[Mesa-dev] [PATCH 1/4] radeonsi: correct maximum wave count per SIMD

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

---
 src/gallium/drivers/radeonsi/si_shader.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index f02fc9e..186a3dd 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -5029,21 +5029,36 @@ static void si_shader_dump_stats(struct si_screen *sscreen,
 			         struct pipe_debug_callback *debug,
 			         unsigned processor,
 				 FILE *file,
 				 bool check_debug_option)
 {
 	const struct si_shader_config *conf = &shader->config;
 	unsigned num_inputs = shader->selector ? shader->selector->info.num_inputs : 0;
 	unsigned code_size = si_get_shader_binary_size(shader);
 	unsigned lds_increment = sscreen->b.chip_class >= CIK ? 512 : 256;
 	unsigned lds_per_wave = 0;
-	unsigned max_simd_waves = 10;
+	unsigned max_simd_waves;
+
+	switch (sscreen->b.family) {
+	/* SGPR initialization bug workaround on Tonga and Iceland reduces
+	 * the wave count to 8. */
+	case CHIP_TONGA:
+	case CHIP_ICELAND:
+	/* These always have 8 waves: */
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+		max_simd_waves = 8;
+		break;
+	default:
+		max_simd_waves = 10;
+	}
 
 	/* Compute LDS usage for PS. */
 	switch (processor) {
 	case PIPE_SHADER_FRAGMENT:
 		/* The minimum usage per wave is (num_inputs * 48). The maximum
 		 * usage is (num_inputs * 48 * 16).
 		 * We can get anything in between and it varies between waves.
 		 *
 		 * The 48 bytes per input for a single primitive is equal to
 		 * 4 bytes/component * 4 components/input * 3 points.
-- 
2.7.4