i965: Fix execution size of scalar TCS barrier setup code.

Previously, the scalar TCS backend was generating:

mov(8)   g17<1>UD     0x00000000UD    { align1 WE_all 1Q compacted };
and(8)   g17.2<1>UD   g0.2<0,1,0>UD   0x0001e000UD  { align1 WE_all 1Q };
shl(8)   g17.2<1>UD   g17.2<8,8,1>UD  0x0000000bUD  { align1 WE_all 1Q };
or(8)    g17.2<1>UD   g17.2<8,8,1>UD  0x00008200UD  { align1 WE_all 1Q };
send(8)  null<1>UW    g17<8,8,1>UD
         gateway (barrier msg) mlen 1 rlen 0 { align1 WE_all 1Q };

This is rubbish - g17.2<8,8,1>UD spans two registers, and is an illegal
region.  Not to mention it clobbers 8 channels of data when we only
wanted to touch m0.2.

Instead, we want:

mov(8)   g17<1>UD     0x00000000UD    { align1 WE_all 1Q compacted };
and(1)   g17.2<1>UD   g0.2<0,1,0>UD   0x0001e000UD  { align1 WE_all };
shl(1)   g17.2<1>UD   g17.2<0,1,0>UD  0x0000000bUD  { align1 WE_all };
or(1)    g17.2<1>UD   g17.2<0,1,0>UD  0x00008200UD  { align1 WE_all };
send(8)  null<1>UW    g17<8,8,1>UD
         gateway (barrier msg) mlen 1 rlen 0 { align1 WE_all 1Q };

Using component() accomplishes this.

Fixes GL44-CTS.tessellation_shader.tessellation_shader_tc_barriers.
barrier_guarded_read_write_calls on Skylake.  Probably fixes other
barrier issues on Gen8+.

v2: Use a group(1, 0) builder so inst->exec_size is set correctly
    (thanks to Francisco Jerez for catching that it was incorrect).

Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com> [v1]
Reviewed-by: Francisco Jerez <currojerez@riseup.net>

diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index df033e163c6af4b4e9bf171c076701036b31cd88..a36765c90c11d1cc3e86b09adc50a37a83378cf3 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -2420,22 +2420,22 @@ fs_visitor::nir_emit_tcs_intrinsic(const fs_builder &bld,
          break;
 
       fs_reg m0 = bld.vgrf(BRW_REGISTER_TYPE_UD, 1);
-      fs_reg m0_2 = byte_offset(m0, 2 * sizeof(uint32_t));
+      fs_reg m0_2 = component(m0, 2);
 
-      const fs_builder fwa_bld = bld.exec_all();
+      const fs_builder chanbld = bld.exec_all().group(1, 0);
 
       /* Zero the message header */
-      fwa_bld.MOV(m0, brw_imm_ud(0u));
+      bld.exec_all().MOV(m0, brw_imm_ud(0u));
 
       /* Copy "Barrier ID" from r0.2, bits 16:13 */
-      fwa_bld.AND(m0_2, retype(brw_vec1_grf(0, 2), BRW_REGISTER_TYPE_UD),
+      chanbld.AND(m0_2, retype(brw_vec1_grf(0, 2), BRW_REGISTER_TYPE_UD),
                   brw_imm_ud(INTEL_MASK(16, 13)));
 
       /* Shift it up to bits 27:24. */
-      fwa_bld.SHL(m0_2, m0_2, brw_imm_ud(11));
+      chanbld.SHL(m0_2, m0_2, brw_imm_ud(11));
 
       /* Set the Barrier Count and the enable bit */
-      fwa_bld.OR(m0_2, m0_2,
+      chanbld.OR(m0_2, m0_2,
                  brw_imm_ud(tcs_prog_data->instances << 8 | (1 << 15)));
 
       bld.emit(SHADER_OPCODE_BARRIER, bld.null_reg_ud(), m0);