v255 clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_add_lshl_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x47,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_add_lshl_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x47,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_add_lshl_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x47,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_add_lshl_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x47,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -144,6 +164,12 @@ v_add_nc_u16_e64_dpp v255, v255, v255 clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_alignbit_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x16,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_alignbit_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x16,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_alignbit_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x16,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_alignbit_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x16,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -177,6 +203,12 @@ v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_alignbyte_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_alignbyte_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x17,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -219,6 +251,12 @@ v_and_b16_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_and_or_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x57,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_and_or_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x57,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_and_or_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x57,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_and_or_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x57,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -273,6 +311,12 @@ v_bcnt_u32_b32_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_bfe_i32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x11,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_bfe_i32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x11,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_bfe_i32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x11,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_bfe_i32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x11,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -309,6 +353,12 @@ v_bfe_i32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_bfe_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x10,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_bfe_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x10,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_bfe_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x10,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_bfe_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x10,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -345,6 +395,12 @@ v_bfe_u32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_bfi_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x12,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_bfi_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x12,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_bfi_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x12,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_bfi_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x12,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -391,6 +447,14 @@ v_cndmask_b16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x00,0x5d,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_cndmask_b16_e64_dpp v5, v1, s2, s3 dpp8:[7,6,5,4,3,2,1,0] +// W32: [0x05,0x00,0x5d,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05] +// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + +v_cndmask_b16_e64_dpp v5, v1, 10, s3 dpp8:[7,6,5,4,3,2,1,0] +// W32: [0x05,0x00,0x5d,0xd6,0xe9,0x14,0x0d,0x00,0x01,0x77,0x39,0x05] +// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_cndmask_b16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x00,0x5d,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -423,12 +487,22 @@ v_cndmask_b16_e64_dpp v5, -v1, |v2|, ttmp[14:15] dpp8:[7,6,5,4,3,2,1,0] fi:1 // W64: [0x05,0x02,0x5d,0xd6,0xea,0x04,0xea,0x21,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_cndmask_b16_e64_dpp v5, -v1, |s2|, ttmp[14:15] dpp8:[7,6,5,4,3,2,1,0] fi:1 +// W64: [0x05,0x02,0x5d,0xd6,0xea,0x04,0xe8,0x21,0x01,0x77,0x39,0x05] +// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_cndmask_b16_e64_dpp v255, -|v255|, -|v255|, null dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX12: [0xff,0x03,0x5d,0xd6,0xe9,0xfe,0xf3,0x61,0xff,0x00,0x00,0x00] v_cubeid_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0c,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_cubeid_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0c,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_cubeid_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0c,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_cubeid_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0c,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -465,6 +539,12 @@ v_cubeid_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0, v_cubema_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0f,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_cubema_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0f,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_cubema_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0f,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_cubema_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0f,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -501,6 +581,12 @@ v_cubema_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0, v_cubesc_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_cubesc_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0d,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_cubesc_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0d,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_cubesc_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0d,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -537,6 +623,12 @@ v_cubesc_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0, v_cubetc_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0e,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_cubetc_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0e,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_cubetc_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0e,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_cubetc_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0e,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -687,6 +779,12 @@ v_cvt_pk_u16_u32_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_cvt_pk_u8_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x26,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_cvt_pk_u8_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x26,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_cvt_pk_u8_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x26,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_cvt_pk_u8_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x26,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -771,6 +869,12 @@ v_cvt_pk_norm_u16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 v_div_fixup_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x54,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_div_fixup_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x54,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_div_fixup_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x54,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_div_fixup_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x54,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -807,6 +911,12 @@ v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0 v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x48,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -843,6 +953,12 @@ v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0 v_fma_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x13,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_fma_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x13,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_fma_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x13,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_fma_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x13,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -891,6 +1007,9 @@ v_ldexp_f32_e64_dpp v255, -|v255|, v255 clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_lerp_u8_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x15,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_lerp_u8_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x15,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + v_lerp_u8_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x15,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -927,6 +1046,12 @@ v_lerp_u8_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_lshl_add_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x46,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_lshl_add_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x46,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_lshl_add_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x46,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_lshl_add_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x46,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -963,6 +1088,12 @@ v_lshl_add_u32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_lshl_or_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x56,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_lshl_or_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x56,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_lshl_or_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x56,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_lshl_or_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x56,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1017,6 +1148,12 @@ v_lshrrev_b16_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_mad_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x53,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mad_i16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x53,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mad_i16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x53,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mad_i16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x53,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1050,6 +1187,12 @@ v_mad_i16_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_mad_i32_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x5a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mad_i32_i16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x5a,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mad_i32_i16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x5a,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mad_i32_i16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x5a,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1086,6 +1229,12 @@ v_mad_i32_i16_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi: v_mad_i32_i24_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mad_i32_i24_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0a,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mad_i32_i24_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0a,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mad_i32_i24_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0a,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1122,6 +1271,12 @@ v_mad_i32_i24_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi: v_mad_u16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x41,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mad_u16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x41,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mad_u16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x41,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mad_u16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x41,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1155,6 +1310,12 @@ v_mad_u16_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_mad_u32_u16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x59,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mad_u32_u16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x59,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mad_u32_u16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x59,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mad_u32_u16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x59,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1191,6 +1352,12 @@ v_mad_u32_u16_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi: v_mad_u32_u24_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0b,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mad_u32_u24_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0b,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mad_u32_u24_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x0b,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mad_u32_u24_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x0b,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1227,6 +1394,12 @@ v_mad_u32_u24_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi: v_max3_num_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2c,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_max3_num_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2c,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_max3_num_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2c,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_max3_num_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2c,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1263,6 +1436,12 @@ v_max3_num_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0, v_max3_num_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_max3_num_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2a,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_max3_num_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2a,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_max3_num_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2a,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1299,6 +1478,12 @@ v_max3_num_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0, v_max3_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_max3_i16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4d,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_max3_i16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4d,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_max3_i16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4d,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1332,6 +1517,12 @@ v_max3_i16_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_max3_i32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_max3_i32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1d,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_max3_i32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1d,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_max3_i32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1d,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1368,6 +1559,12 @@ v_max3_i32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_max3_u16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4e,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_max3_u16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4e,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_max3_u16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4e,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_max3_u16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4e,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1401,6 +1598,12 @@ v_max3_u16_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_max3_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1e,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_max3_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1e,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_max3_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1e,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_max3_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1e,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1455,6 +1658,12 @@ v_max_u16_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_maxmin_num_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6b,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maxmin_num_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6b,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maxmin_num_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6b,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maxmin_num_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6b,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1491,6 +1700,12 @@ v_maxmin_num_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0, v_maxmin_num_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x69,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maxmin_num_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x69,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maxmin_num_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x69,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maxmin_num_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x69,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1527,6 +1742,12 @@ v_maxmin_num_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0, v_maxmin_i32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x64,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maxmin_i32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x64,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maxmin_i32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x64,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maxmin_i32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x64,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1563,6 +1784,12 @@ v_maxmin_i32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_maxmin_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x62,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maxmin_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x62,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maxmin_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x62,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maxmin_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x62,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1617,6 +1844,12 @@ v_mbcnt_lo_u32_b32_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_med3_num_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x32,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_med3_num_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x32,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_med3_num_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x32,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_med3_num_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x32,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1653,6 +1886,12 @@ v_med3_num_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0, v_med3_num_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x31,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_med3_num_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x31,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_med3_num_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x31,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_med3_num_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x31,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1689,6 +1928,12 @@ v_med3_num_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0, v_med3_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x50,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_med3_i16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x50,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_med3_i16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x50,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_med3_i16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x50,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1722,6 +1967,12 @@ v_med3_i16_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_med3_i32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x20,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_med3_i32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x20,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_med3_i32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x20,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_med3_i32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x20,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1758,6 +2009,12 @@ v_med3_i32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_med3_u16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x51,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_med3_u16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x51,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_med3_u16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x51,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_med3_u16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x51,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1791,6 +2048,12 @@ v_med3_u16_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_med3_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x21,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_med3_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x21,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_med3_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x21,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_med3_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x21,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1827,6 +2090,12 @@ v_med3_u32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_min3_num_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2b,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_min3_num_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2b,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_min3_num_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2b,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_min3_num_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2b,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1863,6 +2132,12 @@ v_min3_num_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0, v_min3_num_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x29,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_min3_num_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x29,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_min3_num_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x29,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_min3_num_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x29,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1899,6 +2174,12 @@ v_min3_num_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0, v_min3_i16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_min3_i16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4a,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_min3_i16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4a,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_min3_i16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4a,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1932,6 +2213,12 @@ v_min3_i16_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_min3_i32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_min3_i32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1a,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_min3_i32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1a,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_min3_i32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1a,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -1968,6 +2255,12 @@ v_min3_i32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_min3_u16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4b,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_min3_u16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4b,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_min3_u16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x4b,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_min3_u16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x4b,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2001,6 +2294,12 @@ v_min3_u16_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_min3_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1b,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_min3_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1b,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_min3_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x1b,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_min3_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x1b,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2055,6 +2354,12 @@ v_min_u16_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_minmax_num_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6a,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minmax_num_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6a,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minmax_num_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6a,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minmax_num_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6a,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2091,6 +2396,12 @@ v_minmax_num_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0, v_minmax_num_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x68,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minmax_num_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x68,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minmax_num_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x68,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minmax_num_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x68,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2127,6 +2438,12 @@ v_minmax_num_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0, v_minmax_i32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x65,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minmax_i32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x65,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minmax_i32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x65,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minmax_i32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x65,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2163,6 +2480,12 @@ v_minmax_i32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_minmax_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x63,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minmax_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x63,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minmax_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x63,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minmax_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x63,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2199,6 +2522,9 @@ v_minmax_u32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_msad_u8_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x39,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_msad_u8_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x39,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + v_msad_u8_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x39,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2244,6 +2570,12 @@ v_mul_lo_u16_e64_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0 v_mullit_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x18,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_mullit_f32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x18,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_mullit_f32_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x18,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_mullit_f32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x18,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2280,6 +2612,12 @@ v_mullit_f32_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0, v_or3_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x58,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_or3_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x58,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_or3_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x58,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_or3_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x58,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2337,6 +2675,12 @@ v_pack_b32_f16_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 v_perm_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x44,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_perm_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x44,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_perm_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x44,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_perm_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x44,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2373,6 +2717,9 @@ v_perm_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_sad_hi_u8_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x23,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_sad_hi_u8_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x23,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + v_sad_hi_u8_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x23,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2409,6 +2756,12 @@ v_sad_hi_u8_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_sad_u16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x24,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_sad_u16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x24,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_sad_u16_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x24,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_sad_u16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x24,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2445,6 +2798,12 @@ v_sad_u16_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_sad_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x25,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_sad_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x25,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_sad_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x25,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_sad_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x25,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2481,6 +2840,9 @@ v_sad_u32_e64_dpp v255, v255, v255, src_scc clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_sad_u8_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x22,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_sad_u8_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x22,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + v_sad_u8_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x22,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2518,6 +2880,10 @@ v_sub_co_u32_e64_dpp v5, s6, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x06,0x01,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_sub_co_u32_e64_dpp v5, s6, v1, s2 dpp8:[7,6,5,4,3,2,1,0] +// W32: [0x05,0x06,0x01,0xd7,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05] +// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_sub_co_u32_e64_dpp v5, s105, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x69,0x01,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -2538,6 +2904,10 @@ v_sub_co_u32_e64_dpp v5, s[12:13], v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W64: [0x05,0x0c,0x01,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_sub_co_u32_e64_dpp v5, s[12:13], v1, s2 dpp8:[7,6,5,4,3,2,1,0] +// W64: [0x05,0x0c,0x01,0xd7,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05] +// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_sub_co_u32_e64_dpp v5, s[104:105], v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W64: [0x05,0x68,0x01,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -2584,6 +2954,10 @@ v_subrev_co_u32_e64_dpp v5, s6, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x06,0x02,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_subrev_co_u32_e64_dpp v5, s6, v1, s2 dpp8:[7,6,5,4,3,2,1,0] +// W32: [0x05,0x06,0x02,0xd7,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05] +// W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_subrev_co_u32_e64_dpp v5, s105, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W32: [0x05,0x69,0x02,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W64-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -2608,6 +2982,10 @@ v_subrev_co_u32_e64_dpp v5, s[104:105], v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W64: [0x05,0x68,0x02,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction +v_subrev_co_u32_e64_dpp v5, s[104:105], v1, s2 dpp8:[7,6,5,4,3,2,1,0] +// W64: [0x05,0x68,0x02,0xd7,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05] +// W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction + v_subrev_co_u32_e64_dpp v5, vcc, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // W64: [0x05,0x6a,0x02,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] // W32-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: invalid operand for instruction @@ -2622,6 +3000,12 @@ v_subrev_co_u32_e64_dpp v255, null, v255, v255 clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 v_xad_u32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x45,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_xad_u32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x45,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_xad_u32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x45,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_xad_u32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x45,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2658,6 +3042,12 @@ v_xad_u32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 v_xor3_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x40,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_xor3_b32_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x40,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_xor3_b32_e64_dpp v5, v1, 10, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x40,0xd6,0xe9,0x14,0x0d,0x04,0x01,0x77,0x39,0x05] + v_xor3_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x40,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -2983,7 +3373,7 @@ v_dot2_f16_f16_e64_dpp v0, s1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] // GFX12-ERR: :[[@LINE-1]]:{{[0-9]+}}: error: invalid operand for instruction v_dot2_f16_f16_e64_dpp v0, v1, s2, v3 dpp8:[0,1,2,3,4,4,4,4] -// GFX12-ERR: :[[@LINE-1]]:{{[0-9]+}}: error: invalid operand for instruction +// GFX12: [0x00,0x00,0x66,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x88,0x46,0x92] v_dot2_f16_f16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] // GFX12: [0x00,0x60,0x66,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92] @@ -3004,7 +3394,7 @@ v_dot2_bf16_bf16_e64_dpp v0, s1, v2, v3 dpp8:[0,1,2,3,4,4,4,4] // GFX12-ERR: :[[@LINE-1]]:{{[0-9]+}}: error: invalid operand for instruction v_dot2_bf16_bf16_e64_dpp v0, v1, s2, v3 dpp8:[0,1,2,3,4,4,4,4] -// GFX12-ERR: :[[@LINE-1]]:{{[0-9]+}}: error: invalid operand for instruction +// GFX12: [0x00,0x00,0x67,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x88,0x46,0x92] v_dot2_bf16_bf16_e64_dpp v0, v1, v2, v3 op_sel:[0,0,1,1] dpp8:[0,1,2,3,4,4,4,4] // GFX12: [0x00,0x60,0x67,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x88,0x46,0x92] @@ -3066,6 +3456,12 @@ v_maximum_f16 v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 v_minimum3_f32 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minimum3_f32 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2d,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minimum3_f32 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2d,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minimum3_f32 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2d,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3102,6 +3498,12 @@ v_minimum3_f32 v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0,0,0,0, v_maximum3_f32 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2e,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maximum3_f32 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2e,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maximum3_f32 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2e,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maximum3_f32 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2e,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3138,6 +3540,12 @@ v_maximum3_f32 v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0,0,0,0, v_minimum3_f16 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2f,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minimum3_f16 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2f,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minimum3_f16 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x2f,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minimum3_f16 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x2f,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3174,6 +3582,12 @@ v_minimum3_f16 v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] f v_maximum3_f16 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x30,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maximum3_f16 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x30,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maximum3_f16 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x30,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maximum3_f16 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x30,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3210,6 +3624,12 @@ v_maximum3_f16 v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] f v_maximumminimum_f32 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6d,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maximumminimum_f32 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6d,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maximumminimum_f32 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6d,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maximumminimum_f32 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6d,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3246,6 +3666,12 @@ v_maximumminimum_f32 v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0, v_minimummaximum_f32 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6c,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minimummaximum_f32 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6c,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minimummaximum_f32 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6c,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minimummaximum_f32 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6c,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3282,6 +3708,12 @@ v_minimummaximum_f32 v255, -|v255|, -|v255|, -|src_scc| clamp div:2 dpp8:[0,0,0, v_maximumminimum_f16 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6f,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_maximumminimum_f16 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6f,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_maximumminimum_f16 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6f,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_maximumminimum_f16 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6f,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] @@ -3318,6 +3750,12 @@ v_maximumminimum_f16 v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0, v_minimummaximum_f16 v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6e,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_minimummaximum_f16 v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6e,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] + +v_minimummaximum_f16 v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: [0x05,0x00,0x6e,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] + v_minimummaximum_f16 v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] // GFX12: [0x05,0x00,0x6e,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] |